Docs
AI assistants carry out coding tasks. This guide covers command-line tools (CLI), terminal menus (TUI), the terminal tool that keeps tasks running (tmux), and a standard connection between AI tools (MCP).
Install
You need macOS, Linux or WSL, Node 22.12 or newer, tmux 3.0 or newer, and at least one provider CLI that is installed and signed in.
$ pnpm add -g reevesagents$ reevesagents doctor$ reevesagentsreevesagents doctor checks all of that. reevesagents setup runs the same checks as a first-run wizard, and with --attach it also connects the MCP to every installed host.Quick start
Start a team, check on it, step in, and stop it.
Start a team
reevesagents spawn cc:lead codex:api kimi:docs \
--name "feature x" --prompt "Build feature X. The lead splits the work."Each assistant is written as provider[:nickname[:model]], and the first one leads. Use reevesagents add to add assistants to the latest run.
Watch and steer
reevesagents runs
reevesagents peek api -n 40
reevesagents send api "run the tests"
reevesagents key api enter
reevesagents open apisend pastes text without submitting it, so follow it with key <agent> enter. open takes you to the assistant in tmux.
Stop
reevesagents stop "feature x" --yesstop, kill and the delete commands need --yes (or ALLOW_DESTRUCTIVE=1).Terminal menu, browser and commands
The menu (TUI), browser interface and command-line tool (CLI) share task records under ~/.reeves. The terminal tool tmux keeps assistants running.
- Type
reevesagentswith no arguments to open the TUI. It wraps itself in a tmux session calledreeves, whichREEVES_NO_TMUX_WRAPPER=1turns off. reevesagents webstarts the Web UI on127.0.0.1, port 8080 or the next free one. It refuses non-loopback Host headers and cross-origin writes, and Ctrl+C stops it without touching your assistants.- Everything is also a CLI command. Scripts should read
--json, because the plain text output may change between versions. - Underneath sits tmux, with one session per run and one window per assistant.
reevesagents open <id>jumps to the right window from wherever you are.
Agent Control (MCP)
Connect one coding tool to the others through a standard protocol (MCP). This is optional. Restart the tool after attaching it.
reevesagents attach cc
reevesagents hosts- Six CLIs can host it: Claude Code, Codex, Kimi Code, Qwen Code, Hermes and OpenCode.
reevesagents attachwith no name attaches all the installed ones, andreevesagents detach <cli>removes it again. - The host gets plain tools to spawn assistants, paste text, press keys, read output and handle approvals. What the team does is decided by whoever prompts the host.
- Spawned workers do not get the tools unless you attach their CLI too. MCP spawning enforces
max_agents(100 by default) as the per-run assistant limit.
Commands
Every reevesagents subcommand. With no arguments it opens the TUI.
Runs
spawn [spec...]Start a run. Each spec is provider[:nickname[:model]] and the first one leads. Flags:
add [spec...]Add agents to the most recent active run. Flags:
runsList active runs.
open <id>Jump to a run or agent window in tmux. Accepts an id, name, nickname or unique prefix.
peek <agent-id>Print recent output from one agent.
stop <run-id>needs Stop one run and tear down its tmux session.
kill <agent-id>needs Stop one agent. The run ends with its last live agent.
Driving an assistant
send <agent-id> <text...>Paste text at the agent prompt. Does not submit.
key <agent-id> <key>Send one allowed key: enter, escape, backspace, tab, space, arrows,
interrupt <agent-id>Send
Records and history
agents [run-id]List agents across active runs or one specified run.
providersList providers with availability and known models.
toolsList the agent tools with install and sign-in status.
delete <agent-id>needs Delete an ended agent record.
delete-run <run-id>needs Delete an ended run.
historyList archived run history.
delete-history <id>needs Delete one history record.
Approvals
approvalsList pending approvals.
approve <approval-id> [note]Resolve an approval as approved.
deny <approval-id> [note]Resolve an approval as denied.
MCP hosts
hostsList MCP-capable host CLIs and which are attached.
attach [cli]Attach the MCP to one host CLI, or all installed hosts, using its CLI or config file.
detach <cli>Detach from one host CLI using its CLI or config file.
mcpStart the Agent Control MCP server over stdio. The host CLI runs this itself.
Config and presets
config [key] [value]Show, get, or set an editable config field.
presetsList saved presets.
save-preset <run-id> <name> [description...]Capture a live run into a preset.
start-preset <name>Start a run from a preset.
delete-preset <name>needs Delete a preset.
Setup and tools
setupFirst-run check of tmux, Node and installed CLIs.
doctorRun environment health checks. Non-zero exit on failure.
skills [action]Install, remove or check the ReevesAgents skill for skill-aware CLIs (install, remove, status; default status).
reapEnd agents whose window is gone or that passed max_lifetime_ms, and kill orphan tmux sessions.
webStart the loopback-only Web UI in the foreground.
MCP tools
The 31 tools an attached CLI can call, grouped by purpose.
Spawn and drive
spawnrequiredprovideroptionalrun_idmodeltasknicknamenameworking_dirpermissionsauth_modeeffortextra_argsSpawn a worker. Omit run_id to reuse this MCP session’s run, created on its first spawn; pass run_id to target another run.
killrequiredagent_idStop one agent.
stoprequiredrun_idStop a whole run and tear down its tmux session.
send_textrequiredagent_idtextPaste text at an agent prompt. Does not submit.
send_keyrequiredagent_idkeySend one allowed key: enter, escape, backspace, tab, space, arrows,
interruptrequiredagent_idSend
readrequiredagent_idoptionallinesRead recent pane output, ANSI-stripped and redacted. Default: 20 lines.
Inspect
listList runs and agents.
list_providersProvider and model catalog for this machine.
list_toolsTool catalog for this machine: helper CLIs an agent can run from its shell, with install and sign-in status.
list_historyArchived runs.
list_presetsSaved presets.
list_hostsMCP-capable CLIs and which are attached.
get_configCurrent global config.
doctorEnvironment health checks.
Approvals
request_approvalrequiredagent_idactionsummaryoptionaldetailsriskRaise an approval request.
resolve_approvalrequiredapproval_iddecisionoptionalnoteApprove or deny a pending request.
check_approvalrequiredapproval_idRead one approval.
list_approvalsoptionalrun_idstatusList approvals, filterable.
Lifecycle
deleterequiredagent_idDelete an ended agent record.
delete_runrequiredrun_idDelete an ended run.
delete_historyrequiredidDelete one history record.
openrequiredidSwitch the attached tmux client to a run or agent.
reapSweep dead-window and over-lifetime agents plus orphan tmux sessions now.
Config and presets
set_configoptionalpeek_interval_mspeek_linesmax_depthmax_agentsready_delay_msmax_lifetime_msdefault_permissionslanguageSet one or more editable config fields.
save_presetrequiredrun_idnameoptionaldescriptionCapture a live run as a preset.
start_presetrequirednameoptionalrun_nameworking_dirStart a run from a preset.
delete_presetrequirednameDelete a preset.
Hosts and skills
attach_hostoptionalkeyAttach the MCP to one host CLI, or all.
detach_hostrequiredkeyDetach the MCP from one host CLI.
install_skillsoptionalstatusInstall the ReevesAgents skill for skill-aware CLIs, or report where it is.
reevesagents://providers, reevesagents://guideConfiguration
Settings live in ~/.reeves/config.json. Change one with reevesagents config <key> <value> or from the settings screens. reevesagents config language tr switches the interface to one of its ten languages.
Fields
peek_interval_ms5000
Saved polling-interval setting. Current UIs use fixed refresh intervals.
peek_lines10
Saved output-line setting. Current screens and CLI/MCP reads use their own line counts.
max_agents100
Per-run live-agent cap enforced by MCP spawn. Other launch surfaces do not enforce it.
max_depth5
Saved recursion-depth setting. The current run engine does not enforce it.
ready_delay_ms5000
Wait for a fresh CLI to settle before pasting a prompt.
max_lifetime_ms0
Reap agents older than this. 0 turns it off.
default_permissionsask
Default permission mode for new agents: ask or skip.
languageen
UI language, one of the ten locale codes.
peek_interval_ms | 5000 | Saved polling-interval setting. Current UIs use fixed refresh intervals. |
peek_lines | 10 | Saved output-line setting. Current screens and CLI/MCP reads use their own line counts. |
max_agents | 100 | Per-run live-agent cap enforced by MCP spawn. Other launch surfaces do not enforce it. |
max_depth | 5 | Saved recursion-depth setting. The current run engine does not enforce it. |
ready_delay_ms | 5000 | Wait for a fresh CLI to settle before pasting a prompt. |
max_lifetime_ms | 0 | Reap agents older than this. 0 turns it off. |
default_permissions | ask | Default permission mode for new agents: ask or skip. |
language | en | UI language, one of the ten locale codes. |
State on disk
~/.reeves/
config.json
presets/<name>.json
runs/<run-id>/
run.json
agents/<agent-id>.json
approvals/<approval-id>.json
history/runs/<run-id>.jsonEnvironment overrides
REEVES_REGISTRYOverride the state root (default
REEVES_CONFIGOverride the config file path.
REEVES_NO_TMUX_WRAPPER=1Do not auto-wrap the TUI into a tmux session.
REEVES_NO_COLOR=1Disable TUI colors.
ALLOW_DESTRUCTIVE=1Allow destructive commands without
REEVES_DOCTOR_SKIP_PROVIDER_COMPAT=1Skip the provider-compatibility doctor check.
Providers
25 CLIs, each with a short id you use in a spawn spec. Model lists are suggestions, and any model id you pass goes straight to the provider.
Claude CodeMCP host
Anthropic's coding agent for the terminal
id
ccbinaryclaudesuggested models fable, opus, sonnet, haiku
Codex CLIMCP host
OpenAI's coding agent CLI
id
codexbinarycodexsuggested models gpt-5.6-sol, gpt-5.5, gpt-5.4-mini
OpenCode CLIMCP host
Open-source coding agent for the terminal
id
opencodebinaryopencodesuggested models opencode/claude-sonnet-4-6, opencode/claude-opus-4-8, opencode/gpt-5.2-codex, anthropic/claude-opus-4-8, anthropic/claude-haiku-4-5, openai/gpt-5.5
HermesMCP host
Nous Research's agent CLI
id
hermesbinaryhermessuggested models anthropic:claude-opus-4-8, anthropic:claude-fable-5, openai-codex:gpt-5.5, openai-codex:gpt-5.4-mini
Kimi CodeMCP host
Moonshot AI's coding CLI
id
kimibinarykimisuggested models kimi-code/k3, kimi-code/kimi-for-coding, kimi-code/kimi-for-coding-highspeed
DeepSeek CLI
DeepSeek's coding CLI
id
deepseekbinarydeepseeksuggested models deepseek-v4-pro, deepseek-v4-flash
Pi
A minimal terminal coding harness
id
pibinarypisuggested models sonnet, opus, deepseek/deepseek-chat, openai/gpt-4o
Qwen CodeMCP host
Alibaba's coding agent CLI
id
qwenbinaryqwensuggested models qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next
Aider
AI pair programming in the terminal
id
aiderbinaryaidersuggested models sonnet, opus, haiku, deepseek/deepseek-chat
Gemini CLI
Google's open-source terminal agent
id
geminibinarygeminisuggested models gemini-3.1-pro-preview, gemini-3.5-flash, gemini-3.1-flash-lite
Cline CLI
Autonomous coding agent CLI
id
clinebinaryclinesuggested models anthropic/claude-sonnet-4-6, anthropic/claude-opus-4-8, google/gemini-3.1-pro
Crush
Charm's coding agent for the terminal
id
crushbinarycrushsuggested models chosen inside the CLI
Goose
Open-source general-purpose AI agent
id
goosebinarygoosesuggested models claude-sonnet-4-6, claude-opus-4-8, deepseek-v4-pro
Kilo Code
Open-source coding agent and CLI
id
kilobinarykilosuggested models kilo/~anthropic/claude-sonnet-latest, kilo/~anthropic/claude-opus-latest, kilo/~google/gemini-pro-latest, kilo/~openai/gpt-sol-latest
Letta Code
Coding agent with long-term memory
id
lettabinarylettasuggested models zai-org/GLM-5.3-max, moonshotai/Kimi-K2-Instruct, Qwen/Qwen3-Coder-480B-A35B-Instruct
Mistral Vibe
Mistral's coding agent CLI
id
vibebinaryvibesuggested models chosen inside the CLI
Grok Build
xAI's coding agent CLI
id
grokbinarygroksuggested models grok-4.6, grok-4.5, grok-4.7
Kiro CLI
AWS's agentic coding CLI
id
kirobinarykiro-clisuggested models claude-sonnet-4.6, claude-opus-4.7, claude-opus-4.6
Factory Droid
Factory's coding agent CLI
id
droidbinarydroidsuggested models chosen inside the CLI
Qoder CLI
Qoder's agentic coding CLI
id
qoderbinaryqoderclisuggested models auto, performance, lite
Warp
Warp's agent in the terminal
id
warpbinarywarpsuggested models chosen inside the CLI
Junie CLI
JetBrains' coding agent CLI
id
juniebinaryjuniesuggested models sonnet, opus, gpt-sol
GitHub Copilot CLI
GitHub's coding agent CLI
id
copilotbinarycopilotsuggested models auto, gpt-5.4, claude-opus-4.8
Cursor CLI
Cursor's coding agent CLI
id
cursorbinarycursor-agentsuggested models gpt-5, sonnet-4-thinking, claude-opus-4-8
Rovo Dev CLI
Atlassian's coding agent CLI
id
rovobinaryaclisuggested models chosen inside the CLI
| Provider | id | binary | suggested models | MCP host |
|---|---|---|---|---|
| Claude CodeAnthropic's coding agent for the terminal | cc | claude | fable, opus, sonnet, haiku | ✔ |
| Codex CLIOpenAI's coding agent CLI | codex | codex | gpt-5.6-sol, gpt-5.5, gpt-5.4-mini | ✔ |
| OpenCode CLIOpen-source coding agent for the terminal | opencode | opencode | opencode/claude-sonnet-4-6, opencode/claude-opus-4-8, opencode/gpt-5.2-codex, anthropic/claude-opus-4-8, anthropic/claude-haiku-4-5, openai/gpt-5.5 | ✔ |
| HermesNous Research's agent CLI | hermes | hermes | anthropic:claude-opus-4-8, anthropic:claude-fable-5, openai-codex:gpt-5.5, openai-codex:gpt-5.4-mini | ✔ |
| Kimi CodeMoonshot AI's coding CLI | kimi | kimi | kimi-code/k3, kimi-code/kimi-for-coding, kimi-code/kimi-for-coding-highspeed | ✔ |
| DeepSeek CLIDeepSeek's coding CLI | deepseek | deepseek | deepseek-v4-pro, deepseek-v4-flash | |
| PiA minimal terminal coding harness | pi | pi | sonnet, opus, deepseek/deepseek-chat, openai/gpt-4o | |
| Qwen CodeAlibaba's coding agent CLI | qwen | qwen | qwen3-coder-plus, qwen3-coder-flash, qwen3-coder-next | ✔ |
| AiderAI pair programming in the terminal | aider | aider | sonnet, opus, haiku, deepseek/deepseek-chat | |
| Gemini CLIGoogle's open-source terminal agent | gemini | gemini | gemini-3.1-pro-preview, gemini-3.5-flash, gemini-3.1-flash-lite | |
| Cline CLIAutonomous coding agent CLI | cline | cline | anthropic/claude-sonnet-4-6, anthropic/claude-opus-4-8, google/gemini-3.1-pro | |
| CrushCharm's coding agent for the terminal | crush | crush | chosen inside the CLI | |
| GooseOpen-source general-purpose AI agent | goose | goose | claude-sonnet-4-6, claude-opus-4-8, deepseek-v4-pro | |
| Kilo CodeOpen-source coding agent and CLI | kilo | kilo | kilo/~anthropic/claude-sonnet-latest, kilo/~anthropic/claude-opus-latest, kilo/~google/gemini-pro-latest, kilo/~openai/gpt-sol-latest | |
| Letta CodeCoding agent with long-term memory | letta | letta | zai-org/GLM-5.3-max, moonshotai/Kimi-K2-Instruct, Qwen/Qwen3-Coder-480B-A35B-Instruct | |
| Mistral VibeMistral's coding agent CLI | vibe | vibe | chosen inside the CLI | |
| Grok BuildxAI's coding agent CLI | grok | grok | grok-4.6, grok-4.5, grok-4.7 | |
| Kiro CLIAWS's agentic coding CLI | kiro | kiro-cli | claude-sonnet-4.6, claude-opus-4.7, claude-opus-4.6 | |
| Factory DroidFactory's coding agent CLI | droid | droid | chosen inside the CLI | |
| Qoder CLIQoder's agentic coding CLI | qoder | qodercli | auto, performance, lite | |
| WarpWarp's agent in the terminal | warp | warp | chosen inside the CLI | |
| Junie CLIJetBrains' coding agent CLI | junie | junie | sonnet, opus, gpt-sol | |
| GitHub Copilot CLIGitHub's coding agent CLI | copilot | copilot | auto, gpt-5.4, claude-opus-4.8 | |
| Cursor CLICursor's coding agent CLI | cursor | cursor-agent | gpt-5, sonnet-4-thinking, claude-opus-4-8 | |
| Rovo Dev CLIAtlassian's coding agent CLI | rovo | acli | chosen inside the CLI |
--effortsets reasoning effort for Claude Code and Codex.--auth-mode api-keyapplies to Claude Code.- Pass any other launch flag with
--extra-args, for example Claude Code's--remote-control. - Keep permission prompts enabled.
--skipdisables them in the coding tools.
Agent tools
Four helper CLIs an agent can run from its own shell. They cannot take a chat task, so they are not spawnable providers. reevesagents tools lists them with install and sign-in status.
Perplexity CLI
pplxWeb search and page snippets from Perplexity, as JSON.
Google Colab CLI
colabCPU, GPU and TPU runtimes on Google Colab: run scripts and notebooks remotely.
Download and upload models and datasets, run jobs on the Hugging Face Hub.
Ollama
ollamaRun local or Ollama cloud models from the terminal.
Troubleshooting
Start with reevesagents doctor. It usually names the problem.
tmux is missing
Install it with brew install tmux or sudo apt install tmux, then run doctor again.
A provider does not show up
The CLI is usually not installed or not signed in. Fix that, then check with reevesagents providers.
The Web UI says packages are missing
The live terminal needs the optional ws and @lydell/node-pty modules. Reinstall globally with npm or pnpm to get them back.
Port 8080 is taken
The Web UI moves to the next free port and prints the URL. Pick one yourself with reevesagents web --port 8090.
Native Windows
Run the full product in WSL. For Agent Control only, reevesagents-win runs natively as an MCP server.
Facts you can check
- GitHub stars
- 107
Downloads cover 2025-04-14 to 2026-10-14. GitHub and npm figures checked on 2026-10-15; downloads count package fetches.
Last updated: