Tencent/Teamai-CLI: Make Every Team AI Native

TeamAI manages your team's skills, rules, MCP, and knowledge across Claude Code, Codex, CodeBuddy, WorkBuddy, OpenCode, Cursor, Qoder, and other AI agents.

npm install -g teamai-cli

Create a shared-experience repo on your git host (GitHub, GitLab, GitCode, CNB, TGit, or a private Git service), grant write access to team members, then run teamai init https://github.com/yourorg/yourrepo.

No team repo yet? Start from a template pre-loaded with production-ready skills, rules, and review agents. Browse the teamai-hub org, click Use this template, then teamai init against your new repo.

cd /path/to/my-project
teamai init https://github.com/yourorg/yourrepo

teamai init https://github.com/yourorg/yourrepo --scope user

Once initialized, every AI session automatically pulls the latest skills / rules and other Harness updates published by admins — no manual sync needed.

Full usage guide: docs/usage-guide.md (中文版) — covers everything from team creation to day-to-day use.

Team Execution × Team Context × Team Improvement:

Git providers — GitHub · GitLab · GitCode · CNB · TGit · private Git service.

Team-wide settings an admin configures once and delivers to every member on teamai pull:

One Team. One Harness. Every Agent.

TeamAI keeps skills, rules, docs, and hooks in a shared git repo and distributes them to every member's local AI tools through a "push → review & merge → pull" flow — with support for subscribing to other teams' or shared repos' Harness.

teamai push → create branch + MR → reviewer approves + merges
                                         ↓
              SessionStart hook → teamai pull → synced to local AI tools

Members push changes via teamai push, which opens a Merge Request for review. Re-running teamai push on a resource that is still waiting in an unmerged PR updates that PR in place instead of opening a duplicate. Once merged, teamai pull (triggered automatically on session start via the SessionStart hook) syncs the latest resources locally. Skills sync to ~/.claude/skills/, ~/.codex/skills/, ~/.cursor/skills/, ~/.codebuddy/skills/, etc. In a project-scope install, SessionStart first creates that tool's project root (e.g. <project>/.claude) if it is missing, then pulls into it — a bare teamai pull still will not invent agent directories.

Declare custom hooks in hooks/hooks.yaml and teamai pull delivers them to every AI tool:

hooks:
  - id: block-secret
    description: Scan for secrets before commit
    event: PreToolUse
    matcher: Bash
    command: 'bash -lc "~/.teamai/team-scripts/scan-secret.sh" || true'
    tools: [claude, cursor]
teamai hooks list      # list effective hooks
teamai hooks inject    # re-reconcile into every installed tool
teamai hooks remove    # remove all teamai-managed hooks

Declare once in mcp/mcp.yaml; teamai pull writes each tool's native config. Use ${VAR} for secrets.

servers:
  - name: gpu-analysis
    transport: http            # stdio | http | sse
    url: https://example.com/api/mcp
    headers:
      Authorization: Bearer ${GPU_ANALYSIS_TOKEN}
teamai mcp list | inject | remove

Subscribe to additional skill repos — other teams' public repos, or shared/public repos within your own org:

teamai source add https://github.com/other-team/teamai-public.git --name other-team
teamai source list
teamai source browse other-team    # browse available skills
teamai source remove other-team

The add/remove change takes effect locally right away, and subscribed skills sync on the next teamai pull. Run teamai push when you want to share the teamai.yaml change with teammates.

Share and restore the team's npm packages and Claude Code plugins:

teamai install typescript
teamai install typescript@5.9.2 --npm
teamai install code-review@claude-plugins-official
teamai push       # Share the declarations
teamai install    # Install everything declared by the team

See the Usage Guide for the complete workflow and configuration.

Every agent understands how the team works.

Beyond distributing the Harness, TeamAI organizes accumulated team experience and code structure into a searchable knowledge base that the AI recalls automatically when needed.

When a session ends, the Stop hook scores it by friction — signals that the session hit something worth remembering: you interrupted or corrected the AI, denied a tool call, or the AI had to retry failing tools. A long-but-routine session (lots of tool calls, no friction) does not trigger; a session where you actually fought a problem does. If the score is high enough, the AI suggests:

[teamai] This session may contain a problem worth documenting: you interrupted the AI twice, the AI retried failing tools 8 times.

Task: Fix duplicate project-level Hook injection

Consider running /teamai-share-learnings to summarize what you learned and share it with your team.

The hint names the non-zero friction signals that triggered it and, when available, includes a redacted, single-line summary of the first task. The /teamai-share-learnings skill summarizes the session and pushes a learning document directly to the team repo. Each session is prompted at most once.

Let the AI automatically search accumulated team knowledge before a task. This feature is off by default and must be enabled explicitly — teams can set sharing.recall.enabled: true in teamai.yaml as the default, and members can override locally:

teamai recall enable     # on: deploy the teamai-recall subagent + inject guidance rules
teamai recall disable    # off: remove the subagent and rules
teamai recall status     # show effective state (team default + user override)

Search runs via a subagent: once enabled, teamai pull deploys the built-in teamai-recall subagent into each AI tool's agents/ directory. The AI invokes it before a task — the subagent extracts keywords, runs the search, reads the matched source files, and returns a structured summary of team knowledge. The subagent first runs a relevance precheck (teamai recall --check) and skips retrieval entirely when the task is unrelated to team knowledge. Under the hood it shells out to the teamai recall command, which you can also run manually:

$ teamai recall "port conflict"
[1/2] MR review caught a port-conflict bug ★1 [user]
Author: member-a | Score: 18.5 | Tags: troubleshooting, networking

[2/2] Deployment configuration best practices [project]
Author: member-b | Score: 12.0 | Tags: deploy, config
Matched: conflict | Missing: port

teamai import parses source repos into a structured graph under teamwiki/, enabling structurally-aware retrieval:

teamai import --from-repo https://github.com/org/repo
teamai import --from-org myorg              # batch import all repos
teamai codebase --lint                      # health check

The graph stores components, interfaces, configs, and cross-repo import edges. teamai recall uses it for graph-boosted re-ranking. When a recall hit comes from a codebase page, the result includes a Sources: line listing the relevant source file paths — giving agents a direct starting point for code changes instead of re-exploring the repo.

Edges come from two tracks that run together, with AST results taking precedence on overlap:

• AST track (TypeScript/JavaScript, Python, Go): a WASMtree-sitter parser resolvesimport /require , call sites, and TSimplements clauses to precise file-to-fileDEPENDS_ON /REFERENCES /IMPLEMENTS edges (taggedcode-ast , with confidence weights).
• Heuristic track (all languages, including Java/Rust): regex-based extraction (taggedcode-heuristic ), which also covers languages the AST track does not.

The WASM parser is a pure-JavaScript dependency — no native toolchain is required. If it fails to load for any reason, extraction falls back to the heuristic track and records an AST_UNAVAILABLE gap. Set TEAMAI_SKIP_AST=1 to force heuristic-only extraction.

Every execution makes the entire team smarter.

Insight into how the team actually uses its AI tools, and a starting point for turning session friction into shared skills, rules, and knowledge:

PRs are welcome! Please read CONTRIBUTING.md first.