Persistent, consensus-validated institutional memory for AI agents. Gives LLMs real memory that survives across sessions - validated through BFT consensus, not just dumped to a file.
A self-hosted MCP server that retrieves git-backed engineering experience records (issues, fixes) to inform LLM coding agents, preventing repeated mistakes with a relevance floor.
lunar-mcp is a Go-based MCP server that provides 28+ tools for Chinese traditional calendar, fortune telling, and divination. It enables AI agents to integrate Chinese cultural computations into their workflows.
AI modifies a function but misses 5 callers that also need updating. crag fixes this — it builds precise call graphs via static analysis, so AI knows exactly what's affected before making changes.