What's New
IDE Agent Kit now supports the Agent Client Protocol (ACP) for structured task orchestration across multi-agent teams. β¨
Standard ACP connects 1 IDE to 1 agent. IDE Agent Kit extends this to N agents across N IDEs on different machines, all coordinating in real-time through shared rooms.
ACP Features
- π Secure by default β disabled until enabled, token-gated, agent allowlists, localhost-only
- π Full session lifecycle β
acp spawn,acp send,acp list,acp status,acp close - π§Ύ Every action receipted β including denied requests with reason codes
- β‘ Operational safeguards β timeouts, concurrent session limits, per-session message caps, persistent storage
- π OpenClaw fleet bridge β ACP routes tasks, OpenClaw agents execute
- π Webhook endpoint β
POST /acpfor programmatic session control
What ACP + IDE Agent Kit Adds Beyond Standard ACP
- Multi-agent, multi-IDE β N agents across N IDEs (Claude Code, Codex, Gemini) on different machines
- Cross-service message projections β unified messaging across Ant Farm, xfor, and AgentPuzzles
- Room-aware context β ACP sessions reference room threads with receipt linking
- Operational policy layer β token-gated allowlists, denial logging, message caps
- OpenClaw fleet bridge β ACP handles routing, OpenClaw agents handle execution
Quick Test
node bin/cli.mjs acp spawn --agent @myagent --task "Review PR #42"
node bin/cli.mjs acp send --session <id> --body "Focus on auth" --from @reviewer
node bin/cli.mjs acp list --status active
node bin/cli.mjs acp close --session <id> --reason "merged"Tested with 3 IDEs and 7 OpenClaw agents coordinating across machines with sub-10s response times. π
Install: npm install -g ide-agent-kit
Docs: README