Structured expertise files that accumulate over time, live in git, work with any agent, and run locally with zero dependencies.

Agents start every session from zero. The pattern your agent discovered yesterday is forgotten today. Mulch fixes this: agents call mulch record to write learnings, and mulch query to read them. Expertise compounds across sessions, domains, and teammates.

Mulch is a passive layer. It does not contain an LLM. Agents use Mulch — Mulch does not use agents.

npm install -g mulch-cli

Or use directly with npx — no install required:

npx mulch-cli <command>

mulch init                                            # Create .mulch/ in your project
mulch add database                                    # Add a domain
mulch record database --type convention "Use WAL mode for SQLite"
mulch record database --type failure \
  --description "VACUUM inside a transaction causes silent corruption" \
  --resolution "Always run VACUUM outside transaction boundaries"
mulch query database                                  # See accumulated expertise
mulch prime                                           # Get full context for agent injection
mulch prime database                                  # Get context for one domain only

1. mulch init               → Creates .mulch/ with domain JSONL files
2. Agent reads expertise     → Grounded in everything the project has learned
3. Agent does work           → Normal task execution
4. Agent records insights    → Before finishing, writes learnings back to .mulch/
5. git push                  → Teammates' agents get smarter too

The critical insight: step 4 is agent-driven. Before completing a task, the agent reviews its work for insights worth preserving and calls mulch record. Mulch provides the schema and file structure so those learnings land in a consistent, queryable format.

.mulch/
├── expertise/
│   ├── database.jsonl        # All database knowledge
│   ├── api.jsonl             # One JSONL file per domain
│   └── testing.jsonl         # Each line is a typed, structured record
└── mulch.config.yaml         # Config: domains, governance settings

Everything is git-tracked. Clone a repo and your agents immediately have the project's accumulated expertise.

All records support optional --classification (foundational / tactical / observational), evidence flags (--evidence-commit, --evidence-issue, --evidence-file), --tags, --relates-to, and --supersedes for linking.

$ mulch query database

## database (6 entries, updated 2h ago)

### Conventions
- Use WAL mode for all SQLite connections
- Migrations are sequential, never concurrent

### Known Failures
- VACUUM inside a transaction causes silent corruption
  → Always run VACUUM outside transaction boundaries

### Decisions
- **SQLite over PostgreSQL**: Local-only product, no network dependency acceptable

• Zero LLM dependency — Mulch makes no LLM calls. Quality equals agent quality.
• Provider-agnostic — Any agent with bash access can call the CLI.
• Git-native — Everything lives in .mulch/, tracked in version control.
• Append-only JSONL — Zero merge conflicts, trivial schema validation.
• Storage ≠ Delivery — JSONL on disk, optimized markdown/XML for agents.

Mulch is designed for multi-agent workflows where several agents record expertise concurrently against the same repository.

• Advisory file locking — Write commands acquire a .lock file (O_CREAT|O_EXCL) before modifying any JSONL file. Retries every 50ms for up to 5 seconds; stale locks (>30s) are auto-removed.
• Atomic writes — All JSONL mutations write to a temp file first, then atomically rename into place. A crash mid-write never corrupts the expertise file.
• Git merge strategy — mulch init sets merge=union in .gitattributes so parallel branches append-merge JSONL lines without conflicts.

Same-worktree agents (e.g., Claude Code team, parallel CI jobs):

# Every agent can safely do this in parallel:
mulch prime                                    # Read context
mulch record api --type pattern --name "..." --description "..."  # Locked write
mulch search "error handling"                  # Read-only

Locks ensure correctness automatically. If two agents record to the same domain at the same instant, one waits (up to 5s) for the other to finish.

Multi-worktree / branch-per-agent:

Each agent works in its own git worktree. On merge, merge=union combines all JSONL lines. Run mulch doctor --fix after merge to deduplicate if needed.

Maintenance during swarm work:

mulch compact --analyze          # Safe: read-only scan
mulch prune --dry-run            # Safe: read-only scan
mulch doctor                     # Safe: read-only health check

The --apply, default (non-dry-run), and --fix variants acquire locks and are also safe to run alongside recording agents.

• Lock timeout: If a lock cannot be acquired within 5 seconds, the command fails with an error. Retry or check for stuck processes.
• Stale locks: Locks older than 30 seconds are automatically cleaned up (e.g., after a crash).
• mulch sync: Uses git's own locking for commits. Multiple agents syncing on the same branch will contend on git's ref lock — coordinate sync timing or use per-agent branches.
• prime --export: Multiple agents exporting to the same file path will race. Use unique filenames per agent.

MIT