├── .gitignore ├── CHARTER.pdf ├── working-groups ├── coffee-app-sdk │ ├── README.md │ ├── CONTRIBUTING.md │ ├── meeting-cadence.md │ ├── proposal-cover.md │ ├── charter.md │ └── project-overview.md ├── core │ └── CHARTER.md ├── observe-and-eval │ └── CHARTER.md ├── identity │ └── CHARTER.md └── WORKING-GROUPS.md ├── README.md ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── WORKING-GROUP-PROCESSES.md ├── LICENSE.md └── OPERATING_MODEL.md /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | *~ 3 | .idea/ 4 | -------------------------------------------------------------------------------- /CHARTER.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/agntcy/governance/HEAD/CHARTER.pdf -------------------------------------------------------------------------------- /working-groups/coffee-app-sdk/README.md: -------------------------------------------------------------------------------- 1 | # CoffeeAgntcy & App-SDK Working Group 2 | 3 | This directory contains governance and operating docs for the CoffeeAgntcy & app-sdk Working Group (WG). 4 | 5 | - [Charter](./charter.md) 6 | - [Project Overview](./project-overview.md) 7 | - [Contribution Guide](./CONTRIBUTING.md) 8 | - [Meeting Cadence](./meeting-cadence.md) 9 | -------------------------------------------------------------------------------- /working-groups/coffee-app-sdk/CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | # Contributing to CoffeeAgntcy & App-SDK WG 2 | 3 | This WG follows the general AGNTCY contribution guidelines. 4 | 5 | ### How to Contribute 6 | - File issues in the `app-sdk` or `coffeeAgntcy` repos. 7 | - Use labels (`component: sdk`, `component: coffee`, `type: feature`, etc.). 8 | - Discuss proposals in GitHub Discussions. 9 | 10 | ### Communication 11 | - Slack: `coffee-agntcy-app-sdk` 12 | - GitHub Discussions for async feedback. 13 | 14 | ### Membership 15 | - Open to all contributors. 16 | - Voting rights: N contributions in past 90 days. 17 | -------------------------------------------------------------------------------- /working-groups/coffee-app-sdk/meeting-cadence.md: -------------------------------------------------------------------------------- 1 | # WG Meeting Cadence 2 | 3 | - **Weekly Community Call** (Video). Duration: 45 min. 4 | - See the [AGNTCY Calendar](https://calendar.google.com/calendar/u/0/embed?src=admin@ops.agntcy.org) for details 5 | 6 | - **Standing Agenda**: 7 | 1. Status updates 8 | 2. Blockers / escalations 9 | 3. New proposals / RFCs 10 | 4. Action items 11 | 12 | - **Async updates**: Slack `#wg-coffee-app-sdk`. 13 | - **Minutes**: Latest minutes and next agendas sotred in the [Group Google Drive](https://drive.google.com/drive/folders/1vyKYqh_Hlqi9TNdeGopgtHPjU9ogIxrN?usp=share_link) 14 | 15 | 16 | -------------------------------------------------------------------------------- /working-groups/coffee-app-sdk/proposal-cover.md: -------------------------------------------------------------------------------- 1 | # Proposal to Create CoffeeAgntcy & App-SDK Working Group 2 | 3 | We propose forming a new WG under AGNTCY to coordinate the development of the `app-sdk` and `coffeeAgntcy` repositories. 4 | 5 | **Why now:** 6 | - SDK and CoffeeAgntcy evolve together 7 | - Seeing clear interest in evolving the repos together as a reference application 8 | - Clear WG ensures transparency, accountability, and alignment across contributors. 9 | 10 | **Scope:** 11 | - SDK interface design and implementation. 12 | - CoffeeAgntcy as reference multi-agent application. 13 | - Shared demos, docs, and developer patterns. 14 | 15 | We request TSC review and approval in the upcoming meeting. 16 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # AGNTCY Governance 2 | 3 | - [Operation Model](OPERATING_MODEL.md) 4 | - [Github Operations](#github-operations) 5 | 6 | ## Github Operations 7 | 8 | The administration of the `agntcy` github org is conducted by designated admins, 9 | including but not limited to [working-group](working-groups/WORKING-GROUPS.md) 10 | leaders. 11 | 12 | Please use [agntcy discussions](https://github.com/orgs/agntcy/discussions) or 13 | [agntcy slack #git-operations](https://agntcy.slack.com/archives/C08S2BSEF8R) to follow 14 | communication and participate in discussions for topics related to github 15 | operations, e.g. administering users, teams, repos, actions/envs, packages, etc. 16 | 17 | **Administrators/working-group leads:** refer to the [org-admin wiki](https://github.com/agntcy/org-admin/wiki) 18 | -------------------------------------------------------------------------------- /working-groups/core/CHARTER.md: -------------------------------------------------------------------------------- 1 | # AGNTCY Core Working Group Charter 2 | 3 | ## Mission 4 | 5 | The mission of the AGNTCY Core Working Group is to contribute and to maintain the core components and protocols developed within the AGNTCY organization. 6 | 7 | ## Goals 8 | 9 | The primary goal of the Core Working Group is to develop and maintain all core components of AGNTCY, including: 10 | - Agent Gateway Protocol (AGP) 11 | - Agent Directory 12 | - Continuous System Integration Testing (CSIT) 13 | - Open Agentic Schema Framework (OASF) 14 | - Agent Connect Protocol (ACP) 15 | - Workflow server 16 | - IO Mapper 17 | - API bridge 18 | 19 | ## Scope 20 | 21 | This group is responsible for all matters related to the protocols and components listed above. 22 | 23 | ## Core Working Group Roadmap 24 | 25 | To be determined 26 | -------------------------------------------------------------------------------- /working-groups/observe-and-eval/CHARTER.md: -------------------------------------------------------------------------------- 1 | # AGNTCY Observe and Eval Working Group Charter 2 | 3 | ## Mission 4 | 5 | The Observe and Eval working group mission is to contribute to setting and maintaining standards for observability and evaluation of multi-agentic systems. 6 | 7 | ## Goals 8 | 9 | The goals of this working group can be divided into two main axes, observability and evaluation. 10 | 11 | On the observability axis, the main goal is to set up a comprehensive observability solution, taking into account the different AGNTCY components (such as AGP or ACP). 12 | This includes: 13 | - Defining and maintaining an observability data schema integrating component observables. 14 | - Proposing a methodology for multi-agentic systems observability. 15 | - Offering an SDK for observability instrumentation. 16 | - Integrating third-party observability instrumentation. 17 | 18 | On the evaluation axis, the goal is to propose a data schema for evaluation metrics and standardize how ratings for a multi-agentic system is published in the OASF schema. 19 | 20 | ## Scope 21 | 22 | This group would be responsible of everything that is related to observability and evaluation of multi-agentic systems. 23 | This group will contribute to the [OASF](https://github.com/agntcy/oasf) repository. 24 | 25 | ## Observe and Eval Working Group Roadmap 26 | 27 | 28 | **TODO** 29 | -------------------------------------------------------------------------------- /working-groups/identity/CHARTER.md: -------------------------------------------------------------------------------- 1 | # AGNTCY Identity Working Group Charter 2 | 3 | ## Mission 4 | 5 | The mission of this working group is to contribute to the definition of standards focused on identity in multi-agentic systems. 6 | 7 | ## Goals 8 | 9 | The goals of this working group can be summarized as follows: 10 | 11 | - Defining mechanisms enabling the assignment and onboarding of identities for agents, resources, and tools in an open way. 12 | - Ensuring collision-free assignment and use of identities in multi-agentic systems. 13 | - Defining methods enabling trustworthy assignment, onboarding, presentation, verification, and utilization of identities, including mechanisms to authenticate identifiers and their provenance. 14 | - Addressing identity-centric requirements and standardization needs involving human-to-agent, agent-to-tool, agent-to-agent, and agent-to-human interactions. 15 | - Promoting openness and interoperability across multi-agentic systems and ecosystems, including seamless integration with Identity Providers (IdPs), Auth Servers and standard AuthN/AuthZ flows. 16 | 17 | ## Scope 18 | 19 | This working group would be responsible of everything that is related to identity in multi-agentic systems, and will contribute to the [Identity](https://github.com/agntcy/identity) repository. 20 | 21 | ## Identity Working Group Roadmap 22 | 23 | **TO BE DEFINED** 24 | -------------------------------------------------------------------------------- /working-groups/coffee-app-sdk/charter.md: -------------------------------------------------------------------------------- 1 | # AcoffeeAGNTCY & app-sdk Working Group Charter 2 | 3 | ## Mission 4 | Coordinate development and integration across the `app-sdk` and `coffeeAgntcy` repositories. Ensure that new SDK features are validated through CoffeeAgntcy and that real-world app needs drive the sdk and reference application using AGNTCY or other project components 5 | 6 | ## Scope 7 | - Define and evolve SDK interfaces and APIs for agent interoperability. 8 | - Maintain CoffeeAgntcy as a reference multi-agent application. 9 | - Deliver demos, documentation, and patterns for developers adopting AGNTCY. 10 | 11 | ## Deliverables 12 | - Regular SDK releases aligned with coffeeAgntcy features. 13 | - Reference coffeeAgntcy updates (demo workflows, UI). 14 | - Developer guides, patterns, and contribution docs. 15 | 16 | ## Leadership 17 | - Chairs: TBD (initially lead from TSC + one community lead) 18 | - Membership: open to all contributors. Voting rights require N contributions in past 90 days. 19 | 20 | ## Decision Making 21 | - Default to lazy consensus. 22 | - Escalate deadlocks to TSC for resolution. 23 | 24 | ## Meetings 25 | - Biweekly community call (Zoom/Meet). 26 | - Async updates in `#coffee-agntcy-app-sdk` Slack channel. (rename needed) 27 | 28 | ## Reporting 29 | - Quarterly written update to TSC. 30 | - Presentations at TSC meetings as needed. 31 | 32 | ## Sunset 33 | - WG will be dissolved if inactive for 6 months or if TSC determines scope is complete. 34 | -------------------------------------------------------------------------------- /working-groups/coffee-app-sdk/project-overview.md: -------------------------------------------------------------------------------- 1 | # Coffee AGNTCY Platform – GitHub Project Overview 2 | 3 | Welcome to the **Coffee AGNTCY Platform** project! This GitHub Project coordinates work across two core repositories: 4 | 5 | - [`app-sdk`](https://github.com/agntcy/app-sdk): SDK for building interoperable AI agents. 6 | - [`coffeeAgntcy`](https://github.com/agntcy/coffeeAgntcy): A reference application showcasing agent workflows using the SDK. 7 | 8 | These two repos evolve together, new features in the SDK are tested and validated through CoffeeAgntcy, and real-world app demands drive SDK improvements. 9 | 10 | --- 11 | 12 | ## Project Organization 13 | 14 | ### GitHub Project: Agent App Platform 15 | This cross-repo project tracks epics, features, bugs, and documentation efforts. 16 | 17 | - **Board View**: Weekly triage (`Inbox - Backlog In Progress - In Review - Complete - Closed`) 18 | - **Table View**: Filter by `Component`, `Milestone`, or `Community Priority` 19 | 20 | --- 21 | 22 | ## Issues and Epics 23 | 24 | - **Epics**: GitHub issues labeled `type: epic` with checklists linking related issues. 25 | - Issues should include: description, labels, cross-links. 26 | 27 | ### Example Epic 28 | ``` 29 | # Epic: SLIM v0.4 Integration 30 | 31 | - [ ] Add SLIM node auto-deploy support in `app-sdk` 32 | - [ ] Upgrade group messaging in `coffeeAgntcy` 33 | - [ ] Document SLIM streaming support 34 | ``` 35 | 36 | --- 37 | 38 | ## Labels 39 | 40 | | Label | Purpose | 41 | |------------------|--------------------------------------| 42 | | `type: epic` | Umbrella issue tracking sub-tasks | 43 | | `type: feature` | New functionality | 44 | | `type: bug` | Problem or defect | 45 | | `type: doc` | Documentation issue | 46 | | `component: sdk` | SDK-specific work | 47 | | `component: coffee` | App-specific work | 48 | | `area: slim` | SLIM protocol-related issues | 49 | | `good first issue`| Good entry points for contributors | 50 | 51 | --- 52 | 53 | ## Communication 54 | 55 | - **Slack**: `#app-sdk-coffee-agntcy` 56 | - **GitHub Discussions**: For async feedback and RFCs 57 | 58 | --- 59 | 60 | ## Planning 61 | 62 | Milestones follow format: `FY26Q1-1`, `FY26Q1-2`. 63 | 64 | --- 65 | -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- 1 | # Contributor Covenant Code of Conduct 2 | 3 | ## Our Pledge 4 | 5 | We as members, contributors, and leaders pledge to make participation in our 6 | community a harassment-free experience for everyone, regardless of age, body 7 | size, visible or invisible disability, ethnicity, sex characteristics, gender 8 | identity and expression, level of experience, education, socio-economic status, 9 | nationality, personal appearance, race, religion, or sexual identity 10 | and orientation. 11 | 12 | We pledge to act and interact in ways that contribute to an open, welcoming, 13 | diverse, inclusive, and healthy community. 14 | 15 | ## Our Standards 16 | 17 | Examples of behavior that contributes to a positive environment for our 18 | community include: 19 | 20 | * Demonstrating empathy and kindness toward other people 21 | * Being respectful of differing opinions, viewpoints, and experiences 22 | * Giving and gracefully accepting constructive feedback 23 | * Accepting responsibility and apologizing to those affected by our mistakes, 24 | and learning from the experience 25 | * Focusing on what is best not just for us as individuals, but for the 26 | overall community 27 | 28 | Examples of unacceptable behavior include: 29 | 30 | * The use of sexualized language or imagery, and sexual attention or 31 | advances of any kind 32 | * Trolling, insulting or derogatory comments, and personal or political attacks 33 | * Public or private harassment 34 | * Publishing others' private information, such as a physical or email 35 | address, without their explicit permission 36 | * Other conduct which could reasonably be considered inappropriate in a 37 | professional setting 38 | 39 | ## Enforcement Responsibilities 40 | 41 | Community leaders are responsible for clarifying and enforcing our standards of 42 | acceptable behavior and will take appropriate and fair corrective action in 43 | response to any behavior that they deem inappropriate, threatening, offensive, 44 | or harmful. 45 | 46 | Community leaders have the right and responsibility to remove, edit, or reject 47 | comments, commits, code, wiki edits, issues, and other contributions that are 48 | not aligned to this Code of Conduct, and will communicate reasons for moderation 49 | decisions when appropriate. 50 | 51 | ## Scope 52 | 53 | This Code of Conduct applies within all community spaces, and also applies when 54 | an individual is officially representing the community in public spaces. 55 | Examples of representing our community include using an official e-mail address, 56 | posting via an official social media account, or acting as an appointed 57 | representative at an online or offline event. 58 | 59 | ## Enforcement 60 | 61 | Instances of abusive, harassing, or otherwise unacceptable behavior may be 62 | reported to the community leaders responsible for enforcement at 63 | moderation@agntcy.org. 64 | All complaints will be reviewed and investigated promptly and fairly. 65 | 66 | All community leaders are obligated to respect the privacy and security of the 67 | reporter of any incident. 68 | 69 | ## Enforcement Guidelines 70 | 71 | Community leaders will follow these Community Impact Guidelines in determining 72 | the consequences for any action they deem in violation of this Code of Conduct: 73 | 74 | ### 1. Correction 75 | 76 | **Community Impact**: Use of inappropriate language or other behavior deemed 77 | unprofessional or unwelcome in the community. 78 | 79 | **Consequence**: A private, written warning from community leaders, providing 80 | clarity around the nature of the violation and an explanation of why the 81 | behavior was inappropriate. A public apology may be requested. 82 | 83 | ### 2. Warning 84 | 85 | **Community Impact**: A violation through a single incident or series 86 | of actions. 87 | 88 | **Consequence**: A warning with consequences for continued behavior. No 89 | interaction with the people involved, including unsolicited interaction with 90 | those enforcing the Code of Conduct, for a specified period of time. This 91 | includes avoiding interactions in community spaces as well as external channels 92 | like social media. Violating these terms may lead to a temporary or 93 | permanent ban. 94 | 95 | ### 3. Temporary Ban 96 | 97 | **Community Impact**: A serious violation of community standards, including 98 | sustained inappropriate behavior. 99 | 100 | **Consequence**: A temporary ban from any sort of interaction or public 101 | communication with the community for a specified period of time. No public or 102 | private interaction with the people involved, including unsolicited interaction 103 | with those enforcing the Code of Conduct, is allowed during this period. 104 | Violating these terms may lead to a permanent ban. 105 | 106 | ### 4. Permanent Ban 107 | 108 | **Community Impact**: Demonstrating a pattern of violation of community 109 | standards, including sustained inappropriate behavior, harassment of an 110 | individual, or aggression toward or disparagement of classes of individuals. 111 | 112 | **Consequence**: A permanent ban from any sort of public interaction within 113 | the community. 114 | 115 | ## Attribution 116 | 117 | This Code of Conduct is adapted from the [Contributor Covenant][homepage], 118 | version 2.0, available at 119 | https://www.contributor-covenant.org/version/2/0/code_of_conduct.html. 120 | 121 | Community Impact Guidelines were inspired by [Mozilla's code of conduct 122 | enforcement ladder](https://github.com/mozilla/diversity). 123 | 124 | [homepage]: https://www.contributor-covenant.org 125 | 126 | For answers to common questions about this code of conduct, see the FAQ at 127 | https://www.contributor-covenant.org/faq. Translations are available at 128 | https://www.contributor-covenant.org/translations. 129 | -------------------------------------------------------------------------------- /working-groups/WORKING-GROUPS.md: -------------------------------------------------------------------------------- 1 | # AGNTCY Working Groups 2 | 3 | Most community activity is organized into _working groups_. 4 | 5 | When the need arises, a new working group can be created. See the 6 | [working group processes](../WORKING-GROUP-PROCESSES.md) for working 7 | group proposal and creation procedures. 8 | 9 | The current working groups are: 10 | 11 | | Group | Design Docs | Slack Channel | Description | 12 | | ------------------------------------- | ---------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------- | ------------------------------------- | 13 | | [Core](#core) | [CoreWG drive](https://drive.google.com/drive/folders/1AbFEfM8HZF0_5LbgLXXxiHqFUIsiSjPa?usp=sharing) | [#wg-core](https://agntcy.slack.com/archives/C08R1LZEP0V) | AGNTCY core working group | 14 | | [Observe and Eval](#observe-and-eval) | [drive](https://drive.google.com/drive/folders/1TO_r4xuElzaqZKiQ8g8iSRicCC-s-FVw?usp=sharing) | [#wg-observ-and-eval](https://agntcy.slack.com/archives/C08RMAML6JH) | AGNTCY observe and eval working group | 15 | | [Identity](#identity) | [drive](https://drive.google.com/drive/folders/1TuWnu991AhtpoqFdBjxQdEbb6VadVbBO) | [#wg-identity](https://agntcy.slack.com/archives/C08TZPX83KR) | AGNTCY identity working group | 16 | | [coffee-app-sdk](#coffee-app-sdk) | [drive](https://drive.google.com/drive/folders/1vyKYqh_Hlqi9TNdeGopgtHPjU9ogIxrN?usp=sharing) | [#wg-coffee-app-sdk](https://agntcy.slack.com/archives/C0979J92X9C) | AGNTCY app-sdk and sample app (coffeeAgntcy) working group | 17 | 18 | **NOTE:** [AGNTCY Slack self join link]( https://join.slack.com/t/agntcy/shared_invite/zt-34sxmw5e8-LqlUxxcxROq3HRb56QSkUg) 19 | 20 | ## Core 21 | 22 | - [Charter](core/CHARTER.md) 23 | - Roadmap: **TBD** 24 | - Meetings: [See AGNTCY Calendar](https://calendar.google.com/calendar/embed?src=admin%40ops.agntcy.org&ctz=America%2FNew_York) 25 | - Repos: 26 | - [SLIM](https://github.com/agntcy/slim) 27 | - [Agent Directory](https://github.com/agntcy/dir) 28 | - [CSIT](https://github.com/agntcy/csit) 29 | - [OASF](https://github.com/agntcy/oasf) 30 | - [ACP](https://github.com/agntcy/acp-sdk) 31 | - [Workflow server](https://github.com/agntcy/workflow-srv) 32 | - [IO Mapper](https://github.com/agntcy/iomapper-agnt) 33 | - [API bridge](https://github.com/agntcy/api-bridge-agnt) 34 | - Discussion Channel: [AGNTCY slack #wg-core](https://agntcy.slack.com/archives/C08R1LZEP0V) 35 | 36 | |   | Leads | Company | Profile | 37 | | ------ | ------------------- | ------------- | ------------------------------ | 38 | | | Luca Muscariello | Cisco Systems | https://github.com/muscariello | 39 | | | Alessandro Duminuco | Cisco Systems | https://github.com/aduminuc | 40 | | | Michele Papalini | Cisco Systems | https://github.com/micpapal | 41 | | | Mauro Sardara | Cisco Systems | https://github.com/msardara | 42 | | | Ramiz Polic | Cisco Systems | https://github.com/ramizpolic | 43 | 44 | ## Observe and Eval 45 | 46 | - [Charter](observe-and-eval/CHARTER.md) 47 | - Roadmap: **TBD** 48 | - Meetings: [See AGNTCY Calendar](https://calendar.google.com/calendar/embed?src=admin%40ops.agntcy.org&ctz=America%2FNew_York) 49 | - Repos: 50 | - [Observe-SDK](https://github.com/agntcy/observe) 51 | - Discussion Channel: [AGNTCY slack #wg-observ-and-eval](https://agntcy.slack.com/archives/C08RMAML6JH) 52 | 53 | |   | Leads | Company | Profile | 54 | | ------ | ------------------- | ------------- | ---------------------------- | 55 | | | Giovanna Carofiglio | Cisco Systems | https://github.com/gcarofig | 56 | | | Jacques Samain | Cisco Systems | https://github.com/Castorche | 57 | 58 | ## Identity 59 | 60 | - [Charter](identity/CHARTER.md) 61 | - Roadmap: **TBD** 62 | - Meetings: [See AGNTCY Calendar](https://calendar.google.com/calendar/embed?src=admin%40ops.agntcy.org&ctz=America%2FNew_York) 63 | - Repos: 64 | - [Identity Spec](https://github.com/agntcy/identity-spec) 65 | - [Identity](https://github.com/agntcy/identity) 66 | - Discussion Channel: [AGNTCY slack #wg-identity](https://agntcy.slack.com/archives/C08TZPX83KR) 67 | 68 | |   | Leads | Company | Profile | 69 | | ------ | ---------------- | ------------- | ---------------------------- | 70 | | | Marcelo Yannuzzi | Cisco Systems | https://github.com/mayannuz | 71 | | | Jean Diaconu | Cisco Systems | https://github.com/jadiaconu | 72 | | | Herve Muyal | Cisco Systems | https://github.com/hmuyal | 73 | 74 | ## coffee-app-sdk 75 | 76 | - [Charter](coffee-app-sdk/charter.md) 77 | - Roadmap: **TBD** 78 | - Meetings: [See AGNTCY Calendar](https://calendar.google.com/calendar/embed?src=admin%40ops.agntcy.org&ctz=America%2FNew_York) 79 | - Repos: 80 | - [app-sdk](https://github.com/agntcy/app-sdk) 81 | - [coffeeAgntcy](https://github.com/agntcy/coffeeAgntcy/) 82 | - Discussion Channel: [AGNTCY slack #wg-coffee-app-sdk](https://agntcy.slack.com/archives/C0979J92X9C) 83 | 84 | |   | Leads | Company | Profile | 85 | | ------ | ---------------- | ------------- | ---------------------------- | 86 | | | John Parello | Cisco Systems | https://github.com/jparello | 87 | | | Cody Harstook | Cisco Systems | https://github.com/codyhartsook | 88 | 89 | -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | # AGNTCY, a Series of LF Projects: Contributing Guide 2 | 3 | Welcome to AGNTCY! We’re excited to welcome you to our community. Keep reading to learn more about how we’re building the Internet of Agents and where you can contribute. 4 | 5 | ## AGNTCY’s Mission 6 | 7 | AGNTCY aims to create a common infrastructure layer for AI agent-to-agent collaboration across the complete multi-agent software lifecycle: from discovery and identification, to communication, deployment, observability, and evaluation. This open, interoperable ecosystem aims to securely and seamlessly unite AI agents together, regardless of their provided framework, vendor or platform. 8 | 9 | ## Purpose and Charter 10 | 11 | Read more about the “why” behind AGNTCY via the [Operating Model document](OPERATING_MODEL.md). 12 | 13 | ## Code of Conduct 14 | 15 | AGNTCY has adopted the [Contributor Covenant](https://www.contributor-covenant.org/), ensuring a welcoming and respectful community. Please make sure to read and observe the [Code of Conduct](CODE_OF_CONDUCT.md) while participating in the project. 16 | 17 | ## Start Contributing! 18 | 19 | AGNTCY contains various sub-projects that you’re able to browse and interact with via Issues, Pull Requests, and Discussions in the overall project. Across AGNTCY, all new inbound code contributions must be accompanied by a Developer Certificate of Origin, or [DCO](http://developercertificate.org), sign-off. You must include a sign-off in the commit message of your Pull Request for it to be accepted. The format for a sign-off is: 20 | 21 | ``` 22 | Signed-off-by: Random J Developer 23 | ``` 24 | 25 | Each sub-project has their own CONTRIBUTING.md file where you can read up on the scope of the sub-project, how they complete reviews or submit bug reports, etc. 26 | 27 | ## Roles and Governance 28 | 29 | | Role | Responsibilities | Requirements | Defined By | 30 | | ---- | ---------------- | ------------ | ---------- | 31 | | Adopter | For those using and/or evangelizing AGNTCY in their organization | Your company name in the AGNTCY adopter list on GitHub | Companies that support AGNTCY through use of affiliated projects and shared belief in an open, interoperable Internet of Agents | 32 | | Contributor | Active contributor in the community, reviewer of PRs | Evidence of multiple contributions to AGNTCY projects | Members of GitHub organization | 33 | | Committer | Code review and approvals, help set project direction and priorities, possible Working Group lead | Highly experienced active contributor, author, and reviewer of a project | [CODEOWNERS](https://help.github.com/en/articles/about-code-owners) in GitHub, GitHub Team | 34 | | Technical Steering Committee | Responsible for all technical oversight of AGNTCY and its sub-projects | Core maintainer-based membership | Noted in org-level [CONTRIBUTING.md](#technical-steering-committee-members), GitHub Team | 35 | 36 | You can read more detail about each role in the [Operating Model document](OPERATING_MODEL.md). 37 | 38 | ### Technical Steering Committee Members 39 | 40 | Current TSC members in alphabetical order: 41 | 42 | - John Cardente (Dell Technologies, @jcardente-dell) 43 | - Michael Clifford (Red Hat, @MichaelClifford) 44 | - Luca Muscariello (Cisco, @muscariello) 45 | - John Parello (Cisco, @jparello) 46 | - Egor Pushkin (Oracle, @egorpushkin) 47 | - Todd Segal (Google Cloud, @ToddSegal) 48 | - Marcelo Yannuzi (Cisco, @mayannuz) 49 | 50 | ## Working Groups 51 | 52 | Working groups exist to delegate technical decision-making across the complete multi-agent software lifecycle: they are responsible for the design and implementation of large architectural aspects of the overall AGNTCY project. Working groups operate with a fair amount of autonomy within the broader scope of the project. The [Technical Steering Committee](#technical-steering-committee-members) is responsible for approving the creation of working groups to handle specific scopes of authority, spanning several sub-projects. The processes that govern working group formation, operation, and dissolution are defined per the [working group processes](WORKING-GROUP-PROCESSES.md) documentation. Contributions made under the direction and authority of working groups are expected to conform to the same processes defined in the AGNTCY [Operating Model](OPERATING_MODEL.md) document. 53 | 54 | For more information about our working groups, including leadership roles and scope definition, please see our [Working Groups](working-groups/WORKING-GROUPS.md) documentation. 55 | 56 | ## Community Engagement 57 | 58 | Alongside collaborating via GitHub with Issues, PRs, and Discussions, we welcome you to our Slack Workspace to continue discussing AGNTCY and its sub-projects. Join us at [agntcy.slack.com](https://agntcy.slack.com/archives/C0893S6D284) -- [AGNTCY Slack self join link](https://join.slack.com/t/agntcy/shared_invite/zt-34sxmw5e8-LqlUxxcxROq3HRb56QSkUg). 59 | 60 | To join the various community meetings that have been set up by AGNTCY working groups, see the [AGNTCY calendar](https://calendar.google.com/calendar/embed?src=admin%40ops.agntcy.org&ctz=America%2FNew_York), set up via Google Groups. 61 | 62 | ## License 63 | 64 | Distributed under the Apache 2.0 License. See [LICENSE](LICENSE.md) for more information. 65 | Copyright AGNTCY Contributors (https://github.com/agntcy). 66 | 67 | 68 | 69 | -------------------------------------------------------------------------------- /WORKING-GROUP-PROCESSES.md: -------------------------------------------------------------------------------- 1 | This document describes the processes we use to manage the AGNTCY working 2 | groups. This includes how they are formed, how leads are established, how they 3 | are run, etc. 4 | 5 | - [Why working groups?](#why-working-groups) 6 | - [Proposing a new working group](#proposing-a-new-working-group) 7 | - [Setting up a working group](#setting-up-a-working-group) 8 | - [Dissolving a working group](#dissolving-a-working-group) 9 | - [Leads](#leads) 10 | - [Running a working group](#running-a-working-group) 11 | - [Be open](#be-open) 12 | - [Making decisions](#making-decisions) 13 | - [Subgroups](#subgroups) 14 | - [Escalations](#escalations) 15 | 16 | ## Why working groups? 17 | 18 | AGNTCY working groups are organizations responsible for the design and 19 | implementation of large architectural aspects of the overall AGNTCY project. 20 | Working groups operate with a fair amount of autonomy within the broader scope 21 | of the project. They tend to be long-lived, representing major initiatives over 22 | AGNTCY’s lifetime. 23 | 24 | Some working groups focus on specific technologies. Other working groups are 25 | cross-cutting in nature. 26 | 27 | The steering committee is responsible for the AGNTCY project as a 28 | whole. It sets the overall direction of the project AND, until such time where a 29 | separate Technical Oversight Committee is formed, the steering committee helps make crosscutting 30 | architectural decisions, helps establish and dissolve working groups, and helps 31 | ensure all working groups are generally rowing in the same direction 32 | 33 | Although working groups are relatively lightweight structures, we want to keep 34 | the number of working groups low in order to keep things manageable. 35 | 36 | ## Proposing a new working group 37 | 38 | If you've identified a substantial architectural area which would benefit from long-lived, 39 | concerted and focused design, then you should consider creating a new working 40 | group. To do so, you need to: 41 | 42 | - **Create a charter**. This should be a few paragraphs explaining: 43 | 44 | - The mission of the working group 45 | 46 | - The goals of the working group (problems being solved) 47 | 48 | - The scope of the working group (topics, subsystems, code repos, areas of 49 | responsibility). Also it's very helpful to include items which are out of scope. The Steering Committee will be 50 | looking at this to make sure that there are appropriate touch-points and 51 | contracts between WGs when considering larger problems. 52 | 53 | - **Nominate an initial set of leads**. The leads set the agenda for the working 54 | group and serve as final arbiters on any technical decision. See 55 | [below](#leads) for information on the responsibilities of leads and 56 | requirements for nominating them. 57 | 58 | - **Prepare a Roadmap**. Create a preliminary roadmap (ideally, ~3 months worth) for what the 59 | working group would focus on. 60 | 61 | - **Create a PR**. Create a PR for this repo with a new sub-directory under `working-groups` and add a 62 | `CHARTER.md` file with your charter, nominated leads, and roadmap. The 63 | steering committee will evaluate the request and decide whether the 64 | working group should be formed, whether it should be merely a subgroup of an 65 | existing working group, or whether it should be subsumed by an existing 66 | working group. The PR should include the initial set of leads in a new section 67 | in [WORKING-GROUPS.md](working-groups/WORKING-GROUPS.md). 68 | 69 | - [example PR](https://github.com/agntcy/governance/pull/11) 70 | 71 | ## Setting up a working group 72 | 73 | Once approval has been granted by the technical oversight committee to form a 74 | working group, the working group leads need to take a few steps to establish the 75 | working group._ 76 | 77 | - **Create a Google Drive Folder**. Create a folder to hold your working group 78 | documents within this parent 79 | [folder](https://drive.google.com/drive/folders/1l5v-aEArWGUL2_f79bx3ysizsRH2Z8PM?usp=sharing). 80 | Call your folder "GROUP_NAME". 81 | 82 | - **Create a Meeting Notes Document**. Create a blank document in the above 83 | folder and call it "GROUP_NAME Group Meeting Notes". 84 | 85 | - **Create a Roadmap**. Create a new [Roadmap Project Board](TBD) **TODO**. 86 | 87 | - **Schedule a Recurring Meeting**. Create a recurring meeting (weekly or 88 | bi-weekly, 30 or 60 minutes) on the 89 | [shared calendar](https://calendar.google.com/calendar/embed?src=admin%40ops.agntcy.org&ctz=America%2FNew_York) 90 | and call the meeting "\$GROUP_NAME WG". Attach the meeting notes document to 91 | the calendar event. Generally schedule these meetings between 9:00AM to 2:59PM 92 | Pacific Time. Invite `` Google group to the 93 | meeting, as well as necessary individual participants. 94 | 95 | - **Register the Working Group**. Go to 96 | [WORKING-GROUPS.md](working-groups/WORKING-GROUPS.md) and add your working 97 | group name, the names of the leads, the working group charter, and a link to 98 | the meeting you created. 99 | 100 | - **Announce your Working Group**. Send a message to [#agntcy-general on slack](https://agntcy.slack.com/archives/C0893S6D284) 101 | announcing your new working group. Include your charter in the message and provide 102 | links to the meeting invitation. 103 | 104 | Congratulations, you now have a fully formed working group! 105 | 106 | ### Dissolving a working group 107 | 108 | Some working groups are ephemeral or naturally reach the end of their useful 109 | life. Working group leads can petition to dissolve their working groups by 110 | emailing admin@agntcy.org. 111 | The steering committee takes ownership of any artifacts created or 112 | owned by the dissolved working group. The steering committee also 113 | reserves the right to dissolve or recharter working groups over time as 114 | necessary, though they will strive to first discuss this in committee meetings 115 | and open community discussion. 116 | 117 | ## Leads 118 | 119 | Each working group should have at least 2 leads, ideally 3, though young working 120 | groups may have only 1 lead initially. Working groups should strive to include 121 | representatives from multiple organizations as both leads and members. Working 122 | group leads must be Members of the AGNTCY project (that is, have made multiple 123 | contributions to the project in the form of code, design, or documentation). 124 | 125 | Please see the [Roles](OPERATING_MODEL.md#3-roles-and-governance) defined in the 126 | governance operating model for a description of a lead’s role and requirements. 127 | 128 | ## Running a working group 129 | 130 | Leads are responsible for running a working group. Running the group involves a 131 | few activities: 132 | 133 | - **Meetings**. Prepare the agenda and run the regular working group meetings. 134 | Ensure the meetings are recorded, and properly archived. 135 | 136 | - **Notes**. Ensure that meeting notes are kept up to date. Provide a link to 137 | the recorded meeting in the notes. The lead may delegate note-taking duties. 138 | 139 | - **Decision Log**. Ensure that significant design decisions are captured in 140 | GitHub issues, Google Docs, or markdown files in the repo. 141 | 142 | - **Roadmap**. Establish **and maintain** a roadmap for the working group 143 | outlining the areas of focus for the working group, ideally, over the next 3 months. 144 | 145 | - **Report**. Report current status to main community meetings or maintainers' meetings. 146 | 147 | ### Be open 148 | 149 | The community design process is done in the open. Working groups should 150 | communicate primarily through the public working group meetings, through design 151 | documents in the working group’s folder, through GitHub issues, and GitHub PRs. 152 | Avoid private emails and/or meeting when possible. 153 | 154 | ### Making decisions 155 | 156 | In general, working groups operate in a highly cooperative environment. Working 157 | groups discuss designs in the open and take input from the community at large 158 | when making technical choices. The working group leads are ultimately 159 | responsible for setting the direction of the working group and making the tough 160 | technical choices affecting the working group. 161 | 162 | ### Subgroups 163 | 164 | Subgroups are ad hoc subteams within a working group with a special focus on a 165 | set of problems or technologies. We don’t formalize processes for subgroups, 166 | each working group can decide when subgroups are needed and how they operate. 167 | 168 | ### Escalations 169 | 170 | Working groups can get blocked on specific technical disagreements. Leads are 171 | expected to generally resolve such issues and allow work to progress. 172 | 173 | Sometimes, different working groups can have conflicting goals or requirements. 174 | Leads from all affected working groups generally work together and come to an 175 | agreeable conclusion. 176 | 177 | In all cases, remaining blocking issues can be raised to the 178 | [steering committee](TBD) to help resolve 179 | the situation. To trigger an escalation, create an issue in the **TODO** 180 | steering committee's agenda (or email admin@agntcy.org) and be prepared to attend a meeting to provide 181 | an explanation of the underlying problem as well as cogent arguments for both 182 | sides. 183 | -------------------------------------------------------------------------------- /LICENSE.md: -------------------------------------------------------------------------------- 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 | -------------------------------------------------------------------------------- /OPERATING_MODEL.md: -------------------------------------------------------------------------------- 1 | # The AGNTCY Charter & Operating Model 2 | 3 | ## 1. Project Overview 4 | 5 | ### 1.1 Name & Identity 6 | 7 | - **Project**: **The** **AGNTCY (aka Internet of Agents Project, or the Project)** 8 | - **Identity**: The AGNTCY (pronounced "agency") Project is the collective of contributors and maintainers building the Internet of Agents (IoA): an open, interoperable, internet for agent-to-agent collaboration. 9 | 10 | ### 1.2 Mission & Vision 11 | 12 | - **Mission**: Provide a collaborative environment where contributors of all backgrounds can innovate, develop, and maintain software components that solve key problems in the domain of agentic workflows and multi agent application creation: agent identity, agent announcement, agent discovery and search, agent connectivity, agent to agent collaboration, agentic ensembles deployment, supervision, observability, security and more. Simply put, we intend to build the Internet of Agents, *together*. 13 | 14 | ![Internet of Agents simplified architecture](images/agntcy_ioa_simplified_architecture.svg) 15 | 16 | *Figure 1: The Internet of Agents simplified architecture* 17 | 18 | - **Vision**: We envision a future where Agentic AI systems transform industries by enabling the developer community, partners, and enterprises to build intelligent, autonomous AI applications. This new AI-native world needs a communication layer, *the Internet of Agents*, to enable collaboration across the ecosystem of agentic applications of various kinds, from different vendors, across different industries. 19 | - Agentic software will accelerate all of human work – cognitive, services, and physical. Enterprises will need to create deterministic workflows or planner-based jobs and applications, combining internal and third-party agents, to fully leverage the power of AI to accelerate their business and unlock new step-change in productivity. 20 | - An open, neutral and interoperable Internet of Agents drives maximum value for all players: infrastructure and tool builders, operators, app developers, and consumers. It avoids vendor lock-in. 21 | 22 | --- 23 | 24 | ## 2. Charter 25 | 26 | ### 2.1 Purpose 27 | 28 | AGNTCY intends to serve the IoA ecosystem in the foundation-like role of open source software steward. 29 | 30 | - **Open Collaboration**: Foster a globally accessible community that encourages contributions from individuals and organizations. 31 | - **Innovation**: Empower contributors to experiment, propose, and build new features through open discussion and consensus. 32 | - **Stewardship of the projects**: Give each contributor a voice in shaping the proposed initiatives, relevant open-source projects, and overall direction of AGNTCY. 33 | - **Fostering the growth and evolution of the ecosystem**: Provide community development and education around the project's sub-projects and affiliated projects. This includes reviewing or contributing documentation, workshops, demos, and tutorials to onboard new users and contributors. Serve the community by making the IoA technologies accessible and reliable. 34 | 35 | ### 2.3 Guiding Principles 36 | 37 | #### 1. Trust & Transparency 38 | 39 | - We guide projects to build trust with adopters and users, balancing quality and sustainability with velocity. 40 | - Our technical work must be available to all according to these guiding principles. Our community, processes, and decisions are transparent, visible, and discoverable. 41 | 42 | #### 2. Open & Extensible 43 | 44 | - We are open to and inclusive of all adopters and collaborators to build a collective of different perspectives that can help create a powerful global standard. 45 | - We invite proactive contributions from our community of developers to extend or adopt AGNTCY for all agentic applications beyond its existing capabilities. 46 | 47 | #### 3. Platform Agnostic 48 | 49 | - We have an explicit bias toward projects and specifications developed to be platform agnostic such that they can be implemented on a variety of platforms, architectures, clouds, and operating systems. 50 | 51 | #### 4. Modularity & Interoperability 52 | 53 | - Encourage a modular architecture to facilitate incremental improvements and smooth interoperability with external tools. 54 | 55 | #### 5. Meritocracy & Inclusivity 56 | 57 | - Contributions are valued based on quality and impact, independent of personal background. 58 | - Strive to maintain an inclusive environment where diverse perspectives are respected. 59 | 60 | #### 6. Respect & Professionalism 61 | 62 | - Uphold a Code of Conduct that ensures respectful communication, constructive feedback, and zero tolerance for harassment. 63 | 64 | --- 65 | 66 | ## 3. Roles and Governance 67 | 68 | ### 3.1 Definition of Roles 69 | 70 | This section outlines the various responsibilities of roles in AGNTCY. 71 | 72 | | **Role** | **Responsibilities** | **Requirements** | **Defined By** | 73 | | ------------------ | -------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- | 74 | | Adopter | For those using and/or evangelizing AGNTCY in their organization | Your company name in the AGNTCY adopter list on GitHub | Companies that support AGNTCY through use of affiliated projects and shared belief in an open, interoperable internet of agents | 75 | | Contributor | Active contributor in the community, reviewer of PRs | Evidence of multiple contributions to AGNTCY projects | Members of GitHub organization | 76 | | Committer | Code review and approvals, help set project direction and priorities | Highly experienced active contributor, author, and reviewer of a project | [CODEOWNERS](https://help.github.com/en/articles/about-code-owners) in GitHub, GitHub Team | 77 | | Technical Steering Committee | Responsible for all technical oversight of AGNTCY and its sub-projects | Core maintainer-based membership | Noted in org-level [CONTRIBUTING.md](CONTRIBUTING.md#technical-steering-committee-members), GitHub Team | 78 | 79 | ### 3.2 Adopters 80 | 81 | - People or organizations that use and/or evangelize AGNTCY affiliated projects but may or may not directly contribute to its projects. 82 | - **Participation**: 83 | 1. Share feedback and report bugs. 84 | 2. Share case studies for evangelizing the AGNTCY project. 85 | 3. Participate in user forums, Q&A channels, or community calls. 86 | 87 | ### 3.3 Contributors 88 | 89 | - Individuals who contribute code, documentation, designs, bug fixes, or community support for AGNTCY affiliated projects. Reviewing contributions is also considered active participation as a contributor. 90 | - **Path to Contribution**: 91 | 1. Submit pull requests or patches. 92 | 2. Engage in discussions, design proposals, and issue triage. 93 | 3. Agree to abide by the [Code of Conduct](CODE_OF_CONDUCT.md) and licensing guidelines. 94 | 4. Be nominated by two (2) or more [committers](#committers) to achieve contributor permissions. 95 | 96 | ### 3.4 Committers 97 | 98 | - Individuals who review and/or approve contributed code, documentation, designs, bug fixes, or moderate community support for AGNTCY affiliated projects. 99 | - **Path to Committer**: 100 | 1. Frequently review pull requests or patches. 101 | 2. Lead discussions, design proposals, and issue triage. 102 | 3. Be nominated by the AGNTCY Technical Steering Committee to achieve committer permissions. 103 | 104 | ### 3.5 Technical Steering Committee 105 | 106 | The AGNTCY Technical Steering Committee (TSC) is responsible for the governance of projects jointly owned under AGNTCY and its sub-projects. The Technical Steering Committee will set the technical direction of the project and sub-projects. 107 | 108 | - **Composition**: The TSC membership is defined in [CONTRIBUTING.md](CONTRIBUTING.md#technical-steering-committee-members). It is the intent to establish a voting mechanism and process to expand the Technical Steering Committee, to be determined by the Committee itself. The vision is for the AGNTCY to be a community-governed project and include long-standing contributors and committers from affiliated projects. 109 | 110 | - **Responsibilities**: 111 | 1. Oversee strategic and long-term project goals. 112 | 2. Guide architectural decisions and set standards. 113 | 3. Delegate specific scopes of authority to working groups per the [working-group processes](WORKING-GROUP-PROCESSES.md). 114 | 4. Resolve escalated technical or governance disputes. 115 | 5. Ensure the community adheres to the [Code of Conduct](CODE_OF_CONDUCT.md) and licensing standards. 116 | 6. Approve critical changes to the project's recommendations for sub-projects' or affiliate project's governance and licensing. 117 | 7. Direct marketing, including evangelism, events and ecosystem engagement 118 | 119 | 120 | ### 3.6 **Working Groups** 121 | 122 | The AGNTCY Technical Steering Committee is responsible for approving the creation of working groups to handle specific scopes of 123 | authority. The processes that govern working group formation, operation, and dissolution are defined per the 124 | [working-group processes](WORKING-GROUP-PROCESSES.md). Contributions made under the direction and authority of working-groups 125 | are expected to conform to the same processes defined in the AGNTCY operating model as defined in this document, unless 126 | deviation is specifically defined in the working-group's approved charter. 127 | 128 | --- 129 | 130 | ## 4. Decision-Making Process 131 | 132 | ### 4.1 Consensus Seeking 133 | 134 | - **Proposal Discussion**: Open issues or pull requests on GitHub for discussion. 135 | - **Review Window**: Maintain a minimum discussion period (e.g., 3--5 business days) for meaningful member feedback. 136 | - **Approval**: If no major objections are raised, the proposal is considered accepted. 137 | - **Escalation**: When disagreements persist, the relevant Technical Lead or Technical Steering Committee member mediates. 138 | 139 | ### 4.2 Lazy Consensus 140 | 141 | - For minor changes or routine updates, maintainers can merge after a brief review period if there are no objections. 142 | 143 | ### 4.3 Formal Votes 144 | 145 | - On critical changes (e.g., major feature adoption, license amendments), the Technical Steering Committee may call a vote. 146 | - **Simple Majority**: Required for most issues; **Two-Thirds Majority** for fundamental changes or governance modifications. 147 | 148 | --- 149 | 150 | ## 5. Contribution Workflow 151 | 152 | Contribution workflows can be established for each respective AGNTCY affiliate project, however, the below are recommended guidelines. 153 | 154 | ### 5.1 Source Code Management 155 | 156 | - **Repository**: GitHub (or potentially GitLab) serves as the central code repository. 157 | - **Branching Strategy**: 158 | 1. **main** (stable production branch). 159 | 2. **feature/XYZ** branches for new functionality. 160 | 3. **release/X.Y** branches for versioned releases. 161 | 162 | ### 5.2 Issue Tracking & Labeling 163 | 164 | - **Issue System**: GitHub Issues for bugs, enhancements, and user stories. 165 | - **Labeling**: 166 | 1. **good first issue**: For newcomers. 167 | 2. **help wanted**: For issues needing broader community input. 168 | 3. **bug**, **enhancement**, **documentation**, etc. for clarity. 169 | 170 | ### 5.3 **Pull Request Reviews** 171 | 172 | - **Minimum Approvals**: At least one maintainer or module lead must approve. Two approvals recommended for larger features. 173 | - **Automated CI**: Must pass all tests (unit, integration, lint) before merge. 174 | - **Code Quality**: Follow coding standards, best practices, and style guidelines documented in CONTRIBUTING.md. 175 | 176 | ### 5.4 **Testing & Releases** 177 | 178 | - **Continuous Integration**: Use a CI service (GitHub Actions, CircleCI, Jenkins) to automate builds and tests. 179 | - **Release Cadence**: 180 | - **Monthly Minor Releases**: Include new features, improvements, and bug fixes. 181 | - **Quarterly Major/Minor**: Larger milestones or architectural changes. 182 | - **Patch Releases**: For urgent bug or security fixes. 183 | 184 | --- 185 | 186 | ## 6. Community Engagement 187 | 188 | ### 6.1 Communication Channels 189 | 190 | The core communication will be through the AGNTCY's Slack instance which will be through invite-only access at first. 191 | 192 | - **Real-Time Chat**: Slack (agntcy.slack.com) for quick collaboration, Q&A, Technical Steering Committee and member engagement / collaboration. 193 | - **Video chat:** When necessary and as affiliate project or AGNTCY business needs evolves, members may need to join collaborative video calls via Webex, Google Hangout, Zoom, or similar. 194 | - **Community Calls**: If needed, quarterly video calls could be held that would be open to everyone, focusing on demos, roadmap updates, and Q&A. 195 | 196 | ### 6.2 Documentation & Website 197 | 198 | AGNTCY’s main web home will be a Git repo that all members have access to. The vanity URL and domain of "[AGNTCY.org](https://AGNTCY.org)" will have relevant project information. Some items that may be included there: 199 | 200 | - **User Guide**: Detailed setup instructions, examples, and best practices. 201 | - **Developer Guide**: Architecture overview, how to run tests, coding conventions, how to propose changes. 202 | - **FAQ**: Common usage issues, frequently asked questions, and troubleshooting steps. 203 | 204 | ### 6.3 Events & Outreach 205 | 206 | AGNTCY by definition is a community-oriented organization. To achieve our mission, we must build and collaborate together! We intend to support member initiatives through investing in and coordinating in person and virtual meetups as well as educational initiatives. These could include the following: 207 | 208 | - **Meetups/Workshops**: Encourage local community gatherings and virtual hackathons. 209 | - **Conferences**: Represent AGNTCY at open source conferences, featuring project updates, case studies, or success stories. 210 | - **Social Media & Blog**: Publish release notes, tutorials, and highlight community contributions. 211 | 212 | ### 6.4 Mentorship & Onboarding 213 | 214 | - **Onboarding Guides**: Step-by-step tutorials for new contributors. 215 | - **Mentorship**: Pair newcomers with experienced maintainers for support. 216 | - **Beginner Tasks**: Curate "good first issue" tasks to help new contributors gain confidence. 217 | 218 | --- 219 | 220 | ## 7. Code of Conduct & Conflict Resolution 221 | 222 | ### 7.1 Code of Conduct 223 | 224 | - AGNTCY adopts the [**Contributor Covenant**](https://www.contributor-covenant.org/) (version 2.1 or newer), ensuring a welcoming and respectful community. 225 | - [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) 226 | 227 | ### 7.2 Reporting & Enforcement 228 | 229 | - **Incident Reporting**: Private email alias (e.g., conduct@agntcy.org) for confidentially reporting issues. 230 | - **Investigation**: A designated member or group of the Technical Steering Committee will review reports promptly, ensuring fairness and discretion. 231 | - **Consequences**: Range from warnings to temporary or permanent bans based on severity. 232 | 233 | ### 7.3 Conflict Resolution 234 | 235 | - **Informal Resolution**: Encourage direct, constructive dialogue for small disagreements. 236 | - **Escalation**: If unresolved, present the issue to a Technical Steering Committee member. 237 | - **Final Decision**: The Technical Steering Committee can serve as the last resort for major disputes. 238 | 239 | --- 240 | 241 | ## 8.Licensing 242 | 243 | ### 8.1 Open Source License 244 | 245 | - **Chosen License**: Recommend AGNTCY sub-projects adopt [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). This license promotes collaboration by providing clear patent protections and permissive usage rights. 246 | 247 | ### 8.2 Contributor Agreements 248 | 249 | - **Developer Certificate of Origin (DCO)**: Contributors must sign off commits to confirm they are authorized to contribute. 250 | - Alternatively, the community may adopt a **Contributor License Agreement (CLA)** if needed for legal clarity. 251 | 252 | --- 253 | 254 | ## 9. Implementation & Roadmap 255 | 256 | ### 9.1 Initial Setup 257 | 258 | 1. **Finalize Documentation**: Ensure README.md, CONTRIBUTING.md, SECURITY.md, and CODE_OF_CONDUCT.md are in place. 259 | 2. **Establish Repositories**: Configure main code repo and supporting repos (e.g., docs, website). 260 | 3. **Configure CI/CD**: Automated tests, linting, and build pipelines. 261 | 262 | ### 9.2 Short-Term Roadmap (First 3-6 Months) 263 | 264 | - **Core Features**: Implement essential functions of the AGNTCY platform. 265 | - **Onboarding Material**: Expand documentation and "good first issues." 266 | - **Community Growth**: Host an inaugural community call, set up Slack/Discord, and encourage discussion on the forum. 267 | 268 | ### 9.3 Long-Term Goals 269 | 270 | - **Feature Maturity**: Achieve stable releases, expand integrations, focus on performance and security. 271 | - **Ecosystem Development**: Encourage third-party extensions, plug-in development, and specialized modules. 272 | - **Community Expansion**: Local user groups, speaking engagements at conferences, and official meetups. 273 | 274 | --- 275 | 276 | ## 10. Success Metrics 277 | 278 | ### Community Growth 279 | 280 | - Number of active sub-projects and affiliate projects that have active contributors, diversity of participation, and new committers added. 281 | 282 | ### Project Health 283 | 284 | - Time to First Response and [Contributor Access Factor](https://chaoss.community/kb/metrics-model-starter-project-health/). 285 | - Number of stable releases per quarter and bug fix turnaround. 286 | 287 | ### Adoption & Usage 288 | 289 | - Downloads, GitHub stars/forks, documented user case studies. 290 | - External references and third-party integrations. 291 | 292 | ### Governance Effectiveness 293 | 294 | - Time to decision on major proposals, conflict resolution speed, and community sentiment. 295 | 296 | --- 297 | 298 | ## Conclusion 299 | 300 | This charter and operating model outlines how **AGNTCY** will operate as a transparent, inclusive, and merit-based open source project. By combining clear governance structures, open contribution pathways, a strong code of conduct, and robust technical processes, AGNTCY aims to foster a thriving ecosystem and deliver high-quality software solutions through its members. 301 | 302 | **Welcome to The AGNTCY!** We look forward to building the future of multi agent applications and workflows together. 303 | --------------------------------------------------------------------------------