RepoRadar
Leave a Tip
Item detail

im4codes/imcodes

IM.codes is an MIT-licensed cross-agent collaboration layer that gives Claude Code, Codex, Gemini CLI, GitHub Copilot, Cursor, OpenCode, OpenClaw, and Qwen a single shared memory, one managed MCP tool surface, supervised execution, and a cross-agent audit log. It turns completed work into reusable context, then injects or recalls the right history in future sessions, and ships a built-in auto-supe

Open source →Back to radar
Score8.0
Popularity84.0
Riskconditional
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum8.0
Maturity8.1
Open-source/build8.4
Evidence7.2
Workflow potential9.5
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for developer teams running more than one coding agent (Claude Code + Codex, or Gemini CLI + Cursor) and tired of losing context between sessions: deploy IM.codes, point every agent at the same shared memory endpoint, and use the audit log to see which model made which call.

Who should use it

developer teams running more than one coding agent (Claude Code + Codex, or Gemini CLI + Cursor)platform engineers building a multi-agent orchestrator who want one shared memory and audit layeragent teams that need cross-agent handover with full traceabilityanyone who has lost context between sessions and wants the next agent to start with the previous one's decisions

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

ships an auto-supervision loop that can continue work autonomously — start with the loop disabled and enable it per-agent after you trust the audit log; project README disclaims warranties and warns of breaking changes; pin versions in production.

Evidence links

Closest alternatives / related signals

multi-agentshared-memorymcpsupervisionauditclaude-codecodexgemini-cli