Free & Open Source

Loom

Memory and coordination for AI agents

AI agents lose their context when a session ends. When you have multiple agents, they can't see what the others are doing. Loom gives them shared memory, smart task routing, and the ability to pick up where they left off.

Install in 2 minutes

One-click for your AI tool of choice

Claude Desktop

Add to claude_desktop_config.json

Windsurf

Settings → MCP → View raw config

VS Code
Open Extensions

MCP Server → search "loom"

Codex CLI

codex mcp add loom

npm

Works with any MCP client

How it works

1

Start a task

Tell Loom what you're working on. It tracks the context.

2

Pick the right agent

Loom suggests which agent fits best—by capability, cost, or speed

3

Save your progress

Checkpoint anytime. If something crashes, pick up where you left off.

# Start working (create + claim in one call)
loom work "Fix authentication bug" --agent claude-code

# Save progress (crash recovery point)
loom checkpoint "JWT validation implemented"

# Get routing recommendation
loom route lm-abc --strategy cheapest
→ Route to: gemini (score: 0.85, cost: $0.001/1k)

# Complete with evidence
loom complete lm-abc --evidence "commit abc123"

How Loom compares

Different tools solve different problems

FeatureBeadsGas TownLoom
Multi-agent coordinationNoNoYes
Smart routingNoBasicYes
Session memoryNoYesYes
Crash recoveryNoYesYes
Git syncYesNoYes
Ground integrationNoNoYes
Cost optimizationNoNoYes

What you can do

30+ tools for coordinating AI work

Manage tasks

  • loom_work — Start working on something right now
  • loom_create — Create a task for later
  • loom_spawn — Break a task into smaller pieces
  • loom_ready — See what's available to work on
  • loom_complete — Mark something done

Route work

  • loom_route — Get a suggestion for which agent to use
  • loom_agents — See all your configured agents
  • loom_analytics — See what's worked well in the past
  • loom_record_execution — Help Loom learn from results

Remember context

  • loom_checkpoint — Save your progress
  • loom_resume — Pick up where you left off
  • loom_get_resume_brief — Get a summary of what happened
  • loom_update_context — Note what files you changed, decisions you made

Plan ahead

  • loom_formulas — Use workflow templates
  • loom_discuss — Talk through preferences before starting
  • loom_verify_plan — Check if a plan makes sense
Key Feature

Use the right agent for the job

Not every task needs your most expensive model. Use Claude for architecture decisions, Gemini Flash for mechanical refactoring. Loom tracks what each agent is good at and helps you pick the right one.

5+ agent backends
3 routing strategies
30+ MCP tools
Read the documentation →