mastermind
Active·★ 13·MIT·Updated 2026-10-21
Mastermind provides AI coding agents with a structural view of your code, showing components, dependencies, and potential change impact, while offering a verifiable workflow to validate agent plans against the real repository. It aids in understanding unfamiliar repositories, safely modifying code, selecting focused tests, and auditing agent work through its local codegraph and deterministic style miner.
#codegraph#AI agents#code analysis#workflow automation#developer tools#impact analysis#static analysis#code review
01
Features
01Local Codegraph & Style Miner
02Verifiable Workflow for AI Agents
03Code Change & Test Impact Analysis
04Architecture Invariant Review
05Agent Queryable Graph (MCP Server)
02
Compatibility
macOS
Platform
Verified via docs
Linux
Platform
Verified via docs
Windows
Platform
Verified via docs
Python
Language
Verified via docs
TypeScript/TSX
Language
Verified via docs
JavaScript/JSX
Language
Verified via docs
03
Quick start
1
$ npm install -g @xcraftmind/mastermind
04
Use cases
↳Understand unfamiliar repositories
↳Safely change code
↳Choose focused tests
↳Verify AI agent work
↳Review architecture-critical changes
05
Alternatives
arbor★ 160
Graph-native code intelligence that replaces embedding-based RAG with deterministic program understanding.
Synaptic★ 31
Auditable code intelligence for AI agents - map dependencies, predict change impact, select the right tests, and verify refactors before they ship.
loopover★ 21
The loop never sleeps — you finally can. Agents automate the entire development lifecycle (write, review, merge, learn) end to end, with a published safety record. Self-host today; rentable hosted loops in development. Any GitHub repo; Gittensor-native intelligence built in.
claude-code-plugins★ 26
Claude Code plugin marketplace: repo-agnostic skills, hooks, agents, and MCP servers.
gentle-ai★ 7.9k
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Spec-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.
infimium-agent★ 25
Infimium helps agents find the right code, docs, and dependencies — before they edit. Local-first, open-source, MCP-compatible.
Comments
Log in to leave a comment
No comments yet. Be the first!