A toolkit that generates agent-native command-line interfaces for existing software, plus a CLI-Hub registry for installing ready-made ones.
Tencent/teamai-cli
A CLI that manages a team's AI coding assets (skills, rules, agents, MCP servers, models) in a shared git repo and syncs them to teammates' AI tools.
- Stars
- 5,565
- Forks
- 453
- Open issues
- 50
- Last commit
- 18 hours ago
What is it?
TeamAI is a command-line tool that keeps a team's AI assets in a git repository. Skills, rules, agents, hooks, MCP server configs, model settings and environment variables are stored there, so every teammate's AI coding tool works from the same set of resources. An admin initializes the repo once, and each team member runs an init command pointing at it; after that, the latest published assets are pulled automatically at the start of each AI session.
The tool supports a long list of agent clients, including Claude Code, Codex, Cursor, GitHub Copilot CLI, OpenCode and several domestic products such as CodeBuddy, Qoder and Trae. Resources can be installed at workspace scope or user scope. Beyond execution config, the project also has beta modules for shared learnings, a codebase graph, a team wiki, and usage and session tracking.
Installation is via npm (`teamai-cli`), and the project can also be driven through an AI skill that walks a user through setup. Git hosts named in the docs include GitHub, GitLab, GitCode, CNB and TGit.
Key features
- 01Syncs skills, rules, agents, hooks and MCP configs from a shared git repo to each teammate.
- 02Supports many AI coding agents, including Claude Code, Codex, Cursor and Copilot CLI.
- 03Offers workspace-scope or user-scope installation.
- 04Provides an env command for running processes with team-defined environment variables.
- 05Includes beta modules for team learnings, codebase graph and team wiki.
Use cases
- Standardizing coding conventions and review agents across a team using different AI tools.
- Onboarding new engineers so they get the team's skills and MCP servers automatically.
- Sharing a useful internal skill or MCP configuration with colleagues through a git repo.
Quick start
- 1
Install the CLI from npm
npm install -g teamai-cli - 2
Create a shared git repo for your team, then initialize TeamAI against it
teamai init https://github.com/your-org/your-repo - 3
Team members: move to your workspace folder and initialize against the team repo
cd /path/to/my-workspace
Things to know
- Team Context and Team Improvement features are marked as beta.
- Windows users need extra hooks and shell configuration per the Windows setup guide.
- The license is not detected from metadata, though the README states MIT.
Topics
FAQ
- What is teamai-cli?
- A CLI that manages a team's AI coding assets (skills, rules, agents, MCP servers, models) in a shared git repo and syncs them to teammates' AI tools. TeamAI is a command-line tool that keeps a team's AI assets in a git repository. Skills, rules, agents, hooks, MCP server configs, model settings and environment variables are stored there, so every teammate's AI coding tool works from the same set of resources. An admin initializes the repo once, and each team member runs an init command pointing at it; after that, the latest published assets are pulled automatically at the start of each AI session.
- Is teamai-cli free to use? What license does it have?
- teamai-cli is open source under the Other license. Check the license terms before using it in commercial products.
- Is teamai-cli still maintained?
- Actively maintained. The last commit to teamai-cli was on Oct 19, 2026.
- What can I use teamai-cli for?
- Standardizing coding conventions and review agents across a team using different AI tools. Onboarding new engineers so they get the team's skills and MCP servers automatically. Sharing a useful internal skill or MCP configuration with colleagues through a git repo.
- How do I install teamai-cli?
- Install the CLI from npm: npm install -g teamai-cli Create a shared git repo for your team, then initialize TeamAI against it: teamai init https://github.com/your-org/your-repo Team members: move to your workspace folder and initialize against the team repo: cd /path/to/my-workspace
- Where can I get teamai-cli?
- The source code and installation instructions are on GitHub: https://github.com/Tencent/teamai-cli
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A personal context store that gives AI coding agents like Codex, Claude Code and OpenCode persistent project knowledge via a CLI, MCP server and desktop app.
MCP server and CLI letting AI agents reverse engineer native binaries, Electron apps, .NET assemblies and websites.
A plugin-based harness that gives Claude Code, Codex and other coding agents shared agents, skills, hooks, memory and security scanning.
A modular runtime and orchestration system that coordinates AI coding agents through gated pipelines for tasks, review, shipping and docs across Claude Code, Codex, Cursor and more.
A prompt-based skill that makes AI coding agents write only the code a task needs, favoring reuse and minimal solutions over large implementations.