Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Repository Index
47,133 repositories indexed
1–8 of 8 · Most stars
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
- ai
- code-intelligence
- dead-code
- developer-tools
Open source AI code review for coding agents. A separate reviewer checks every change your agent writes before you push, in Claude Code, Codex, Cursor and Cline. No account or key of its own.
- agent-skills
- ai-agents
- ai-code-review
- claude-code
Auditable code review skill for Claude Code and Codex: four independent probes, evidence-backed findings, and a JSON-derived merge gate.
- agent-skills
- ai-code-review
- claude-code
- code-review
The standards-based Web Components multitool. Generate Custom Elements Manifests, Dev Server, LSP, and MCP for your app or design system
- custom-elements
- custom-elements-manifest
- go
- golang
PostgreSQL migration linter. Blocks unsafe migrations before merge: 112 rules, the real Postgres parser, lock analysis, auto-fix. CLI, GitHub Action, MCP.
AI writes. SPARDA proves. A deterministic, offline gate that catches when an AI edit removes a guard, exposes a route, or breaks an invariant — no API key, right in the agent edit loop.
- ai-agents
- ai-code-review
- authorization
- bola
Turn any Java, Kotlin or Python project into an AI-ready context file in one command.