magents

Shared session bus MCP+CLI for Claude/Codex/Cursor/Grok: list, read, handoff, send, spawn.

OtherRustv0.12.0

Claude Code, Codex, Copilot, Cursor, Gemini, Grok, and OpenCode already keep transcripts on disk. magents is the shared API over those sessions - an MCP server plus a small CLI - so one agent can pick up where another left off without you recapping, ping a specific live chat when you are not sitting in the middle, or start an independent persisted chat for a complete task.

It is not a second copy of history and not a fire-and-forget council. Existing chats stay the default unit of work; new chats are for independent work that benefits from its own session and working directory.

Install · Plugins · What you can do · Quick start · Tools · CLI · Releases

Why

You already run more than one coding agent. The pain is not "more models" - it is context trapped in another window.

PainWhat magents does
You switched hosts mid-taskRead the live session and continue here
Agent A hit a wall Agent B ownsInject into that live chat without you as the messenger
A subtask can run aloneSpawn a headless persisted session with a complete prompt + reply path

What you can do

1. Handoff without a new thread
You were in Claude on the disaster-recovery branch. Now you are in Grok. Ask Grok what they were doing; it reads the live session and continues. No paste buffer. No "new chat, here's the context."

2. Send when you are not the messenger
Three agents running. Claude hits a wall Codex owns. Claude injects into that Codex thread and keeps going - especially useful when the sender already has the failing query, file, and constraint you would otherwise reconstruct.

3. Spawn independent work
When a task can proceed alone, start a new headless persisted session with a complete prompt, an isolated working directory when files could collide, and a request to reply through magents. Spawned agents keep their host's native approval policy - spawning does not add an approval bypass.

Install

Homebrew (macOS / Linux)

brew install abnegate/tap/magents
magents install --all

APT (Debian / Ubuntu)

curl -fsSL https://abnegate.github.io/apt-repo/pubkey.gpg | sudo gpg --dearmor -o /usr/share/keyrings/abnegate.gpg
echo "deb [signed-by=/usr/share/keyrings/abnegate.gpg] https://abnegate.github.io/apt-repo stable main" | sudo tee /etc/apt/sources.list.d/abnegate.list
sudo apt update && sudo apt install magents
magents install --all

Binary

From Releases:

curl -LSsf -o magents \
  "https://github.com/abnegate/magents/releases/latest/download/magents-$(uname -m | sed 's/arm64/aarch64/')-$(uname -s | tr 'A-Z' 'a-z' | sed 's/darwin/apple-darwin/;s/linux/unknown-linux-musl/')"
chmod +x magents
./magents install --all

Assets: magents-x86_64-unknown-linux-musl, magents-aarch64-unknown-linux-musl, magents-aarch64-apple-darwin, magents-x86_64-apple-darwin.

Container

docker pull ghcr.io/abnegate/magents:latest
docker run --rm --user "$(id -u):$(id -g)" \
  -v "$HOME:$HOME" -e HOME \
  ghcr.io/abnegate/magents list --live

From source

cargo install --path .
magents install --all

Plugins

Host plugins package the magents skill plus an MCP entry that runs magents mcp. Install the CLI first (brew install abnegate/tap/magents), then load the matching folder under plugins/.

HostPath
Claude Codeplugins/claude
Codexplugins/codex
Cursorplugins/cursor

Details and marketplace notes: plugins/README.md.

Quick start

magents install --all registers the stdio MCP server with each installed host, skipping hosts whose required binaries are unavailable:

  • Grok (grok mcp add magents -- magents mcp)
  • Claude Code (claude mcp add --scope user magents -- magents mcp)
  • Codex (codex mcp add magents -- magents mcp)
  • Cursor (~/.cursor/mcp.json)
  • OpenCode (~/.config/opencode/opencode.json)
  • Gemini CLI (gemini mcp add -s user magents magents mcp)
  • GitHub Copilot CLI (copilot mcp add magents -- magents mcp)

It also writes the magents and learn skills under supported hosts' skills directories (~/.grok/skills/{magents,learn}, ~/.claude/skills/{magents,learn}, ~/.cursor/skills/{magents,learn}, and the OpenCode / Gemini / Copilot equivalents). /learn reads every local agent's sessions, not only Grok.

For Grok and Codex only, point a host at the binary yourself:

[mcp_servers.magents]
command = "/path/to/magents"
args = ["mcp"]

Restart the agent session (or refresh /mcps) so the tools appear.

Try:

magents list --live
magents digest grok:latest
magents handoff grok:latest --reason "continuing in grok"

Tools

ToolPurpose
list_sessionsLive and recent sessions; filter by cwd / branch
get_sessionLookup by id, title, live name, pid, or agent:ref
read_transcriptCompact inert handoff (last request, last action, recent turns)
search_transcriptsFull-text search across those transcripts
search_memoriesPhrase search over Claude / Codex / Grok memory markdown
create_memoryWrite a note into Claude / Codex / Grok first-party memory
spawn_sessionStart a new headless persisted session for independent work
send_messageDeliver a user turn to an existing chat
handoffCompact this session and inject it into another live chat
inbox / ack / await_reply / replyMailbox for cross-session replies
session_digestCompact last request / action / cwd / branch / clipped turns
files_touchedPaths another session edited
stop_sessionStop a magents-supervised spawn or resume
read_memoryRead one Claude / Codex / Grok memory markdown file
get_note / put_noteMagents-owned shared scratch for a working directory
whoamiDetect this connection; resolve session via env, socket, or unique cwd
learn_collectCollect compact records from every local agent's full history for /learn, or estimate a run
learn_stateRead or update /learn state, decisions, and trash

Refs can be prefixed: claude:disaster recovery, grok:latest, codex:<uuid>, cursor:latest, opencode:<id>, gemini:latest, copilot:<id>.

CLI

magents list --live
magents list --agent grok --query edge
magents get 'claude:disaster recovery'
magents read grok:latest -n 20
magents digest grok:latest
magents search "dedicated databases" --agent claude
magents spawn codex --prompt-file /path/to/task.md --cwd /path/to/isolated-worktree
magents send grok:latest "handoff: the DR runbook is in docs/RUNBOOK.md"
magents handoff grok:latest --reason "continuing in grok"
magents whoami
magents learn estimate
magents learn collect
magents learn plan
magents learn collect --since-last
magents learn state

Pass --output json on any command for stable machine-readable stdout.

magents with no args on a piped stdin starts the MCP server.

magents spawn reads the complete task from stdin by default (--prompt-file supported). Prompt text is never a process argument.

How sessions talk

list_sessions / read_transcript / search_transcripts / search_memories are the handoff. create_memory writes into another harness's first-party memory (Claude, Codex, or Grok).

Choose the write path by where the work should happen:

  • spawn_session - new, headless, persisted, independent session. Complete task, verification, reply-through-magents, isolated cwd when edits could collide. Success means launch accepted (accepted: true, status: "starting"), not that the task finished.
  • send_message - existing session. Always records mailbox mail; injects a live user turn where the host supports one.
  • handoff - compact this session into an existing live session so that session continues the same work.

Delivery routes (existing chats)

send_message always appends to the mailbox, then prefers a native live path and otherwise starts a supervised headless resume:

SurfaceDelivery route
Claude DesktopUDS user turn (/tmp/cc-socks/<pid>.sock), then tmux or supervised claude -p --verbose --resume <id>
Claude CLIUDS when available, then tmux or supervised resume
GrokSupervised grok --cwd <cwd> --resume <id> --output-format streaming-json --prompt-file /dev/stdin
Codex Desktop / VS CodeLength-prefixed JSON-RPC on ~/.codex/ipc/ipc.sock, then supervised codex exec ... resume
Codex CLISupervised codex exec --json -C <cwd> resume <id> -
CursorSupervised cursor-agent -p --output-format stream-json --resume <id> --workspace <cwd>
OpenCodeSupervised opencode run --format json --dir <cwd> --session <id>
Gemini CLISupervised gemini --resume <id> --output-format stream-json
GitHub Copilot CLISupervised copilot --resume=<id> --output-format json

Supervised routes pass the user turn through stdin and do not expose transcript text, tokens, or raw host output in the response. Spawn never adds approval bypasses (--dangerously-skip-permissions, --yolo, --full-auto, etc.).

Session discovery sources (unchanged): Claude ~/.claude/sessions, Grok ~/.grok/active_sessions.json, Codex sqlite + rollout JSONL, Cursor agent-transcripts, OpenCode DB, Gemini journals, Copilot session-state.

Tests

cargo test --locked --all-targets
cargo llvm-cov --locked --all-targets --ignore-filename-regex 'src/main.rs|/rustlib/' --fail-under-lines 98

CI runs format, clippy (-D warnings), the full test suite, and a 98% line-coverage gate.

Requirements

  • Rust 1.88+
  • macOS or Linux (Claude UDS inject is Unix-only)

License

MIT

Installation

Source-derived launch command. Check the maintainer’s required arguments and credentials before running:

bash
docker run -i --rm ghcr.io/abnegate/magents:0.12.0

Set up in your AI client

Merge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.

json
{
  "mcpServers": {
    "io-github-abnegate-magents": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/abnegate/magents:0.12.0"
      ]
    }
  }
}

Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.

Claude Desktop setup reference

Package

ghcr.io/abnegate/magents:0.12.0docker

Compatible MCP Clients

magents works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.

  • Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.
  • Cursor~/.cursor/mcp.jsonRestart Cursor for changes to take effect.
  • VS Code.vscode/mcp.jsonReload VS Code window for changes to take effect.
  • Windsurf~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect.
  • Claude Code.mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.

Learn More