AI Agent Coordination

Your projects,
one conductor

Maestro orchestrates AI agents across all your projects. Shared knowledge, codebase scanning, dependency graphs, and autonomous builds — all from inside Claude Code.

27
MCP Tools
18
Languages
8
Agent Types
0
Apps to Install
01

How Maestro works

You talk to Claude Code. Claude Code talks to Maestro. Maestro coordinates everything else — agents, knowledge, code graphs, builds.

You Claude Code MCP Maestro orchestrate coordinate dispatch learn Knowledge Base semantic search Code Graph symbols & impact Agent Pipeline plan → build → test Your Projects api-service web-frontend auth-library mobile-app
02

What Maestro does

Six capabilities, one MCP connection. No dashboards, no context switching.

Codebase Scanning

Index any repo with tree-sitter. Search symbols, trace callers and callees, and run transitive impact analysis before you change a line.

Knowledge Base

Semantic search across every project's code, docs, patterns, and decisions. pgvector embeddings so you find answers, not just keywords.

Cross-Project Intelligence

Dependency graphs with circular detection. Ask "does any project already handle SAML?" and get an answer across your entire stack.

Agent Pipeline

Planner, builder, tester, reviewer, docs, bug hunter, frontend, and discovery. Specialized agents collaborate on threads with evolving skills.

Autonomous Builds

File a request, approve a plan, and agents create branches, write code, run tests, and open pull requests. You review, they execute.

Capability Registry

Projects declare what they can do — auth, APIs, data, UI, infra. Before building something new, Maestro checks if it already exists.

03

Code graph

Index your repos. Search every symbol. Trace the blast radius of any change before you make it.

Symbol search

Functions, classes, methods, interfaces, enums — all indexed and searchable. Find what you need across every project, instantly.

codegraph_search codegraph_file
UserService authenticate() get_profile() validate_token() update_role()
change here blast radius

Impact analysis

Trace callers, callees, and transitive dependencies. See exactly what breaks if you refactor a function — across projects.

codegraph_callers codegraph_callees codegraph_impact
Tree-sitter powered — 18 languages indexed
Python TypeScript JavaScript Go Rust Java C# Swift Kotlin Ruby PHP C++ C Dart Scala Elixir Lua R
04

The agent pipeline

File a request. Agents triage, plan, build, test, and review — each with specialized skills that improve over time.

01
Plan
Decompose, search KB, check dependencies
02
Build
Branch, implement, commit
03
Test
Run suites, fix trivial failures
04
Review
Security, bugs, conventions
05
Ship
Open PR, update docs
Claude Code Session
you > File a feature request for maestro: add rate limiting to the /api/search endpoint claude> maestro.file_request( kind="feature", title="Rate limit /api/search", project="api-service" ) Thread #247 filed. Planner agent assigned. Suggested approach uses existing rate-limit middleware from auth-library (found via KB).
05

27 tools, one connection

Every feature is an MCP tool. No web dashboard, no context switching. Just talk to Claude.

6
Code Graph
search, index, callers, callees, impact, file symbols
5
Knowledge
search, add, find capability, suggest approach, agent types
6
Requests
file, check status, thread detail, list projects, notifications
3
Builds
approve plan, start build, check progress
4
Projects
register, create agents, setup agents, add dependencies
3
Identity
register, verify, whoami
06

Connect in seconds

01 Add the MCP server

Paste this into your Claude Code chat:

Add an MCP server called "maestro" with URL https://maestromojo.com/mcp
02 Register

Tell Claude to register you:

Register me with Maestro using your@email.com
03 Verify & go

Check your email for the code, then:

Verify my Maestro code: XXXXXX
07

Why Maestro

Native

MCP-First

Not a separate app. Maestro lives inside your Claude Code session as a tool, right where you already work.

Connected

Cross-Project

Dependency graphs and shared knowledge mean Maestro knows your Library B already has SAML before you build it again.

Adaptive

Evolving Skills

Agent skills track success rates and refine over time. The more your team uses Maestro, the better it gets.

Deep

Code-Aware

Not just docs — Maestro indexes your actual code. Symbols, relationships, and impact analysis across your entire stack.