agentmako

agentmako is a local-first codebase intelligence engine for AI coding tools.

It gives agents like Codex, Claude Code, Cursor, and local harnesses a typed MCP toolset for understanding a project before they edit it. Mako indexes your repo, builds local SQLite-backed facts, tracks diagnostics and review notes, and returns structured context packets instead of making the agent rediscover everything with raw grep.

Mako is built for the first mile of coding-agent work:

What files matter? What routes, symbols, tables, diagnostics, and prior findings are relevant? What should the agent read next?

What You Get

• MCP server for coding agents: agentmako mcp
• Local dashboard: agentmako dashboard
• Queryable workflow orientation: mako_help
• Deterministic context packets: context_packet, reef_scout
• _hints on tool results so agents get result-specific next steps
• Central MCP annotations so clients can distinguish safe reads, live reads, and local-state mutations
• Code search and structure tools: cross_search, live_text_search, ast_find_pattern, repo_map
• Reef Engine facts and findings across indexed, working-tree, and staged state
• Reef convention extraction for auth guards, runtime boundaries, generated paths, route patterns, and schema usage
• TypeScript, ESLint, Oxlint, Biome, and staged git diagnostic ingestion
• Hot-reloaded .mako/rules YAML rule packs, including primitive cross-file helper-bypass rules via canonicalHelper
• Optional Postgres/Supabase schema snapshots and read-only DB inspection
• Local DB review comments for notes on tables, RLS, triggers, publications, subscriptions, and replication
• Recall, acknowledgements, and agent feedback for repeated review work

Everything important runs locally. No hosted service is required.

Install

Requires Node.js 20 or newer.

npm install -g agentmako

Confirm the CLI is available:

agentmako --version
agentmako doctor

You should see green checks for configuration and the local API service.

Prefer to build from source (e.g. to contribute)? See Develop From Source at the bottom of this file.

Happy Path Setup

1. Attach your real project

Go to the project you want Mako to understand:

cd C:/path/to/your/project

Attach and index it:

agentmako connect . --no-db

Use --no-db for the first run. It gets the code intelligence path working before adding database scope.

2. Confirm Mako sees the project

agentmako status .
agentmako tool list

Run a real scout query:

agentmako --json tool call . reef_scout "{\"query\":\"where should I inspect auth route state?\"}"

If that returns ranked candidates, facts, or findings, the core setup is working.

reef_scout classifies broad requests before ranking. App-flow questions favor file, route, and finding evidence; RLS/schema questions favor database facts and review comments. To inspect project rules of thumb directly:

agentmako --json tool call . project_conventions "{}"

3. Configure your MCP client

Add this to your MCP client config:

{
  "mcpServers": {
    "mako-ai": {
      "command": "agentmako",
     

... [View full README on GitHub](https://github.com/drhalto/agentmako#readme)