Code intelligence for agents: find the code that matters and keep your context window and tokens lean.

rust code-navigation tree-sitter mcp code-search dsh cordis code-intelligence code-retrieval context-window coding-agents ai-coding model-context-protocol mcp-server codebase-indexing context-engineering token-counting token-budget token-efficient dsh-plugin

• Updated Nov 9, 2026
• Rust

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

nlp benchmark retrieval code pytorch dataset dpr passage-retrieval passage rag huggingface code-retrieval retrieval-augmented-generation code-retrieval-augmented-generation

• Updated Jun 30, 2025
• Python

OpenContextEngine is a self-hosted, ACE-compatible code retrieval service. It indexes source files with cAST-aware chunking, stores metadata in PostgreSQL or SQLite, performs dense vector retrieval in Milvus 3.0, and reranks results with an LLM before coverage-aware selection.

open-source ace oce code-retrieval context-engine context-engineering codebase-retrieval

• Updated Oct 20, 2026
• Python

Local code search for AI agents: cheaper, faster and sweeter. Because maybe grep isn't all you need... 🍬

rust tree-sitter retrieval mcp opencode code-search developer-tools grep semantic-search codex ai-agents rag code-intelligence local-first code-graph hybrid-search code-retrieval claude-code coding-agent context-engineering

• Updated Nov 11, 2026
• JavaScript

Verified code context for agents

python tree-sitter retrieval mcp ast pi code-search developer-tools agents semantic-search code-intelligence local-first code-retrieval coding-agents token-efficiency context-engineering context-window-optimization archex

• Updated Nov 8, 2026
• Python

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

python open-source developer-tools tfidf bm25 zero-dependencies code-retrieval llm context-compression token-optimization

• Updated May 30, 2026
• Python

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.

tree-sitter typescript oss mcp code-search developer-tools semantic-search rag vector-database hybrid-search code-retrieval ai-tools ai-agent lancedb context-management mcp-server claude-code codebase-indexing context-engineering project-memory

• Updated Jun 2, 2026
• TypeScript

Agentic code retrieval benchmark for coding agents

benchmark software-engineering code-retrieval coding-agents agentic-retrieval retrieval-benchmark

• Updated Oct 27, 2026
• Python

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

tree-sitter mcp code-retrieval model-context-protocol mcp-server swe-bench ai-coding-agents

• Updated Oct 11, 2026
• Python

PiJev: a terminal coding agent with Jev in the loop — Jev ranks the repository's files before the first call, picks skills and triages failures; your coding model writes the code. Built on Pi.

agent typescript terminal pi typesafe code-retrieval ai-agent coding-agent vercel-ai-gateway jev

• Updated Sep 23, 2026
• TypeScript

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

code-search neural-networks code-retrieval joint-embedding

• Updated Feb 12, 2021
• Jupyter Notebook

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

information-retrieval code-retrieval

• Updated Jun 3, 2025
• Jupyter Notebook

🌈 Paper-implementations in Code Search (Baseline).

deep-learning artificial-intelligence paper-implementations code-intelligence code-retrieval

• Updated Jun 15, 2022
• Python

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%.

tree-sitter csharp dotnet mcp ast polyglot developer-tools astral ai-agents claude code-retrieval llm mcp-server code-indexing

• Updated Nov 7, 2026
• C#

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

python mcp developer-tools cursor codex rag code-intelligence vector-search hybrid-search code-retrieval ai-tools graphify llm antigravity mcp-server claude-code ai-coding-assistant

• Updated Jul 21, 2026
• Python

Capture, verify and repair code evidence for coding agents / 编程智能体的代码证据采集、校验与修复

python information-retrieval reproducible-research mcp code-retrieval coding-agents context-engineering

• Updated Oct 15, 2026
• Python

Deterministic method-first retrieval for AI coding agents.

static-analysis developer-tools semantic-search fastapi code-retrieval llm-tools ai-coding code-agents

• Updated Mar 19, 2026
• Python

Free, open-source semantic code search for coding agents. Ask where behavior lives in plain English; Satori returns the owning code and exact source, locally through MCP.

tree-sitter typescript mcp code-search developer-tools semantic-search ai-agents rag vector-search milvus local-first code-retrieval

• Updated Nov 10, 2026
• TypeScript

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

knowledge-graph code-retrieval

• Updated Mar 3, 2026
• Python

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

nodejs tree-sitter typescript sqlite mcp ast code-search developer-tools full-text-search semantic-search rag vector-search hybrid-search code-retrieval context-engine lancedb model-context-protocol ai-coding-assistant code-indexing

• Updated Jun 13, 2026
• TypeScript