Havuz

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

Review code changes by what they do, and learn the concepts behind them.

Whole-codebase knowledge for AI coding agents. A field-aware code graph (functions, classes, methods, fields, references) plus persistent me

Local-first RAG knowledge base for Pi agents with hybrid code/doc search, reranking, diagnostics, and large-project indexing.

Retrieval + inference offload for AI coding agents.

ContextAtlas — context infrastructure for AI coding agents: hybrid retrieval, project memory and retrieval observability via CLI, MCP server

Semantic shell command safety classifier — AST-based risk scoring for AI coding agents

Diff filter that expands every hunk to include the enclosing function or block via tree-sitter. Pager for git, gh, or lazygit; viewer for co

A tool that replaces everything that can be deterministic in repository work: search, symbols, callers, task scope, history, review and Git

A code knowledge graph built for LLM agents — accurate answers, minimal tokens, maximum speed

Portable, always-fresh docs for agents and humans. A Surface hub is a conformant OKF concept; Surface adds the freshness OKF leaves out - it

Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed m

Evidence-backed TS/JS repo structure lens for Claude Code

The first vim IDE. A vim-native IDE in a single binary: multi-server LSP, tree-sitter, four DAP debuggers, opt-in Copilot, an AI pane, and t

🥷 Give your codebase a black belt. Local code intelligence, security analysis, and compiler-backed facts for humans and AI.

The Private Context Layer & Super Brain for Your Codebase. Give AI agents persistent memory, deep dependency graphs, and instant code contex

Prevent cross-repo architectural breakage before merge. Architecture knowledge graph from static analysis, blast radius in CI, MCP server fo

Turn your codebase into a living knowledge graph. An MCP server using tree-sitter to stream high-fidelity context to Cursor & Claude. Watch

Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and l

Code intelligence engine for AI coding agents. Structural graph queries plus semantic search, exposed via CLI and MCP.

Live code graph that fuses static analysis (tree-sitter) with OpenTelemetry runtime traces, queried over MCP so AI coding agents get real fu

An eraser against LLM-induced code & document entropy. Support if you like it!

Deterministic tree-sitter + SQLite/FTS5 code knowledge graph for coding agents and developers: symbols, calls and dependencies over a CLI, a

Multi-language static analysis for agents, editors, and large repositories.

Local-first MCP server giving AI coding agents fast, structured, and semantic context over any codebase. Zero config, zero cloud, full conte

Universal zero-dependency linter and formatter. One pure-Rust binary (poly) that lints and formats ~30 languages in-process — ruff, oxc, bio

Structured file edits for AI agents (JSON/YAML/TOML, markdown, AST, dry-run, MCP). Not a generic filesystem MCP.

"Review Ducktective" is an automated code review platform based on an LLM: it takes a diff as input and outputs structured findings with sev

Delphi-native, MIT-licensed RAG + linter for Delphi/Pascal source code. Symbol-exact + fuzzy + tree-sitter lint. Pure Delphi at runtime.

Deterministic semantic linter and PR reviewer for IEC 61131-3 Structured Text. 80 checks across diff-based, static integrity, FB-instance, P

A live, graph-verified map of your codebase for AI coding agents — real call graphs, compiler-verified edges, and hard safety gates on the w

Autonomous AI agent that detects breaking dependency changes via Tree-Sitter AST analysis, synthesizes verified patches, and opens human-rev

The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing tha

A CLI tool that uses Tree-sitter to index codebases and generate structured snapshots.

MIT-licensed code knowledge graph: index any source repo into a queryable graph of symbols, call chains and blast radius — with wiki generat

Multi-language cognitive complexity linter, as a single static binary

Girder saves AI coding-agent context by giving agents exactly the code they need instead of whole files.

Turn code in 10 languages into a DSTU 19.701-90 / ISO 5807 flowchart or Nassi-Shneiderman structogram. Go engine, Web editor, 8 export forma

Structural code intelligence for DeepSeek Harness (dsh) — gives the agent codegraph and codegraph_index tools to find where a symbol is decl

A token-saving CLI for AI coding agents: query symbols and call graphs instead of grepping and reading files

Deterministic code-graph (GraphRAG) over your repo for LLM agents — local-first, git-native, zero-infra, served via MCP. Python, TS/JS, Rust

Succinct Compositional Program Graph (SCPG) static analysis engine & 14-diagram UML generator in Rust.

🗄️ Every Unity asset reference in one queryable database. Rust + SQLite + tree-sitter. CLI + Web UI + MCP server.