Recall-rag is a Python package that implements trustworthy retrieval-augmented generation specifically for an AI agent's long-term memory. It returns a verdict, confidence score, and provenance for every retrieval hit, or issues an explicit abstention when confidence is insufficient. Built on PostgreSQL/pgvector with support for hybrid search, reranking, and calibration, it is designed for LLM agent developers who need reliable memory systems.
recall-rag is a RAG, search & retrieval product. It focuses on retrieving information from an AI agent's memory without hallucinations or untrustworthy results. It is built as an open-source project for developers. recall-rag is open source under the MIT license. It runs on the command line and API, and it can be self-hosted.
Behind recall-rag is GiulioDER, and the product first shipped in 2026. Development happens publicly on GitHub with 127 commits in the last 90 days. Key capabilities include Trustworthy Retrieval, Confidence Scoring, and Provenance Tracking. It exposes integrations via an MCP server and a public API.
Latest indexed changes and source events
Other apps tracked under the same category.