Home of CodeT5: Open Code LLMs for Code Understanding and Generation

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

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.

CodeTF: One-stop Transformer Library for State-of-the-art Code LLM

Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A with file paths and line numbers. Works in any AI IDE.

Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 commands, 224 MCP tools, change-safety gates, audit evidence, zero API keys.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · Hermes · VS Code · Windsurf.

Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].

Entity-level code review. Triages pull requests by structural risk using cross-file dependency graphs and LLMs that read for meaning.

Temporal Code Intelligence platform. Time-series complexity analysis across Python, JavaScript, Java, and Go. Linear regression trend detection, cyclomatic complexity tracking, confidence scoring, and predictive decay forecasting.

Enterprise-grade graph-powered code intelligence engine. Deep structural awareness for Laravel, PHP, Python, and JS. Powers AI agents with high-fidelity architectural context via MCP & Neo4j.

This repository provide the studies on the security of language models for code (CodeLMs).

Verified code context for agents

Deep code indexing MCP server for AI agents. 25 tools: hybrid FTS5 + embedding search, call graphs, git blame/hotspots, build system analysis. Multi-repo workspaces, GPU-accelerated semantic search, 10 languages via tree-sitter. Fully local, zero cloud dependencies.

Cross-language-safe code-intelligence MCP for AI agents — 13 languages, family-gated call graph (CodeGraph wires 745 cross-language mis-wires on this repo, TSA 6 — ~390x cleaner). Run miswire-audit on your repo. 8 facade tools, TOON output, 100% local. Python.

AI Coders search blindly. Be their guide.

Give your AI agent instant API lookups instead of expensive source file reads. MCP server for C#, Go, Java, Python, and TypeScript.

[ARCHIVED] aurora is archived. Memory → "litectx," orchestration → "bareagent"

Architecture rules your AI coding agent can't break — generates AGENTS.md, per-folder CLAUDE.md, and Claude Code hooks from your codebase.