├── LICENSE
├── README.md
├── backend
├── .env.template
├── .gitignore
├── README.md
├── app.py
├── crons
│ └── repo_metadata_cron.py
├── poetry.lock
├── pyproject.toml
├── src
│ ├── gitsummarize
│ │ ├── __init__.py
│ │ ├── auth
│ │ │ ├── auth.py
│ │ │ └── key_manager.py
│ │ ├── clients
│ │ │ ├── ai_client_abc.py
│ │ │ ├── github.py
│ │ │ ├── google_genai.py
│ │ │ ├── openai.py
│ │ │ └── supabase.py
│ │ ├── constants
│ │ │ └── constants.py
│ │ ├── exceptions
│ │ │ └── exceptions.py
│ │ ├── model
│ │ │ └── repo_metadata.py
│ │ └── prompts
│ │ │ ├── business_logic.py
│ │ │ ├── resource_repo.py
│ │ │ └── technical_documentation.py
│ └── scripts
│ │ ├── get_popular_gh_repos.py
│ │ └── precache_repos.py
└── tests
│ └── __init__.py
└── frontend
├── LICENSE
├── README.md
├── components.json
├── next-env.d.ts
├── next.config.js
├── package-lock.json
├── package.json
├── postcss.config.js
├── prettier.config.js
├── public
├── favicon.ico
├── favicon.png
└── og-image.png
├── src
├── app
│ ├── [username]
│ │ └── [repo]
│ │ │ └── page.tsx
│ ├── _actions
│ │ ├── cache.ts
│ │ ├── github.ts
│ │ └── repo.ts
│ ├── api
│ │ └── generate
│ │ │ └── route.ts
│ ├── layout.tsx
│ ├── page.tsx
│ └── providers.tsx
├── components
│ ├── action-button.tsx
│ ├── api-key-button.tsx
│ ├── api-key-dialog.tsx
│ ├── copy-button.tsx
│ ├── customization-dropdown.tsx
│ ├── export-dropdown.tsx
│ ├── footer.tsx
│ ├── header.tsx
│ ├── hero.tsx
│ ├── loading-animation.tsx
│ ├── loading.tsx
│ ├── main-card.tsx
│ ├── mermaid-diagram.tsx
│ ├── private-repos-dialog.tsx
│ └── ui
│ │ ├── button.tsx
│ │ ├── card.tsx
│ │ ├── dialog.tsx
│ │ ├── input.tsx
│ │ ├── progress.tsx
│ │ ├── switch.tsx
│ │ ├── textarea.tsx
│ │ └── tooltip.tsx
├── env.js
├── lib
│ ├── exampleRepos.ts
│ ├── github.ts
│ ├── supabase.ts
│ └── utils.ts
├── server
│ └── db
│ │ ├── index.ts
│ │ └── schema.ts
└── styles
│ └── globals.css
├── tailwind.config.ts
└── tsconfig.json
/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "[]"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright 2025 Antarix
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
202 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # 🧠 GitSummarize
2 |
3 |
4 |
5 |
6 |
7 | ## **Generate beautiful, world-class documentation from any GitHub repository — instantly.**
8 |
9 | Just replace `hub` with `summarize` in any GitHub URL to generate a live, interactive documentation hub.
10 |
11 | https://gitsummarize.com/
12 |
13 |
14 | ---
15 |
16 | ## 🚀 Features
17 |
18 | GitSummarize analyzes any GitHub repo (public or private) and generates:
19 |
20 | - 📄 **System-level architecture overviews**
21 | - 📁 **Per-directory and file summaries**
22 | - 🧠 **Natural language descriptions of purpose, flow, and structure**
23 | - 🔗 **Business Logic and Rules Extraction**
24 | - 📊 **Architecture diagrams and flows**
25 |
26 | It’s perfect for onboarding, exploring unfamiliar codebases, and writing technical documentation — all powered by Gemini.
27 |
28 | ---
29 |
30 | ## 🧰 Tech Stack
31 |
32 | | Area | Stack |
33 | |------------|-------|
34 | | **Frontend** | Next.js, TypeScript, Tailwind CSS, ShadCN |
35 | | **Backend** | FastAPI, Python, Server Actions |
36 | | **Database** | PostgreSQL (Supabase) |
37 | | **AI** | Gemini 2.5 Pro |
38 | | **Analytics**| PostHog |
39 | | **Hosting** | Vercel (Frontend), Render (Backend) |
40 |
41 | ---
42 |
43 | ## 🤔 Why GitSummarize?
44 |
45 | We wanted to contribute to open-source projects but found it difficult to understand massive codebases quickly.
46 |
47 | GitSummarize automates the hardest part: figuring out *what the code does* and *how it's structured* — giving you useful documentation and high level overview of the codebase.
48 |
49 | ---
50 |
51 | ## 🧪 Local Development / Self-Hosting
52 |
53 | 1. **Clone the repo**
54 | ```bash
55 | git clone https://github.com/antarixxx/gitsummarize
56 | cd gitsummarize
57 | ```
58 |
59 | 2. **Run the Next.js Project**
60 | ```bash
61 | npm run dev
62 | ```
63 |
64 | You can now access the website at `localhost:3000`.
65 |
66 |
67 | ## Contributing
68 |
69 | Contributions are welcome! Please feel free to submit a Pull Request.
70 |
71 | ## Acknowledgements
72 |
73 | Shoutout to [GitIngest](https://gitingest.com/) and [GitDiagram](https://gitdiagram.com/) for the inspiration and styling.
74 |
75 | ## 📈 Rate Limits
76 |
77 | We are currently hosting it for free with rate limits though this is somewhat likely to change in the future based on Gemini's API policies.
78 |
79 | ## 🤔 Future Steps
80 |
81 | - Expand documentation to cover more topics (Setup, Onboarding Guide)
82 | - Add Architecture Diagrams
83 |
84 |
85 | ## Star History
86 |
87 | [](https://www.star-history.com/#antarixxx/gitsummarize&Date)
88 |
--------------------------------------------------------------------------------
/backend/.env.template:
--------------------------------------------------------------------------------
1 | PYTHON_VERSION=3.13.2
2 | POETRY_VERSION=2.1.2
3 | PORT=8000
4 | API_TOKEN=
5 | NUM_GEMINI_KEYS=1
6 | GEMINI_API_KEY_1=
7 | GITHUB_TOKEN=
8 | SUPABASE_URL=
9 | SUPABASE_ANON_KEY=
10 | SUPABASE_ADMIN_KEY=
11 | OPENAI_API_KEY=
--------------------------------------------------------------------------------
/backend/.gitignore:
--------------------------------------------------------------------------------
1 | # Byte-compiled / optimized / DLL files
2 | __pycache__/
3 | *.py[cod]
4 | *$py.class
5 |
6 | # C extensions
7 | *.so
8 |
9 | # Distribution / packaging
10 | .Python
11 | build/
12 | develop-eggs/
13 | dist/
14 | downloads/
15 | eggs/
16 | .eggs/
17 | lib/
18 | lib64/
19 | parts/
20 | sdist/
21 | var/
22 | wheels/
23 | share/python-wheels/
24 | *.egg-info/
25 | .installed.cfg
26 | *.egg
27 | MANIFEST
28 |
29 | # PyInstaller
30 | # Usually these files are written by a python script from a template
31 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
32 | *.manifest
33 | *.spec
34 |
35 | # Installer logs
36 | pip-log.txt
37 | pip-delete-this-directory.txt
38 |
39 | # Unit test / coverage reports
40 | htmlcov/
41 | .tox/
42 | .nox/
43 | .coverage
44 | .coverage.*
45 | .cache
46 | nosetests.xml
47 | coverage.xml
48 | *.cover
49 | *.py,cover
50 | .hypothesis/
51 | .pytest_cache/
52 | cover/
53 |
54 | # Translations
55 | *.mo
56 | *.pot
57 |
58 | # Django stuff:
59 | *.log
60 | local_settings.py
61 | db.sqlite3
62 | db.sqlite3-journal
63 |
64 | # Flask stuff:
65 | instance/
66 | .webassets-cache
67 |
68 | # Scrapy stuff:
69 | .scrapy
70 |
71 | # Sphinx documentation
72 | docs/_build/
73 |
74 | # PyBuilder
75 | .pybuilder/
76 | target/
77 |
78 | # Jupyter Notebook
79 | .ipynb_checkpoints
80 |
81 | # IPython
82 | profile_default/
83 | ipython_config.py
84 |
85 | # pyenv
86 | # For a library or package, you might want to ignore these files since the code is
87 | # intended to run in multiple environments; otherwise, check them in:
88 | # .python-version
89 |
90 | # pipenv
91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies
93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not
94 | # install all needed dependencies.
95 | #Pipfile.lock
96 |
97 | # UV
98 | # Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
99 | # This is especially recommended for binary packages to ensure reproducibility, and is more
100 | # commonly ignored for libraries.
101 | #uv.lock
102 |
103 | # poetry
104 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
105 | # This is especially recommended for binary packages to ensure reproducibility, and is more
106 | # commonly ignored for libraries.
107 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
108 | #poetry.lock
109 |
110 | # pdm
111 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
112 | #pdm.lock
113 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
114 | # in version control.
115 | # https://pdm.fming.dev/latest/usage/project/#working-with-version-control
116 | .pdm.toml
117 | .pdm-python
118 | .pdm-build/
119 |
120 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
121 | __pypackages__/
122 |
123 | # Celery stuff
124 | celerybeat-schedule
125 | celerybeat.pid
126 |
127 | # SageMath parsed files
128 | *.sage.py
129 |
130 | # Environments
131 | .env
132 | .venv
133 | env/
134 | venv/
135 | ENV/
136 | env.bak/
137 | venv.bak/
138 |
139 | # Spyder project settings
140 | .spyderproject
141 | .spyproject
142 |
143 | # Rope project settings
144 | .ropeproject
145 |
146 | # mkdocs documentation
147 | /site
148 |
149 | # mypy
150 | .mypy_cache/
151 | .dmypy.json
152 | dmypy.json
153 |
154 | # Pyre type checker
155 | .pyre/
156 |
157 | # pytype static type analyzer
158 | .pytype/
159 |
160 | # Cython debug symbols
161 | cython_debug/
162 |
163 | # PyCharm
164 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
165 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
166 | # and can be added to the global gitignore or merged into this file. For a more nuclear
167 | # option (not recommended) you can uncomment the following to ignore the entire idea folder.
168 | #.idea/
169 |
170 | # Ruff stuff:
171 | .ruff_cache/
172 |
173 | # PyPI configuration file
174 | .pypirc
175 |
176 | tmp/
177 |
178 | .DS_Store
179 |
--------------------------------------------------------------------------------
/backend/README.md:
--------------------------------------------------------------------------------
1 | # gitsummarize backend
2 |
3 | ## Setup
4 |
5 | Make sure that you have `cd`-ed into `backend`.
6 |
7 | 1. Create a new Python environment (Python 3.13 or above) using `conda`, `venv`, `pipx`, etc.
8 | 2. Install Poetry: `pip install poetry==2.1.2`.
9 | 3. Install dependencies: `poetry install`.
10 | 4. Create a new `.env` file and copy the contents of `.env.template` to it.
11 | 5. Add your GitHub API key to `.env`.
12 | 6. Create a new Supabase project with a table with the following columns:
13 | ```psql
14 | id uuid
15 | repo_url text
16 | business_summary text
17 | technical_documentation text
18 | created_at timestamptz
19 | ```
20 | 7. Add Supabase keys to `.env`.
21 | 8. Add Gemini API keys to `.env`. You can add as many keys as you want.
22 | 9. Set `API_TOKEN` in `.env` to anything you want (preferably something secure).
23 |
24 | ## Running
25 | Again, make sure that you have `cd`-ed into `backend`.
26 |
27 | Run `fastapi run app.py`. Go to `http://0.0.0.0:8000/docs` to see the OpenAPI documentation.
28 |
--------------------------------------------------------------------------------
/backend/app.py:
--------------------------------------------------------------------------------
1 | import asyncio
2 | import logging
3 | import os
4 | from typing import Optional
5 | from dotenv import load_dotenv
6 | from fastapi import FastAPI, HTTPException, Depends
7 | from fastapi.responses import JSONResponse
8 | from gitsummarize.exceptions.exceptions import GitHubAccessError
9 | from pydantic import BaseModel
10 |
11 | from gitsummarize.auth.auth import verify_token
12 | from gitsummarize.auth.key_manager import KeyGroup, KeyManager
13 | from gitsummarize.clients.openai import OpenAIClient
14 | from gitsummarize.clients.supabase import SupabaseClient
15 | from src.gitsummarize.clients.github import GithubClient
16 | from src.gitsummarize.clients.google_genai import GoogleGenAI
17 |
18 | load_dotenv()
19 |
20 | logger = logging.getLogger(__name__)
21 |
22 | gh = GithubClient(os.getenv("GITHUB_TOKEN"))
23 | openai = OpenAIClient(os.getenv("OPENAI_API_KEY"))
24 | supabase = SupabaseClient(os.getenv("SUPABASE_URL"), os.getenv("SUPABASE_ADMIN_KEY"))
25 |
26 | key_manager = KeyManager()
27 | for i in range(1, int(os.getenv("NUM_GEMINI_KEYS")) + 1):
28 | key_manager.add_key(KeyGroup.GEMINI, os.getenv(f"GEMINI_API_KEY_{i}"))
29 |
30 |
31 | app = FastAPI()
32 |
33 |
34 | class SummarizeRequest(BaseModel):
35 | repo_url: str
36 | gemini_key: Optional[str] = None
37 |
38 |
39 | @app.post("/summarize", operation_id="summarize_repo")
40 | async def summarize(request: SummarizeRequest, _: str = Depends(verify_token)):
41 | if not _validate_repo_url(request.repo_url):
42 | raise HTTPException(status_code=400, detail="Invalid GitHub URL")
43 | logger.info(f"Summarizing repository: {request.repo_url}")
44 |
45 | directory_structure = await gh.get_directory_structure_from_url(request.repo_url)
46 | all_content = await gh.get_all_content_from_url(request.repo_url)
47 |
48 | key_1 = request.gemini_key or key_manager.get_key(KeyGroup.GEMINI)
49 | key_2 = request.gemini_key or key_manager.get_key(KeyGroup.GEMINI)
50 |
51 | try:
52 | client_1, client_2 = GoogleGenAI(key_1), GoogleGenAI(key_2)
53 | business_summary = await client_1.get_business_summary(
54 | directory_structure, all_content
55 | )
56 | technical_documentation = await client_2.get_technical_documentation(
57 | directory_structure, all_content
58 | )
59 | except Exception as e:
60 | raise HTTPException(status_code=500, detail=str(e))
61 |
62 | supabase.insert_repo_summary(
63 | request.repo_url, business_summary, technical_documentation
64 | )
65 | try:
66 | await _update_repo_metadata(request.repo_url)
67 | except GitHubAccessError as e:
68 | logger.error(f"Error updating repo metadata for {request.repo_url}: {e}")
69 | return JSONResponse(content={"message": "Repository summarized successfully"})
70 |
71 |
72 | @app.post("/repo-metadata-cron")
73 | async def repo_metadata_cron(_: str = Depends(verify_token)):
74 | repo_urls = supabase.get_all_repo_urls()
75 | for repo_url in repo_urls:
76 | try:
77 | metadata = await gh.get_repo_metadata_from_url(repo_url)
78 | supabase.upsert_repo_metadata(repo_url, metadata)
79 | except GitHubAccessError as e:
80 | logger.error(f"Error updating repo metadata for {repo_url}: {e}")
81 |
82 |
83 | @app.post("/summarize-local", operation_id="summarize_store_local")
84 | async def summarize_store_local(
85 | request: SummarizeRequest, _: str = Depends(verify_token)
86 | ):
87 | if not _validate_repo_url(request.repo_url):
88 | raise HTTPException(status_code=400, detail="Invalid GitHub URL")
89 | logger.info(f"Summarizing repository: {request.repo_url}")
90 |
91 | directory_structure = await gh.get_directory_structure_from_url(request.repo_url)
92 | all_content = await gh.get_all_content_from_url(request.repo_url)
93 |
94 | business_summary, technical_documentation = await asyncio.gather(
95 | openai.get_business_summary(directory_structure, all_content),
96 | openai.get_technical_documentation(directory_structure, all_content),
97 | )
98 |
99 | with open("tmp/openai/business_summary.txt", "w") as f:
100 | f.write(business_summary)
101 | with open("tmp/openai/technical_documentation.txt", "w") as f:
102 | f.write(technical_documentation)
103 |
104 |
105 | def _validate_repo_url(repo_url: str) -> bool:
106 | return repo_url.startswith("https://github.com/")
107 |
108 |
109 | async def _update_repo_metadata(repo_url: str):
110 | try:
111 | metadata = await gh.get_repo_metadata_from_url(repo_url)
112 | supabase.upsert_repo_metadata(repo_url, metadata)
113 | except GitHubAccessError as e:
114 | logger.error(f"Error updating repo metadata for {repo_url}: {e}")
115 |
--------------------------------------------------------------------------------
/backend/crons/repo_metadata_cron.py:
--------------------------------------------------------------------------------
1 | import asyncio
2 | import logging
3 | from gitsummarize.clients import supabase
4 | from gitsummarize.clients.github import GithubClient
5 | import os
6 |
7 | from gitsummarize.exceptions.exceptions import GitHubAccessError
8 |
9 | logger = logging.getLogger(__name__)
10 |
11 | gh = GithubClient(os.getenv("GITHUB_TOKEN"))
12 | supabase = supabase.SupabaseClient(os.getenv("SUPABASE_URL"), os.getenv("SUPABASE_ADMIN_KEY"))
13 |
14 | async def main():
15 | repo_urls = supabase.get_all_repo_urls()
16 | for repo_url in repo_urls:
17 | try:
18 | metadata = await gh.get_repo_metadata_from_url(repo_url)
19 | supabase.upsert_repo_metadata(repo_url, metadata)
20 | except GitHubAccessError as e:
21 | logger.error(f"Error updating repo metadata for {repo_url}: {e}")
22 |
23 |
24 | if __name__ == "__main__":
25 | asyncio.run(main())
26 |
--------------------------------------------------------------------------------
/backend/pyproject.toml:
--------------------------------------------------------------------------------
1 | [project]
2 | name = "gitsummarize"
3 | version = "0.1.0"
4 | description = ""
5 | authors = [
6 | {name = "Antarix N",email = "antarix18@gmail.com"}
7 | ]
8 | readme = "README.md"
9 | requires-python = ">=3.13,<4.0"
10 | dependencies = [
11 | "google-genai (>=1.8.0,<2.0.0)",
12 | "fastapi[standard] (>=0.115.12,<0.116.0)",
13 | "aiohttp (>=3.11.14,<4.0.0)",
14 | "python-dotenv (>=1.1.0,<2.0.0)",
15 | "supabase (>=2.15.0,<3.0.0)",
16 | "openai (>=1.69.0,<2.0.0)",
17 | ]
18 |
19 | [tool.poetry]
20 | packages = [{include = "gitsummarize", from = "src"}]
21 |
22 |
23 | [build-system]
24 | requires = ["poetry-core>=2.0.0,<3.0.0"]
25 | build-backend = "poetry.core.masonry.api"
26 |
--------------------------------------------------------------------------------
/backend/src/gitsummarize/__init__.py:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/antarixxx/gitsummarize/0c6781f953f51b5539a01ebbbffec5ff15f4e7b8/backend/src/gitsummarize/__init__.py
--------------------------------------------------------------------------------
/backend/src/gitsummarize/auth/auth.py:
--------------------------------------------------------------------------------
1 | from dotenv import load_dotenv
2 | from fastapi import Security, HTTPException
3 | from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
4 | import os
5 |
6 | load_dotenv()
7 |
8 | API_TOKEN = os.getenv("API_TOKEN")
9 |
10 | security_scheme = HTTPBearer(description="Enter your API token")
11 |
12 | def verify_token(credentials: HTTPAuthorizationCredentials = Security(security_scheme)):
13 | if not credentials:
14 | raise HTTPException(status_code=401, detail="Authorization header missing")
15 |
16 | token = credentials.credentials
17 | if token != API_TOKEN:
18 | raise HTTPException(status_code=401, detail="Invalid token")
19 |
20 | return token
--------------------------------------------------------------------------------
/backend/src/gitsummarize/auth/key_manager.py:
--------------------------------------------------------------------------------
1 | from collections import defaultdict
2 | from enum import StrEnum
3 | import itertools
4 | import random
5 |
6 |
7 | class KeyGroup(StrEnum):
8 | OPENAI = "openai"
9 | GEMINI = "gemini"
10 |
11 |
12 | class KeyManager:
13 | def __init__(self):
14 | self.keys = defaultdict(list)
15 | self.iterators = {}
16 |
17 | def add_key(self, group: KeyGroup, key: str):
18 | self.keys[group].append(key)
19 | self.iterators[group] = itertools.cycle(self.keys[group])
20 | random.shuffle(self.keys[group])
21 |
22 | def get_key(self, group: KeyGroup) -> str:
23 | return next(self.iterators[group])
24 |
--------------------------------------------------------------------------------
/backend/src/gitsummarize/clients/ai_client_abc.py:
--------------------------------------------------------------------------------
1 | from abc import ABC, abstractmethod
2 |
3 |
4 | class AIBaseClient(ABC):
5 | @abstractmethod
6 | def get_business_summary(self, prompt: str) -> str:
7 | pass
8 |
9 | @abstractmethod
10 | def get_technical_documentation(self, prompt: str) -> str:
11 | pass
12 |
13 | def _truncate_text(self, text: str, max_tokens: int, multiplier: float = 3.7) -> str:
14 | return text[: int(max_tokens * multiplier)]
--------------------------------------------------------------------------------
/backend/src/gitsummarize/clients/github.py:
--------------------------------------------------------------------------------
1 | import asyncio
2 | import base64
3 | from itertools import batched
4 | import logging
5 | from pathlib import Path
6 | from textwrap import dedent
7 | import zipfile
8 | import aiohttp
9 | from typing import Dict, List
10 |
11 | from gitsummarize.constants.constants import VALID_FILE_EXTENSIONS
12 | from gitsummarize.exceptions.exceptions import (
13 | GitHubAccessError,
14 | GitHubNotFoundError,
15 | GitHubRateLimitError,
16 | GitHubTreeError,
17 | )
18 | from gitsummarize.model.repo_metadata import RepoMetadata
19 |
20 | logger = logging.getLogger(__name__)
21 |
22 | FILE_LIMIT = 100 * 1000 # 100kb
23 |
24 |
25 | class GithubClient:
26 | def __init__(self, token: str):
27 | self.token = token
28 | self.headers = {"Authorization": f"Bearer {self.token}"}
29 |
30 | async def get_repo_metadata_from_url(self, gh_url: str) -> RepoMetadata:
31 | owner, repo = self._parse_gh_url(gh_url)
32 | return await self.get_repo_metadata(owner, repo)
33 |
34 | async def get_repo_metadata(self, owner: str, repo: str) -> RepoMetadata:
35 | url = f"https://api.github.com/repos/{owner}/{repo}"
36 | async with aiohttp.ClientSession() as session:
37 | async with session.get(url, headers=self.headers) as response:
38 | data = await response.json()
39 | if response.status != 200:
40 | raise GitHubAccessError(owner, repo)
41 | return RepoMetadata(
42 | num_stars=data["stargazers_count"],
43 | num_forks=data["forks_count"],
44 | language=data["language"],
45 | description=data["description"],
46 | )
47 |
48 | async def get_all_content_from_url(self, gh_url: str) -> str:
49 | owner, repo = self._parse_gh_url(gh_url)
50 | zip_path = await self.download_repository_zip(owner, repo)
51 | return await self.get_all_content_from_zip(zip_path)
52 |
53 | async def get_directory_structure_from_url(self, gh_url: str) -> str:
54 | owner, repo = self._parse_gh_url(gh_url)
55 | return await self.get_directory_structure(owner, repo)
56 |
57 | async def get_all_content_from_zip(self, path: Path) -> str:
58 | with zipfile.ZipFile(path, "r") as zip_ref:
59 | valid_files = [
60 | file
61 | for file in zip_ref.namelist()
62 | if file.endswith(VALID_FILE_EXTENSIONS)
63 | ]
64 |
65 | formatted_content = []
66 | for file in valid_files:
67 | try:
68 | if zip_ref.getinfo(file).file_size > FILE_LIMIT:
69 | logger.warning(f"Skipping file: {file} because it is too large")
70 | continue
71 | decoded_content = zip_ref.read(file).decode("utf-8")
72 | except UnicodeDecodeError:
73 | logger.warning(f"Failed to decode content for file: {file}")
74 | continue
75 | formatted_content.append(
76 | self._get_formatted_content(
77 | self._get_file_name_from_zip_name(file),
78 | decoded_content,
79 | )
80 | )
81 |
82 | return "\n\n".join(formatted_content)
83 |
84 | async def download_repository_zip(self, owner: str, repo: str) -> Path:
85 | url = f"https://api.github.com/repos/{owner}/{repo}/zipball"
86 | async with aiohttp.ClientSession() as session:
87 | async with session.get(url, headers=self.headers) as response:
88 | with open(f"/tmp/{repo}.zip", "wb") as f:
89 | f.write(await response.content.read())
90 | return Path(f"/tmp/{repo}.zip")
91 |
92 | async def get_directory_structure(self, owner: str, repo: str) -> str:
93 | """Get the directory structure of a repository in a tree-like format."""
94 | default_branch = await self._get_default_branch(owner, repo)
95 | latest_commit = await self._get_latest_commit(owner, repo, default_branch)
96 | tree_sha = await self._get_tree_sha(owner, repo, latest_commit)
97 |
98 | url = f"https://api.github.com/repos/{owner}/{repo}/git/trees/{tree_sha}?recursive=1"
99 | async with aiohttp.ClientSession() as session:
100 | async with session.get(url, headers=self.headers) as response:
101 | await self._raise_for_status(owner, repo, response)
102 | try:
103 | data = await response.json()
104 | except Exception as e:
105 | logger.error(f"Error parsing JSON response: {e}")
106 | raise GitHubTreeError(owner, repo)
107 |
108 | # Build directory structure
109 | structure = self._build_directory_structure(data["tree"])
110 | return self._format_directory_structure(structure)
111 |
112 | async def get_popular_repos(self, num_repos: int = 1000) -> list[dict]:
113 | items = []
114 | page = 1
115 | per_page = min(100, num_repos) # GitHub max per page is 100
116 | remaining = num_repos
117 |
118 | while remaining > 0:
119 | current_per_page = min(per_page, remaining)
120 | url = f"https://api.github.com/search/repositories?q=stars:>1000&sort=stars&order=desc&page={page}&per_page={current_per_page}"
121 |
122 | async with aiohttp.ClientSession() as session:
123 | async with session.get(url, headers=self.headers) as response:
124 | await self._raise_for_status("search", "repositories", response)
125 | data = await response.json()
126 |
127 | if not data.get("items"):
128 | break
129 |
130 | items.extend(data["items"])
131 | if len(data["items"]) < current_per_page:
132 | break
133 |
134 | remaining -= len(data["items"])
135 | page += 1
136 |
137 | if len(items) >= num_repos:
138 | break
139 | print(f"Fetched {len(items)} repos so far")
140 | await asyncio.sleep(1)
141 |
142 | return items[:num_repos] # Ensure we don't return more than requested
143 |
144 | def _parse_gh_url(self, gh_url: str) -> tuple[str, str]:
145 | """Parse a GitHub URL into owner, repo, and path."""
146 | # Remove the protocol part if present
147 | gh_url = gh_url.replace("https://", "").replace("http://", "")
148 |
149 | # Split by '/' and take the last two parts
150 | parts = gh_url.split("/")
151 | if len(parts) < 2:
152 | raise ValueError("Invalid GitHub URL")
153 | owner = parts[-2]
154 | repo = parts[-1]
155 | return owner, repo
156 |
157 | def _get_file_name_from_zip_name(self, zip_name: str) -> str:
158 | zip_name = zip_name.split("/")
159 | root_dir = zip_name[0]
160 | return "-".join(root_dir.split("-")[1:-1]) + "/" + "/".join(zip_name[1:])
161 |
162 | async def _raise_for_status(
163 | self, owner: str, repo: str, response: aiohttp.ClientResponse
164 | ):
165 | if response.status == 404:
166 | raise GitHubNotFoundError(owner, repo)
167 | elif response.status in (429, 403):
168 | raise GitHubRateLimitError(owner, repo)
169 | elif response.status != 200:
170 | raise GitHubAccessError(owner, repo)
171 |
172 | async def _get_default_branch(self, owner: str, repo: str) -> str:
173 | url = f"https://api.github.com/repos/{owner}/{repo}"
174 | async with aiohttp.ClientSession() as session:
175 | async with session.get(url, headers=self.headers) as response:
176 | data = await response.json()
177 | return data["default_branch"]
178 |
179 | async def _get_latest_commit(self, owner: str, repo: str, branch: str) -> str:
180 | url = f"https://api.github.com/repos/{owner}/{repo}/commits/{branch}"
181 | async with aiohttp.ClientSession() as session:
182 | async with session.get(url, headers=self.headers) as response:
183 | data = await response.json()
184 | return data["sha"]
185 |
186 | async def _get_tree_sha(self, owner: str, repo: str, commit_sha: str) -> str:
187 | url = f"https://api.github.com/repos/{owner}/{repo}/commits/{commit_sha}"
188 | async with aiohttp.ClientSession() as session:
189 | async with session.get(url, headers=self.headers) as response:
190 | data = await response.json()
191 | return data["commit"]["tree"]["sha"]
192 |
193 | def _build_directory_structure(self, tree: List[Dict]) -> Dict:
194 | """Build a nested dictionary representing the directory structure."""
195 | structure = {}
196 | for item in tree:
197 |
198 | path_parts = item["path"].split("/")
199 | current = structure
200 | for i, part in enumerate(path_parts[:-1]):
201 | if part not in current:
202 | current[part] = {}
203 | current = current[part]
204 | if path_parts[-1]: # Don't add empty string for root
205 | current[path_parts[-1]] = item
206 | return structure
207 |
208 | def _format_directory_structure(
209 | self, structure: Dict, prefix: str = "", is_last: bool = True
210 | ) -> str:
211 | """Format the directory structure into a tree-like string."""
212 | if not isinstance(structure, dict):
213 | return ""
214 |
215 | lines = []
216 | items = sorted(structure.items())
217 | for i, (name, value) in enumerate(items):
218 | is_last_item = i == len(items) - 1
219 | connector = "└── " if is_last_item else "├── "
220 | if isinstance(value, dict) and value["type"] == "tree":
221 | # Directory
222 | lines.append(f"{prefix}{connector}{name}/")
223 | new_prefix = prefix + (" " if is_last_item else "│ ")
224 | lines.append(
225 | self._format_directory_structure(value, new_prefix, is_last_item)
226 | )
227 | elif isinstance(value, dict) and value["type"] == "blob":
228 | lines.append(f"{prefix}{connector}{name}")
229 |
230 | return "\n".join(lines)
231 |
232 | def _get_formatted_content(self, path: str, content: str) -> str:
233 | return dedent(
234 | f"""
235 | =============================================================================
236 | File: {path}
237 | =============================================================================
238 | {content}
239 | """
240 | )
241 |
--------------------------------------------------------------------------------
/backend/src/gitsummarize/clients/google_genai.py:
--------------------------------------------------------------------------------
1 | import re
2 | from aiohttp import ClientError
3 | from google import genai
4 | from google.genai import types
5 |
6 | from gitsummarize.clients.ai_client_abc import AIBaseClient
7 | from gitsummarize.prompts.business_logic import BUSINESS_SUMMARY_PROMPT
8 | from gitsummarize.prompts.technical_documentation import TECHNICAL_DOCUMENTATION_PROMPT
9 |
10 | ALLOWED_INPUT_TOKENS_COUNT = 1_048_576
11 | TIMEOUT = 1000 * 60 * 20 # 20 minutes
12 |
13 |
14 | class GoogleGenAI(AIBaseClient):
15 | def __init__(self, api_key: str):
16 | self.client = genai.Client(api_key=api_key)
17 |
18 | async def get_business_summary(
19 | self, directory_structure: str, codebase: str
20 | ) -> str:
21 | prompt = BUSINESS_SUMMARY_PROMPT.format(
22 | directory_structure=directory_structure, codebase=codebase
23 | )
24 | truncated_prompt = self._truncate_text(prompt, 800_000)
25 | try:
26 | response = await self.client.aio.models.generate_content(
27 | model="gemini-2.5-pro-exp-03-25",
28 | contents=truncated_prompt,
29 | config=types.GenerateContentConfig(
30 | http_options=types.HttpOptions(
31 | timeout=TIMEOUT,
32 | ),
33 | ),
34 | )
35 | except Exception as e:
36 | if e.code == 400 and e.status == "INVALID_ARGUMENT":
37 | truncated_prompt = self._truncate_text_from_error(truncated_prompt, e)
38 | response = await self.client.aio.models.generate_content(
39 | model="gemini-2.5-pro-exp-03-25",
40 | contents=truncated_prompt,
41 | config=types.GenerateContentConfig(
42 | http_options=types.HttpOptions(
43 | timeout=TIMEOUT,
44 | ),
45 | ),
46 | )
47 | else:
48 | raise e
49 | return response.text
50 |
51 | async def get_technical_documentation(
52 | self, directory_structure: str, codebase: str
53 | ) -> str:
54 | prompt = TECHNICAL_DOCUMENTATION_PROMPT.format(
55 | directory_structure=directory_structure, codebase=codebase
56 | )
57 | truncated_prompt = self._truncate_text(prompt, 800_000)
58 | try:
59 | response = await self.client.aio.models.generate_content(
60 | model="gemini-2.5-pro-exp-03-25",
61 | contents=truncated_prompt,
62 | config=types.GenerateContentConfig(
63 | http_options=types.HttpOptions(
64 | timeout=TIMEOUT,
65 | ),
66 | ),
67 | )
68 | except Exception as e:
69 | if e.code == 400 and e.status == "INVALID_ARGUMENT":
70 | truncated_prompt = self._truncate_text_from_error(truncated_prompt, e)
71 | response = await self.client.aio.models.generate_content(
72 | model="gemini-2.5-pro-exp-03-25",
73 | contents=truncated_prompt,
74 | config=types.GenerateContentConfig(
75 | http_options=types.HttpOptions(
76 | timeout=TIMEOUT,
77 | ),
78 | ),
79 | )
80 | else:
81 | raise e
82 |
83 | return response.text
84 |
85 | def _truncate_text_from_error(self, prompt: str, error: ClientError) -> str:
86 | input_tokens_count = self._extract_input_tokens_count_from_error(error)
87 | difference = input_tokens_count - ALLOWED_INPUT_TOKENS_COUNT
88 | if difference > 0:
89 | prompt = prompt[: -(difference * 4)]
90 | return prompt
91 |
92 | def _extract_input_tokens_count_from_error(self, error: ClientError) -> int:
93 | regex = r"The input token count \((\d+)\) exceeds the maximum number"
94 | match = re.search(regex, error.message)
95 | if match:
96 | return int(match.group(1))
97 | return 0
98 |
--------------------------------------------------------------------------------
/backend/src/gitsummarize/clients/openai.py:
--------------------------------------------------------------------------------
1 | from openai import AsyncOpenAI
2 | from pydantic import BaseModel
3 |
4 | from gitsummarize.clients.ai_client_abc import AIBaseClient
5 | from gitsummarize.prompts.business_logic import BUSINESS_SUMMARY_PROMPT
6 | from gitsummarize.prompts.resource_repo import RESOURCE_REPO_PROMPT
7 | from gitsummarize.prompts.technical_documentation import TECHNICAL_DOCUMENTATION_PROMPT
8 |
9 |
10 | class IsResourceRepo(BaseModel):
11 | is_resource_repo: bool
12 | reason: str
13 |
14 |
15 | class OpenAIClient(AIBaseClient):
16 | def __init__(self, api_key: str):
17 | self.client = AsyncOpenAI(api_key=api_key)
18 |
19 | async def get_business_summary(
20 | self, directory_structure: str, codebase: str
21 | ) -> str:
22 | prompt = BUSINESS_SUMMARY_PROMPT.format(
23 | directory_structure=directory_structure, codebase=codebase
24 | )
25 | response = await self.client.chat.completions.create(
26 | model="o3-mini",
27 | messages=[
28 | {"role": "user", "content": self._truncate_text(prompt, 200_000, 4.1)}
29 | ],
30 | )
31 | return response.choices[0].message.content
32 |
33 | async def get_technical_documentation(
34 | self, directory_structure: str, codebase: str
35 | ) -> str:
36 | prompt = TECHNICAL_DOCUMENTATION_PROMPT.format(
37 | directory_structure=directory_structure, codebase=codebase
38 | )
39 | response = await self.client.chat.completions.create(
40 | model="o3-mini",
41 | messages=[
42 | {"role": "user", "content": self._truncate_text(prompt, 200_000, 4.1)}
43 | ],
44 | )
45 | return response.choices[0].message.content
46 |
47 | async def get_is_resource_repo(self, repo_info: str) -> IsResourceRepo:
48 | prompt = RESOURCE_REPO_PROMPT.format(repo_info=repo_info)
49 | response = await self.client.beta.chat.completions.parse(
50 | model="gpt-4o-mini",
51 | messages=[{"role": "user", "content": prompt}],
52 | response_format=IsResourceRepo,
53 | )
54 | return response.choices[0].message.parsed
55 |
--------------------------------------------------------------------------------
/backend/src/gitsummarize/clients/supabase.py:
--------------------------------------------------------------------------------
1 | from gitsummarize.model.repo_metadata import RepoMetadata
2 | from supabase import create_client, Client
3 |
4 |
5 | class SupabaseClient:
6 | def __init__(self, url: str, key: str):
7 | self.client = create_client(supabase_url=url, supabase_key=key)
8 |
9 | def insert_repo_summary(self, repo_url: str, business_summary: str, technical_documentation: str):
10 | self.client.table("repo_summaries").insert({
11 | "repo_url": repo_url,
12 | "business_summary": business_summary,
13 | "technical_documentation": technical_documentation
14 | }).execute()
15 |
16 | def check_repo_url_exists(self, repo_url: str) -> str | None:
17 | response = self.client.table("repo_summaries").select("repo_url").eq("repo_url", repo_url).execute()
18 | if len(response.data) == 0:
19 | return None
20 | return response.data[0]
21 |
22 | def get_all_repo_urls(self) -> list[str]:
23 | response = self.client.table("repo_summaries").select("repo_url").execute()
24 | return [row["repo_url"] for row in response.data]
25 |
26 | def upsert_repo_metadata(self, repo_url: str, metadata: RepoMetadata):
27 | self.client.table("repo_metadata").upsert({
28 | "repo_url": repo_url,
29 | "num_stars": metadata.num_stars,
30 | "num_forks": metadata.num_forks,
31 | "language": metadata.language,
32 | "description": metadata.description
33 | }, on_conflict="repo_url").execute()
34 |
--------------------------------------------------------------------------------
/backend/src/gitsummarize/constants/constants.py:
--------------------------------------------------------------------------------
1 | VALID_FILE_EXTENSIONS = (
2 | # Documentation
3 | ".md", ".rst", ".txt", ".adoc", ".asciidoc", ".wiki",
4 |
5 | # Web Development
6 | ".html", ".htm", ".css", ".scss", ".sass", ".less", ".js", ".jsx", ".ts", ".tsx", ".vue",
7 |
8 | # Configuration
9 | ".json", ".yaml", ".yml", ".toml", ".ini", ".cfg", ".conf", ".config", ".properties",
10 | ".env", ".env.*", ".rc", ".rc.*", ".lock", ".lockb", ".lock.json", ".lock.yaml", ".lock.yml",
11 | ".lock.toml", ".lock.lockb",
12 |
13 | # Programming Languages
14 | # Python
15 | ".py", ".pyi", ".pyw", ".pyx", ".pxd", ".pxi", ".pyd", ".so",
16 |
17 | # Java & JVM
18 | ".java", ".kt", ".kts", ".scala", ".groovy", ".clj", ".cljs", ".cljc", ".edn",
19 |
20 | # JavaScript/TypeScript
21 | ".js", ".jsx", ".ts", ".tsx", ".mjs", ".cjs",
22 |
23 | # C/C++
24 | ".c", ".h", ".cpp", ".hpp", ".cc", ".hh", ".cxx", ".hxx", ".inl",
25 |
26 | # Go
27 | ".go", ".mod", ".sum",
28 |
29 | # Rust
30 | ".rs", ".rlib",
31 |
32 | # PHP
33 | ".php", ".phtml", ".php3", ".php4", ".php5", ".php7", ".phps",
34 |
35 | # Ruby
36 | ".rb", ".rbw", ".rake", ".gemspec", ".gemfile", ".gemfile.lock",
37 |
38 | # Swift
39 | ".swift", ".swiftmodule", ".swiftinterface",
40 |
41 | # Dart
42 | ".dart",
43 |
44 | # Shell Scripts
45 | ".sh", ".bash", ".zsh", ".fish", ".csh", ".tcsh", ".ksh", ".mksh",
46 |
47 | # SQL
48 | ".sql", ".psql", ".mysql", ".sqlite", ".db",
49 |
50 | # R
51 | ".r", ".rdata", ".rds", ".rda",
52 |
53 | # MATLAB
54 | ".m", ".mat",
55 |
56 | # Julia
57 | ".jl",
58 |
59 | # Lua
60 | ".lua",
61 |
62 | # Perl
63 | ".pl", ".pm", ".pod", ".t",
64 |
65 | # Haskell
66 | ".hs", ".lhs", ".cabal", ".hsc",
67 |
68 | # F#
69 | ".fs", ".fsi", ".fsx",
70 |
71 | # OCaml
72 | ".ml", ".mli", ".mll", ".mly",
73 |
74 | # Elixir
75 | ".ex", ".exs", ".heex", ".eex",
76 |
77 | # Erlang
78 | ".erl", ".hrl", ".escript",
79 |
80 | # Clojure
81 | ".clj", ".cljs", ".cljc", ".edn",
82 |
83 | # Kotlin
84 | ".kt", ".kts",
85 |
86 | # Nim
87 | ".nim", ".nimble",
88 |
89 | # Crystal
90 | ".cr", ".ecr",
91 |
92 | # Zig
93 | ".zig",
94 |
95 | # V
96 | ".v",
97 |
98 | # Odin
99 | ".odin",
100 |
101 | # Assembly
102 | ".asm", ".s", ".S", ".inc",
103 |
104 | # LaTeX
105 | ".tex", ".ltx", ".sty", ".cls", ".bbl", ".aux", ".log",
106 |
107 | # Markup
108 | ".xml", ".svg", ".xhtml", ".xslt", ".xsl", ".xsd", ".dtd",
109 |
110 | # Data Formats
111 | ".csv", ".tsv", ".jsonl", ".jsonc", ".yaml", ".yml", ".toml", ".ini", ".cfg",
112 |
113 | # Build Systems
114 | ".cmake", ".cmake.in", "CMakeLists.txt", ".ninja", ".gradle", ".gradle.kts",
115 | ".bazel", ".bzl", "BUILD", "WORKSPACE", ".buck", "BUCK", ".podspec", ".podspec.json",
116 |
117 | # Package Management
118 | "package.json", "package-lock.json", "yarn.lock", "pnpm-lock.yaml", "Cargo.lock",
119 | "Pipfile", "Pipfile.lock", "poetry.lock", "requirements.txt", "setup.py", "setup.cfg",
120 | "pyproject.toml", "composer.json", "composer.lock", "Gemfile", "Gemfile.lock",
121 | "Podfile", "Podfile.lock", "pubspec.yaml", "pubspec.lock", "mix.exs", "mix.lock",
122 | "cabal.project", "stack.yaml", "package.yaml", "*.cabal",
123 |
124 | # IDE & Editor Config
125 | ".editorconfig", ".vscode/*", ".idea/*", ".project", ".classpath", ".settings/*",
126 | ".sublime-project", ".sublime-workspace", ".vimrc", ".viminfo", ".vim/*",
127 |
128 | # Git
129 | ".gitignore", ".gitattributes", ".gitmodules",
130 |
131 | # Docker
132 | "Dockerfile", ".dockerignore",
133 |
134 | # CI/CD
135 | ".github/workflows/*", ".gitlab-ci.yml", ".travis.yml", ".circleci/config.yml",
136 | "azure-pipelines.yml", ".drone.yml", ".woodpecker.yml", "Jenkinsfile",
137 |
138 | # Documentation
139 | "README.md", "CHANGELOG.md", "CONTRIBUTING.md", "LICENSE", "AUTHORS",
140 | "docs/*", "*.md", "*.rst", "*.txt", "*.adoc", "*.asciidoc", "*.wiki",
141 | )
--------------------------------------------------------------------------------
/backend/src/gitsummarize/exceptions/exceptions.py:
--------------------------------------------------------------------------------
1 | class GitHubAccessError(Exception):
2 | def __init__(self, owner: str, repo: str):
3 | self.message = f"Failed to access GitHub repository {owner}/{repo}"
4 | super().__init__(self.message)
5 |
6 |
7 | class GitHubRateLimitError(GitHubAccessError):
8 | def __init__(self, owner: str, repo: str):
9 | self.message = f"GitHub rate limit exceeded for repository {owner}/{repo}"
10 | super().__init__(owner, repo)
11 |
12 |
13 | class GitHubNotFoundError(GitHubAccessError):
14 | def __init__(self, owner: str, repo: str):
15 | self.message = f"Repository {owner}/{repo} not found"
16 | super().__init__(owner, repo)
17 |
18 |
19 | class GitHubTreeError(GitHubAccessError):
20 | def __init__(self, owner: str, repo: str):
21 | self.message = f"Failed to get tree for repository {owner}/{repo}"
22 | super().__init__(owner, repo)
23 |
--------------------------------------------------------------------------------
/backend/src/gitsummarize/model/repo_metadata.py:
--------------------------------------------------------------------------------
1 | from pydantic import BaseModel
2 |
3 |
4 | class RepoMetadata(BaseModel):
5 | num_stars: int
6 | num_forks: int
7 | language: str | None
8 | description: str | None
9 |
--------------------------------------------------------------------------------
/backend/src/gitsummarize/prompts/business_logic.py:
--------------------------------------------------------------------------------
1 | BUSINESS_SUMMARY_PROMPT = """
2 | You are a distinguished software architect reviewing the business logic layer of this codebase. Your goal is to produce a clear, structured, and high-level documentation of the business logic implemented in the provided files.
3 |
4 | Focus on **what the code does for the product or business**, not just how it works technically.
5 |
6 | ---
7 |
8 | Please generate a structured design document with the following format:
9 |
10 | 1. **Component Name**
11 | - The name of the business logic component (e.g. BillingService, PermissionsEngine)
12 |
13 | 2. **Purpose**
14 | - What business problem does this logic solve?
15 | - What domain concept does it represent?
16 |
17 | 3. **Key Responsibilities**
18 | - A bullet list of the core behaviors this component implements.
19 | - Try to phrase these as “rules,” “flows,” or “requirements” (e.g. “Users cannot access premium features until payment is verified”).
20 |
21 | 4. **Workflows / Use Cases**
22 | - Describe the primary workflows this logic supports.
23 | - Explain what triggers them, what the steps are, and what the outcomes are.
24 |
25 | 5. **Inputs and Outputs**
26 | - What data does this component operate on?
27 | - What does it return or affect?
28 |
29 | 6. **Dependencies**
30 | - What external services, database models, or internal modules does this depend on?
31 |
32 | 7. **Business Rules & Constraints**
33 | - Any conditional logic or constraints (e.g. pricing tiers, roles, quotas)
34 | - Anything that would be found in a product requirements doc
35 |
36 | 8. **Design Considerations**
37 | - Any notable trade-offs or reasons the logic is written this way
38 | - Any risks or edge cases
39 |
40 | ---
41 |
42 | Use concise, structured language. Think like a staff engineer writing for a new team member trying to understand how this part of the app maps to real product behavior.
43 | IMPORTANT: Please use the ## heading accurately. I will use it to divide the documentation into high level component sections, these headings should be business specific behaviors only.
44 | IMPORTANT: Just output the documentation in markdown format, no other text.
45 |
46 | ---
47 | Here is the directory structure of the codebase:
48 |
49 | {directory_structure}
50 |
51 | ---
52 |
53 | Here is the codebase:
54 |
55 | {codebase}
56 | """
--------------------------------------------------------------------------------
/backend/src/gitsummarize/prompts/resource_repo.py:
--------------------------------------------------------------------------------
1 | RESOURCE_REPO_PROMPT = """
2 | You are a helpful assistant that determines if a repository is a codebase or just a resource repository (collection of resources).
3 | For example, react, pytorch, etc. are codebases, but free-programmin-books, awesome-python, etc. are resource repositories.
4 |
5 | Here is info about the repository:
6 |
7 | {repo_info}
8 |
9 | Please determine if this is a codebase or a resource repository.
10 | """
11 |
--------------------------------------------------------------------------------
/backend/src/gitsummarize/prompts/technical_documentation.py:
--------------------------------------------------------------------------------
1 | TECHNICAL_DOCUMENTATION_PROMPT = """
2 | You are a distinguished software architect and expert technical writer. You specialize in deeply understanding codebases and producing high-quality technical documentation that is both comprehensive and easy to follow.
3 |
4 | Your role is to analyze the given code or repository and generate clear, well-structured documentation. This may include:
5 | • High-level architectural overviews
6 | • Component breakdowns
7 | • Class and function documentation
8 | • Usage examples and onboarding guides
9 | • Configuration and environment setup details
10 | • Diagrams (e.g., Mermaid flowcharts, class diagrams) where helpful
11 |
12 | You think like an engineer reading the code for the first time—curious, meticulous, and detail-oriented. You always strive to capture the “why” behind the implementation, not just the “how”.
13 |
14 | Write in a professional, concise tone. Use bullet points, headers, and code snippets where appropriate. Prioritize clarity, accuracy, and utility for both new contributors and experienced developers.
15 |
16 | When applicable, infer and document:
17 | • The purpose and responsibilities of each module
18 | • The relationships between components
19 | • Trade-offs or design patterns used
20 | • How to extend or customize the code
21 |
22 | Your output should be production-quality documentation suitable for internal engineering wikis or public open-source repositories.
23 |
24 | IMPORTANT: Please use the ## heading accurately. I will use it to divide the documentation into high level component sections.
25 | IMPORTANT: Just output the documentation in markdown format, no other text.
26 |
27 | ---
28 |
29 | Here is the directory structure of the codebase:
30 |
31 | {directory_structure}
32 |
33 | ---
34 |
35 | Here is the codebase:
36 |
37 | {codebase}
38 | """
--------------------------------------------------------------------------------
/backend/src/scripts/get_popular_gh_repos.py:
--------------------------------------------------------------------------------
1 | import asyncio
2 | from itertools import batched
3 | from gitsummarize.clients.github import GithubClient
4 |
5 | from dotenv import load_dotenv
6 | import os
7 |
8 | from gitsummarize.clients.openai import OpenAIClient
9 |
10 | load_dotenv()
11 | openai_client = OpenAIClient(os.getenv("OPENAI_API_KEY"))
12 |
13 |
14 | async def main():
15 | gh = GithubClient(os.getenv("GITHUB_TOKEN"))
16 | # Get up to 500 popular repositories
17 | repos = await gh.get_popular_repos(num_repos=1000)
18 | non_resource_repos = await filter_resource_repos(repos)
19 | print(non_resource_repos)
20 |
21 |
22 | async def filter_resource_repos(repos: list[dict]) -> list[dict]:
23 | non_resource_repos = []
24 | for repos_batch in batched(repos, 100):
25 | tasks = [openai_client.get_is_resource_repo(str(repo)) for repo in repos_batch]
26 | results = await asyncio.gather(*tasks)
27 | for i, result in enumerate(results):
28 | if not result.is_resource_repo:
29 | non_resource_repos.append(repos_batch[i])
30 | return non_resource_repos
31 |
32 |
33 |
34 | if __name__ == "__main__":
35 | asyncio.run(main())
36 |
--------------------------------------------------------------------------------
/backend/src/scripts/precache_repos.py:
--------------------------------------------------------------------------------
1 | import os
2 | from dotenv import load_dotenv
3 | import requests
4 |
5 | from gitsummarize.clients.supabase import SupabaseClient
6 |
7 | load_dotenv()
8 | API_TOKEN = os.getenv("API_TOKEN")
9 |
10 |
11 | def main():
12 | supabase = SupabaseClient(os.getenv("SUPABASE_URL"), os.getenv("SUPABASE_ANON_KEY"))
13 |
14 | with open("tmp/repolist.txt", "r") as f:
15 | repos = f.readlines()
16 | for repo in repos:
17 | repo_summary = supabase.check_repo_url_exists(repo)
18 | if repo_summary:
19 | print(f"Repo {repo} already exists")
20 | continue
21 | else:
22 | print(f"Summarizing repo {repo}")
23 |
24 | url = f"http://0.0.0.0:8000/summarize"
25 | headers = {
26 | "Content-Type": "application/json",
27 | "Authorization": f"Bearer {API_TOKEN}",
28 | }
29 | data = {
30 | "repo_url": repo,
31 | }
32 |
33 | response = requests.post(url, headers=headers, json=data)
34 | print(response.text)
35 |
36 |
37 | if __name__ == "__main__":
38 | main()
39 |
--------------------------------------------------------------------------------
/backend/tests/__init__.py:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/antarixxx/gitsummarize/0c6781f953f51b5539a01ebbbffec5ff15f4e7b8/backend/tests/__init__.py
--------------------------------------------------------------------------------
/frontend/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "[]"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright 2025 Antarix
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
--------------------------------------------------------------------------------
/frontend/README.md:
--------------------------------------------------------------------------------
1 | # 🧠 GitSummarize
2 |
3 |
4 |
5 |
6 |
7 | ## **Generate beautiful, world-class documentation from any GitHub repository — instantly.**
8 |
9 | Just replace `hub` with `summarize` in any GitHub URL to generate a live, interactive documentation hub.
10 |
322 | Turn any GitHub repository into a comprehensive AI-powered documentation hub.
323 |
324 |
325 | PRO TIP: Replace 'hub' with 'summarize' in any
326 | GitHub URL
327 |
328 |
329 |
330 | {/* Pass handleNavigation to MainCard if it needs to trigger loading */}
331 |
332 |
333 |
334 | {/* Explore Section */}
335 |
336 |
Explore Popular Repositories
337 |
338 |
339 | {isDataLoading ? (
340 | // Loading skeletons for data fetching - use fallbackRepos.length to match actual data
341 | [...new Array(fallbackRepos.length)].map((_, index) => (
342 |