claude-anyteam

Native Claude Code teammates, any LLM.

Codex, Gemini, and Kimi today. GLM, DeepSeek next — on the same team-native architecture.

Quickstart · Architecture · Roadmap

claude-anyteam spawning a mixed Codex + Claude team

What it is

Claude Code's Agent Teams feature is built for multi-agent collaboration — but every teammate is a Claude instance. claude-anyteam makes it possible for any external agent harness to join the same team, with the same native UX, without wrapping it inside a Claude LLM.

Your Claude Code session orchestrates. External agents execute. No chat-wrapper overhead. No "Claude pretending to be Codex." No routers. Real agent CLIs, real teammates.

claude-anyteam architecture

Quickstart

npx --yes claude-anyteam

That's the entire install. The installer:

Detects python3 and installs uv if missing (non-interactive, no shell profile edits)
Installs the claude-anyteam Python tool via uv tool install
Runs claude-anyteam install (verifies tmux/psmux, probes for the OpenAI Codex CLI, Gemini CLI, and Kimi CLI, warns if any are missing or Codex is below 0.120, writes ~/.claude/settings.json + ~/.claude.json, records install-state for symmetric uninstall)

Restart Claude Code, enable Agent Teams mode, and create a teammate named codex-<anything>, gemini-<anything>, or kimi-<anything>:

codex-alice      → routed to claude-anyteam + Codex
codex-reviewer   → routed to claude-anyteam + Codex
gemini-alice     → routed to claude-anyteam + Gemini CLI
gemini-reviewer  → routed to claude-anyteam + Gemini CLI
kimi-architect   → routed to claude-anyteam + Kimi CLI
kimi-reviewer    → routed to claude-anyteam + Kimi CLI
alice            → native Claude (unchanged)

Codex-, Gemini-, and Kimi-prefixed names appear in your TUI presence line exactly like native teammates. Single-terminal mode or tmux — both work.

Provider CLIs are runtime prerequisites for their prefixes: install/authenticate Codex for codex-*, Gemini for gemini-*, and Kimi for kimi-* (uv tool install --python 3.13 kimi-cli or the upstream installer, then kimi login). The probed Kimi default user-facing model slug is kimi-code/kimi-for-coding (Kimi-k2.6, 262k context).

Why it feels native

Real teammate protocol

Not a chat wrapper. The adapter speaks Claude Code's agent-team protocol directly: mailbox I/O, atomic task claims, idle notifications, shutdown lifecycle. A Codex teammate is functionally indistinguishable from a native Claude teammate.

Mid-task reactivity

When a peer messages a working teammate, the adapter injects the message mid-turn via Codex's turn/steer App Server call. Codex reshapes the in-flight turn instead of discarding it. v7.1.

Cross-task memory

Each new task forks from the previous task's Codex thread via thread/fork. The teammate carries its own conversational context forward across the team's task list. v7.3.

Battle-tested parity

400 passing tests. Ten parity bugs caught by a live 4-teammate hunt (mixed Claude + Codex) and fixed. Zero accepted limitations on the protocol layer.

Supported backends

Backend	Teammate prefix	Status	Notes
Codex via OpenAI Codex CLI 0.120+	`codex-*`	✅ Supported today	App Server mode for mid-task steer and `thread/fork`; fresh-exec fallback with `codex exec resume`.
Gemini via Gemini CLI	`gemini-*`	✅ Supported today	Default headless `gemini --prompt ... --output-format stream-json`, plus ACP via `gemini-anyteam --backend acp`; ACP supports `--trust default
Kimi via Kimi CLI	`kimi-*`	✅ Supported today	Headless `kimi --print --output-format stream-json` with adapter-owned HOME and MCP wrapper. Best for large-context / architecture work and Kimi native skills/swarm. v1 has no Codex App Server or live `turn/steer`, no CLI `--output-schema`, and Kimi MCP tools are addressed by bare names.

Mixed-team example

codex-implementer   # Codex App Server executor
gemini-reviewer     # Gemini second-opinion reviewer
kimi-architect      # Kimi large-context architecture reviewer
claude-planner      # Native Claude lead/planner

Coming next

Coming next
⏳ GLM adapter
⏳ DeepSeek adapter
⏳ Generic CLI adapter template

Codex, Gemini, and Kimi are shipping. Everything in "coming next" is on the same architectural surface — each new model is a new adapter binary + one line in the spawn shim's routing table. See docs/roadmap.md.

Requirements

Python 3.12+
Node 18+ (for the npm installer; not required at runtime)
OpenAI Codex CLI 0.120+ on PATH for codex-* teammates
Gemini CLI on PATH for gemini-* teammates
Kimi CLI on PATH for kimi-* teammates (uv tool install --python 3.13 kimi-cli or upstream installer + kimi login)
Claude Code 2.1+ with Agent Teams mode
Terminal multiplexer on PATH (tmux or psmux) — see configuration.md

Docs

Install — how the installer wires Claude Code, alternative install methods, headless launches
Architecture — how the adapter integrates with Claude Code's team protocol
Roadmap — supported today vs coming next, contribution pointers
Configuration — CLI flags, env vars, advanced modes
Releasing — maintainer-facing tag-triggered publish flow

License

MIT

Metadata

Release files for claude-anyteam 0.8.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for claude-anyteam 0.8.4
File	Size	Uploaded
claude_anyteam-0.8.4.tar.gz	13.3 MB	May 5, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for claude-anyteam 0.8.4
File	Interpreter	ABI	Platform	Reset
claude_anyteam-0.8.4-py3-none-any.whl 337.2 kB May 5, 2026	Python 3	none	any	Details

Total release size: 13.6 MB

Release files / claude_anyteam-0.8.4.tar.gz

Download URL	claude_anyteam-0.8.4.tar.gz
Size	13.3 MB
Tags	Source
SHA-256 checksum How to use checksums	`2c27738ba1fd0f5e88f1ba63af4a4a431fe1d1ba06b7ff86d774dd047d59b4c3`
BLAKE2b-256 checksum How to use checksums	`666eaaaaf5eb4a1fd5e804f54c2a9bbb2b7570c48d070cfc1241d1178e0489fc`
Upload date	May 5, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.11.9 {"installer":{"name":"uv","version":"0.11.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`

Release files / claude_anyteam-0.8.4-py3-none-any.whl

Download URL	claude_anyteam-0.8.4-py3-none-any.whl
Size	337.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`ca3312d81c351cc5be7d20a461d20c3fefdd84f21b2e0094c08cbebffb78f138`
BLAKE2b-256 checksum How to use checksums	`e7b4f1e72db4e343074e58dc6af43b07b2afcabef23c0abb22c5110e0768eff7`
Upload date	May 5, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.11.9 {"installer":{"name":"uv","version":"0.11.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`