retrieval

Local-first desktop LLM wiki that hydrates notes, PDFs, emails, and docs into Markdown entries, then retrieves them with keyword search and link traversal instead of embeddings or a vector DB.

Long-term memory for LLM apps with dated facts, supersession, and receipts. It exposes Python, CLI, local GUI, HTTP, and MCP interfaces, and supports local or hosted models.

memU is an open-source shared memory system for AI agents, aimed at capturing useful session knowledge and reusing it across sessions, devices, and tools like Codex, Claude Code, Cursor, and Hermes.

An OTP-native Elixir library for building AI agents, durable LLM workflows, retrieval pipelines, and production LLM services.

An open-source memory governance layer for AI agents. It adds deduplication, conflict detection, decay, archival, and explainable retrieval so agent memory can be managed with more control than passive storage.

Deterministic retrieval-only Q&A system for documentation that avoids LLM calls at runtime. It uses Gemini embeddings, local Qdrant storage, and a CLI chatbot to answer questions with low latency and near-zero per-query cost.

An open-source MCP server that returns page-cited, verbatim evidence from embedded and firmware reference docs for coding agents.

An offline hybrid retrieval engine for RAG that runs on-device, including phones. The repo shows BM25 plus dense retrieval, cross-encoder reranking, sparse expansion support, and bindings for Rust, Python, Swift, and Kotlin.

A governed memory runtime for AI assistants with typed storage, policy checks, audit logging, tenant isolation, and hybrid retrieval. The repo includes a backend API, worker jobs, SDK examples, architecture docs, and eval harnesses.

Open-source local-first contract layer and runtime for canonical data, retrieval, durable execution, and agent-facing AI. The repo includes a quick start, capability boundaries, client/runtime notes, and examples for running locally and inspecting providers.

AletheionAGI is a grounding and memory layer for production AI. It adds persistent context, authorized evidence, and fail-closed delivery so AI systems can block unsupported claims before they reach users.

A zero-budget research search engine and RAG pipeline for 5,600 arXiv papers, built with free Colab processing, Qdrant free tier, and hybrid dense+sparse retrieval.

A GitHub example that audits LangChain’s RAG quickstart with retrieval-quality metrics, flags off-topic and out-of-distribution queries, and surfaces ranking and calibration issues with charts and results files.