mertkayacs/reevesagents
mertkayacs/reevesagents has 108 GitHub stars and 14 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-17 23:15 UTC. Last push 2026-11-15.
What you can do
- reevesagents spawn provider[:nickname[:model]] starts a run. The first agent leads and the rest join as workers, and reevesagents add grows the latest run.
- Per agent you choose the model, the permission mode (ask first, or skip with each CLI's own bypass flag), reasoning effort for Claude Code and Codex, and extra launch flags.
- Presets save a live run and start it again later. Ended runs move to history, and reap ends zombie agents and orphan tmux sessions.
- peek reads recent output, send pastes text and key <id> enter submits it, interrupt sends Ctrl-C and open jumps to the agent's tmux window. stop and kill need --yes.
Measured star growth
- in 24h
- 0
- in 7 days
- 0
- in 15 days
- Update delayed
- in 1 month
- Update delayed
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
About
Run Claude Code, Codex, Kimi, OpenCode, Hermes and 20 other coding agents side by side, from the CLI, TUI, Web UI or MCP.
Developer ToolsREADME.md
Original
Spawn the team. Steer every agent.
Open-source workspace that runs AI coding CLIs side by side on your machine.
25 CLIs, each in its own tmux window. One of them can drive the rest over MCP.
ReevesAgents is a free, open-source workspace for AI coding agents. It runs Claude Code, Codex, Kimi, OpenCode, Gemini CLI and 20 other coding CLIs side by side, each in its own tmux window, and gives you a terminal UI, a browser UI and a scriptable CLI over the same runs. Attach its MCP server to one CLI and that agent can spawn, read, steer and stop the others. Every CLI keeps its own login, and ReevesAgents keeps its state in a few JSON files under ~/.reeves.
Why ReevesAgents
You already use these CLIs, and you are already signed in to them. ReevesAgents runs them as a team on your machine and leaves every login where it was.
| Claude Code, Codex, Kimi, OpenCode, Hermes, Gemini CLI and 19 more start from one command. Each runs as the real CLI in its own tmux window, so agents keep running after you close the UI. | |
reevesagents attach cc gives Claude Code the MCP tools to spawn, read, steer and stop other agents. Codex, Kimi Code, Qwen Code, Hermes and OpenCode can host it too, and it stays off until you attach it (details). |
|
| Each CLI signs in the way it always does. ReevesAgents stores no API keys, adds no proxy, and redacts token-like text in tasks, notes and approvals before it writes state. | |
A terminal UI, a Web UI with a live pane per agent, a CLI with --json output for scripts, and the MCP. All four read and write the same runs. |
|
A few JSON files under ~/.reeves, with no database and no Docker. The Web UI answers on 127.0.0.1 only and rejects foreign Host and Origin headers (guards). |
|
| tmux 3.0 or newer on macOS, Linux and WSL. Native Windows 10 1809 or later runs on the built-in winmux multiplexer over ConPTY, without WSL (2.1.0). |
A quick tour
Watch every agent livePick an agent to open its live terminal. Here the tests agent has added three cases and npm test reports two failures. |
Start a run from the browserChoose one of the 25 CLIs, a model and a permission mode. CLIs that are not installed are marked. |
Let one agent drive the restAttach the MCP to Claude Code, Codex, Kimi Code, Qwen Code, Hermes or OpenCode, then restart that CLI to load the tools. |
Script it from the terminalOne spawn line starts a mixed team and prints the commands to watch and steer it. |
The Web UI screenshots show a demo run of four Kilo Code agents on a sample repository. Any of the 25 CLIs works the same way.
Features
Run a team
reevesagents spawn provider[:nickname[:model]]starts a run. The first agent leads and the rest join as workers, andreevesagents addgrows the latest run.- Per agent you choose the model, the permission mode (ask first, or skip with each CLI's own bypass flag), reasoning effort for Claude Code and Codex, and extra launch flags.
- Presets save a live run and start it again later. Ended runs move to history, and
reapends zombie agents and orphan tmux sessions.
Watch and steer
peekreads recent output,sendpastes text andkey <id> entersubmits it,interruptsends Ctrl-C andopenjumps to the agent's tmux window.stopandkillneed--yes.- The Web UI shows every run, a live terminal for the selected agent, approvals, presets and history, in a light or dark theme and ten languages.
- A CLI with the MCP attached can ask for approval before a risky step, and you approve or deny it from the CLI or the Web UI.
Develop, review, fix
reevesagents flow startattaches a flow to an existing run: a developer agent, a reviewer agent and the repository. Eachflow tickmoves it one step: the developer gets the next spec, the reviewer checks the commit, and the item is closed or sent back for a fix within the round budgets.- Specs wait in a queue (
flow add-spec) or come from a plan imported from a document in the repository (flow plan).status,notes,logsandincidentsshow where each flow stands, what the reviewer found, the journal, and questions or failures that need attention. The TUI, the Web UI and the MCP tools show the same flows, and the MCP server runs a step only when asked.
Agent Control (MCP)
reevesagents attachconnects every installed host CLI, or one by its id:cc,codex,kimi,qwen,hermesoropencode.hostsshows the state anddetach <id>removes it.- The host gets tools to spawn agents, read their output, send text and keys, interrupt, stop, and handle approvals and presets. Workers get none of them unless you attach their CLI too.
- A Claude Code plugin ships in this repository, and the server is listed in the official MCP Registry as io.github.mertkayacs/reevesagents.
Local by design
- State is plain JSON under
~/.reeves, andREEVES_REGISTRYandREEVES_CONFIGmove it elsewhere. - Provider credentials are never stored and model traffic goes straight from each CLI to its provider. Known token patterns are redacted before state is written.
- The Web UI binds to 127.0.0.1, checks the Host header on every request and checks the Origin header on every request that changes state.
Helper tools
reevesagents toolslists Perplexity CLI, Google Colab CLI, Hugging Face CLI and Ollama with a purpose, an example command and their install and sign-in state. Agents call them from their own shell.
Quick start
Install with pnpm, check the machine, then open the terminal UI:
pnpm add -g reevesagents
reevesagents doctor
reevesagents
npm, Homebrew and a one-off check work too:
npm install -g reevesagents
brew install mertkayacs/reevesagents/reevesagents
npx reevesagents doctor
Start a team from the command line:
reevesagents spawn claude-code:lead codex:tests hermes:research \
--name "release check" \
--prompt "Review the release path, test coverage, and docs."
Open the Web UI, which listens on 127.0.0.1 only:
reevesagents web
Let Claude Code drive the others, then restart it so it loads the MCP tools:
reevesagents attach cc
reevesagents hosts
In Claude Code you can install the connection and its operating instructions as a plugin instead:
claude plugin marketplace add mertkayacs/reevesagents
claude plugin install reevesagents@reevesagents
Requirements
- Node.js 22.12 or newer.
- tmux 3.0 or newer on macOS, Linux and WSL. Native Windows 10 1809 or later uses the built-in winmux multiplexer instead.
- At least one supported coding CLI, installed and signed in.
reevesagents doctorchecks Node, tmux and which CLIs it can launch. - The Web UI uses the optional
wsand@lydell/node-ptymodules, which npm installs by default.
Supported CLIs
Use the id in a spawn spec such as codex:tests. Aliases like claude work there too, while attach and detach take the id.
| CLI | id | MCP host |
|---|---|---|
| Claude Code | cc |
yes |
| Codex CLI | codex |
yes |
| OpenCode CLI | opencode |
yes |
| Hermes | hermes |
yes |
| Kimi Code | kimi |
yes |
| DeepSeek CLI | deepseek |
|
| Pi | pi |
|
| Qwen Code | qwen |
yes |
| Aider | aider |
|
| Gemini CLI | gemini |
|
| Cline CLI | cline |
|
| Crush | crush |
|
| Goose | goose |
|
| Kilo Code | kilo |
|
| Letta Code | letta |
|
| Mistral Vibe | vibe |
|
| Grok Build | grok |
|
| Kiro CLI | kiro |
|
| Factory Droid | droid |
|
| Qoder CLI | qoder |
|
| Warp | warp |
|
| Junie CLI | junie |
|
| GitHub Copilot CLI | copilot |
|
| Cursor CLI | cursor |
|
| Rovo Dev CLI | rovo |
The binary on your PATH matches the id, except claude (cc), kiro-cli (kiro), qodercli (qoder), cursor-agent (cursor) and acli (rovo). reevesagents providers shows which of them it finds, with their aliases and suggested models.
FAQ
Does ReevesAgents store my API keys?
No. Each CLI keeps its own login and keys, the same as when you run it by hand. ReevesAgents keeps run records under ~/.reeves and redacts text that looks like a token before writing it.
Does my code leave my machine?
Each coding CLI sends your code to its own model provider, as it always does, and ReevesAgents adds nothing in between. The Web UI answers only on 127.0.0.1. To use it from another machine, forward the port over SSH with ssh -L 8080:127.0.0.1:8080 user@host.
Do I have to let one agent control the others?
No. Agents can work side by side with nobody in charge. Agent Control is an MCP server you attach to one CLI with reevesagents attach cc (or another id), and reevesagents detach cc removes it.
Can Codex drive the team?
Yes. Codex sandboxes MCP calls by default, which blocks tmux launches, so run it with full access when it hosts the MCP, for example codex --sandbox danger-full-access, or use a Codex profile that sets sandbox_mode = "danger-full-access".
What happens when I close the UI?
The agents keep working. Each one lives in its own tmux window, or a winmux window on native Windows, and reevesagents open <id> takes you back to it.
Does it run on Windows?
Yes. Since 2.1.0 it runs natively on Windows 10 1809 and later through the built-in winmux multiplexer, and it also runs in WSL.
Can I script it?
Yes. spawn, runs, agents, providers and doctor accept --json, and REEVES_REGISTRY and REEVES_CONFIG keep a scripted run away from your own ~/.reeves.
What does it cost?
ReevesAgents is free under Apache-2.0. Your providers bill you as usual, and ReevesAgents adds nothing on top.
Documentation
- User guide, also in nine other languages
- Agent Control MCP: attaching, the tool list and the safety model
- AGENTS.md: how an AI agent drives ReevesAgents
- Online docs: every command, configuration key and provider
- FAQ
- Changelog
- README in Deutsch, Français, Español, Português, Italiano, Türkçe, Русский, 简体中文 and العربية
Build from source
git clone https://github.com/mertkayacs/reevesagents.git
cd reevesagents
pnpm install
pnpm build
pnpm link --global
reevesagents doctor
Development
Contributors use pnpm, TypeScript, tsup, Vitest and ESLint from the repository. Run the focused checks before a pull request:
pnpm typecheck
pnpm lint
pnpm test
pnpm verify
pnpm verify runs the type check, lint, unit tests, the build, a CLI smoke test against fake provider binaries and a check of the npm package contents. Testing and releasing have the details.
Contributing and security
Issues and pull requests are welcome. See CONTRIBUTING.md. Report vulnerabilities privately as described in SECURITY.md.
If ReevesAgents is useful to you, a ⭐ helps other people find it.
License
Apache-2.0. ReevesAgents is built by Mert Kaya at Eschatia Labs, an independent, non-profit open-source AI research lab. Photos behind the screenshots are credited in docs/assets/readme/CREDITS.md.