3 |
3 |
4 |
5 | 9 | Autonomous and goal-seeking coding agents 10 |
11 | 12 | --- 13 | 14 | **Spellbound** is a [Visual Studio Code extension](https://marketplace.visualstudio.com/items?itemName=mpoteat-vsce.spellbound) that leverages the power of the OpenAI API to create an intelligent coding assistant. With _Spellbound_, you can harness the capabilities of cutting-edge AI to improve your coding experience and productivity. 15 | 16 | ## Installation 17 | 18 | 1. Install the Spellbound VS Code extension from the marketplace. 19 | 2. Obtain an API key for the OpenAI API and configure it in your VS Code settings. 20 | 3. Obtain a Pinecone API key, create a Pinecone index, and configure it in your VS Code settings. 21 | 22 | ## Usage 23 | 24 | To use Spellbound, simply interact with your codebase as usual. Whenever you need help, type your request in the Spellbound dialog. Spellbound will use the OpenAI API to help you generate code, troubleshoot, and offer suggestions. 25 | 26 | Spellbound uses a "thought/action" control loop to create an autonomous coding agent, as described in the **[ReAct paper](https://arxiv.org/abs/2210.03629)**. The agent is able to take actions based on its current thoughts, and its future thoughts are influenced by the results of its actions. 27 | 28 | ## Extension Settings 29 | 30 | | Parameter | Description | Default | Scope | 31 | | --------------------------- | ---------------------------------------------------- | ------- | ------- | 32 | | spellbound.model | Select the AI model used by the Spellbound extension | gpt-4 | | 33 | | spellbound.openai_api_key | Enter your OpenAI API key here, used for inference. | | machine | 34 | | spellbound.pinecone_api_key | Enter your Pinecone API key here, used for search. | | machine | 35 | | spellbound.pinecone_index | Enter your Pinecone index name here, used for search | | machine | 36 | 37 | ### Configuring Settings 38 | 39 | To configure the extension settings, open the Settings editor in Visual Studio Code by clicking on the gear icon in the lower left corner and selecting "Settings" from the menu. In the search bar, type "Spellbound" to filter the settings related to the extension. You can then enter your API keys and select the preferred model from the available options. 40 | 41 | Environment variables `OPENAI_API_KEY` and `PINECONE_API_KEY` will be used in place of the settings if they are set. 42 | 43 | ## Tools 44 | 45 | The following tools are available for use in Spellbound. The underlying AI model uses tools to solve open-ended tasks. 46 | 47 | | Tool | Description | 48 | | ------------------------ | -------------------------------------------------------------------------------------- | 49 | | cat {path} | Read the content of a file at the given path. | 50 | | ls {path, recursive?} | List files and folders at the given path. | 51 | | search {description} | Search for a file or relevant information by description, via vector embedding search. | 52 | | write {path, contents} | Write (or overwrite) the given contents into the specified file. | 53 | | replace {path, old, new} | Replace all occurrences of `old` with `new` in the specified file. | 54 | | ask {question} | Ask a question to the user. | 55 | | npm {script} | Run an npm script (e.g., `npm run [script]`). | 56 | | done {output?} | Indicate that you are done with the task. | 57 | 58 | ## Features 59 | 60 | - Code generation based on natural language input 61 | - Troubleshooting and bug fixing assistance 62 | - Documentation writing and code critique 63 | - Autonomous and goal-seeking coding agents 64 | - Integration with your existing VS Code workflow 65 | 66 | ## Local Development 67 | 68 | To set up the local development environment for the Spellbound extension, see the [LOCAL_SETUP.md](LOCAL_SETUP.md) file. 69 | 70 | ## License 71 | 72 | Spellbound is released under the MIT License. See the LICENSE file for the full license text. 73 | -------------------------------------------------------------------------------- /apps/agentitive-site/.gitignore: -------------------------------------------------------------------------------- 1 | # Dependencies 2 | /node_modules 3 | 4 | # Production 5 | /build 6 | 7 | # Generated files 8 | .docusaurus 9 | .cache-loader 10 | 11 | # Misc 12 | .DS_Store 13 | .env.local 14 | .env.development.local 15 | .env.test.local 16 | .env.production.local 17 | 18 | npm-debug.log* 19 | yarn-debug.log* 20 | yarn-error.log* 21 | -------------------------------------------------------------------------------- /apps/agentitive-site/README.md: -------------------------------------------------------------------------------- 1 | # Website 2 | 3 | This website is built using [Docusaurus 2](https://docusaurus.io/), a modern static website generator. 4 | 5 | ### Installation 6 | 7 | ``` 8 | $ yarn 9 | ``` 10 | 11 | ### Local Development 12 | 13 | ``` 14 | $ yarn start 15 | ``` 16 | 17 | This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server. 18 | 19 | ### Build 20 | 21 | ``` 22 | $ yarn build 23 | ``` 24 | 25 | This command generates static content into the `build` directory and can be served using any static contents hosting service. 26 | 27 | ### Deployment 28 | 29 | Using SSH: 30 | 31 | ``` 32 | $ USE_SSH=true yarn deploy 33 | ``` 34 | 35 | Not using SSH: 36 | 37 | ``` 38 | $ GIT_USER=docs directory.
29 |
30 | ),
31 | },
32 | {
33 | title: 'Powered by React',
34 | Svg: require('@site/static/img/undraw_docusaurus_react.svg').default,
35 | description: (
36 | <>
37 | Extend or customize your website layout by reusing React. Docusaurus can
38 | be extended while reusing the same header and footer.
39 |
40 | ),
41 | },
42 | ];
43 |
44 | function Feature({title, Svg, description}: FeatureItem) {
45 | return (
46 | {description}
53 |