Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.

(ACL 2025 Main) A Comprehensive Benchmark for Code Information Retrieval.

Verified code context for agents

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

ContextAtlas — context infrastructure for AI coding agents: hybrid retrieval, project memory and retrieval observability via CLI, MCP server or embeddable library. Tree-sitter indexing, LanceDB vector search, FTS5 and token-aware context packing.

Local code search for AI agents: six fast, purpose-built tools that return ranked answers, not raw grep. Because maybe grep isn't all you need... 🍬

Make every AI token leaner with one CLI, MCP. Search code, inspect structure, read ranges, and explore Git history.

This repository contains the implementations of our experiments and our approach presented in the paper: CoNCRA: A Convolutional Neural Network Code Retrieval Approach

CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval

🌈 Paper-implementations in Code Search (Baseline).

Agentic code retrieval benchmark for coding agents

Deterministic method-first retrieval for AI coding agents.

Zero-LLM structural code retrieval for AI coding agents — tree-sitter index, BM25+dense+structural fusion, served over MCP.

Agent-safe code retrieval for MCP coding agents: runtime-first search, exact reads, call graph context, and fresh repo evidence before edits.

A local-first code retrieval MCP server for AI coding agents. Hybrid keyword + vector search over Graphify-indexed codebases, with domain-aware ranking profiles.

Adaptive q-log BM25 for code retrieval under fixed generic tokenization

Semantic Language-Indexed Code Extraction with Backward Slicing for Repository-Scale Code Generation

Semantic code retrieval engine for AI coding agents, with hybrid search, AST-aware chunking, graph expansion, and token-aware context packing.

Interactive HTML literature explorers for AI-agent research topics: agentic memory design, multi-agent orchestration reliability, and enterprise code retrieval, generated by a Python pipeline and published via GitHub Pages.

Structured code retrieval for AI agents — index once with tree-sitter, query symbols precisely via MCP. Cut code-reading token costs by up to 99%.