A self-correcting RAG backend that audits its own retrieval quality, rewrites and retries failed queries (bounded), and returns cited, self-verified answers, exposed through both a Fastify REST API and an MCP server, with a reproducible evaluation harness proving the adaptive loop outperforms a single-shot baseline.
Cross-referenced across 55 tracked directories
#2872
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
8/9/2026
Created
1
GitHub Stars
8/12/2026
Last Commit
Recently added to the ecosystem
bytedance
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Erick Friis <[email protected]>
Building applications with LLMs through composability
klim.paskov
One-time non-executable namespace claim for OIDC trusted-publisher setup.
letta-ai
Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.