AutoPatch is a self-healing debugging agent that runs a repo's tests, retrieves similar past fixes from its git history, proposes and applies function-level patches, and re-tests until the suite passes. It exposes this loop as MCP tools for clients like Claude Desktop and Cursor.
A methodology and MCP server for agent-driven software development where humans write specs and agents implement code, enforced by six mechanical gates to ensure spec validity, contracts, tests, and review.
An MCP server that extends AI coding assistants with deterministic, algorithmic capabilities such as code analysis, fault localization, and formal verification, enabling an autonomous engineering team within the IDE.
A shared, concurrency-safe ledger for LLM code audits. It enables multiple agents to collaboratively report, verify, and resolve bugs with deduplication and hallucination resistance.