Historical proof

Loom coordination archive

The continuity problem that led to Linear-first coordination

Loom proved that agents need task ownership, checkpoints, routing, and recovery. Current CREATE SOMETHING repo work now uses Linear as the source of truth for tracked ownership, status, and evidence.

Legacy install references

Kept for historical MCP users. New CREATE SOMETHING coordination should start in Linear.

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

What Loom proved

1

Continuity matters

Agent work needs persistent context when sessions end or hands change.

2

Routing needs evidence

Agent choice only matters when the task, cost, and proof surface are visible.

3

Progress needs receipts

A task is not done until evidence survives outside the chat window.

# Legacy MCP reference. Current repo coordination uses Linear.
# 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

Legacy tool surface

These tools remain useful as design evidence. They are not the current repo task source of truth.

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 coordination surface for the job

Loom showed why agent work needs routing, recovery, and receipts. In this repository, Linear now owns tracked work while product pages keep Loom as historical proof of the coordination problem.

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