RAG & Knowledge Bases

Graph-Native Infrastructure for Context and Accountable AI Systems

A Codex relationship-advice strategist that first acknowledges emotions, then analyzes relationships and provides actionable strategies. Includes knowledge bases covering psychology, law, society, humanities, philosophy, marriage and family, and sexology; supports diverse relationships.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

Open-source always-on Memory Agent for wearables. Turns your days into short- and long-term memory you can revisit and question, with an Agent that acts on it and builds new Skills from one sentence. The longer you wear it, the better it knows you.

Curated list of the best truly open-source AI projects, models, tools, and infrastructure. Daily updated.

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

An experimental LLM platform for local and cloud inference, chat, RAG, agents and tools, guardrails, security, monitoring, evaluation, LLM-as-a-Judge, and research into original features.

3,516 curated Figure 1 / teasers from ICLR, ICML, NeurIPS, CVPR, ACL, AAAI (2023-2026), with tier badges and FigureForge retrieval-augmented figure drafting

AI-powered GitHub stars manager with semantic search, auto-categorization, and release tracking

A linked-list discipline for knowledge, memory and pointer hygiene in large projects: five laws plus portable Python engines (declarative rule table, dry-run health check, link-integrity scan).

Durable, searchable memory of your past agent sessions.

EduBot is a powerful RAG (Retrieval-Augmented Generation) chatbot that utilizes the latest SOTA models to provide a seamless and interactive learning experience.

An experimental AI chat tool with a knowledge base, for personal use

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed clo

Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.

Local, offline RAG chatbot for company documents — multi-format ingestion, citation tracking, and evaluation testing. No data leaves the machine.

A complete, structured hub for learning Artificial Intelligence — covering AI, Machine Learning, Deep Learning, and Data Science with books, roadmaps, and curated resources from beginner to advanced.

A complete serverless research paper ingestion and search system built on AWS. The system fetches papers from arXiv, generates embeddings using Amazon Titan, stores them in PostgreSQL with pgvector, and provides semantic search with AI-powered chat responses using OpenAI models via AWS Bedrock.

Postgres with GPUs for ML/AI apps.

A bounded, self-correcting long-term memory layer for LLM agents: distills continuous, contradictory project interaction logs into a bounded, self-updating memory store. Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamics + tension adjudication + causal-replay evals.

🎙️ Voice-driven AI portfolio — talk to my site. Next.js 15 + FastAPI + OpenAI Agents + Retell + Pinecone. → art3m1s.me

Local-first AI job intelligence workbench for scraping roles, ranking fit, and generating tailored application materials.

Where rain falls, memories bloom again. A self-hostable AI long-term memory and chat gateway. Self-hosted AI memory & chat gateway for long-term conversations.

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive s

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

An AI-based WeChat group chat bot 🤖 supporting message summaries, @-mention questions and conversations, Map‑Reduce long-text chunking, proactive messaging, and long-term memory. Compatible with multiple AI backends including DeepSeek/Claude, with a built-in React web dashboard, prompt sandbox, and configuration management. Simulates keyboard input; no protocol reverse engineering required…

BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications.

Learn Ollama by doing; run large-model deployments on the CPU. Read online at: https://datawhalechina.github.io/handy-ollama/

Doghead Strategist: an Android relationship decision-support app powered by the goutoujunshi knowledge base (BYOK / fully local / dual-channel screenshot analysis)

Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.

MeNote, a lightweight personal notes and knowledge-base system supporting Markdown notes, category management, bidirectional links, and a knowledge graph. Includes a P2P tunnel so the mobile app can connect directly to the notes service on a NAS without a public IP. Data is stored locally, keeping privacy under your control.

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. A simple, general-purpose swarm intelligence engine that predicts everything

Mobile first Note Taking integrated with Git

Run all of Wikipedia offline next to a local LLM — sovereign, private, low-carbon, verifiable. Kiwix + Ollama + RAG.

CrewMeld — Enterprise AI Digital Workforce Platform. Manage AI employees like real team members. Visual SOP orchestration, 13 LLM providers (including China-native models), 8+ messaging channels(WeCom/DingTalk/Feishu/Telegram), knowledge base with RAG, and full private deployment support. Built with

There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.

Hierarchical Agent Memory with Git-Like Version Control

LLM Zoomcamp - a free online course about real-life applications of LLMs. In 10 weeks you will learn how to build an AI system that answers questions about your knowledge base. Register here 👇🏼

Official code for "Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection" (NeurIPS 2026). RAMSAD selects the best anomaly detector for a new series by retrieving similar series from a knowledge base, with no selector training.

AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).

Profile of blacknyaa. A freelance AI engineer in Osaka.

A terminal-first Linux AI operations workbench: SSH/SFTP, real command output, tiered approvals, and step-by-step, one-card-at-a-time tutorials. Windows desktop pre-stable version. A terminal-first AI workbench for Linux operations.

This project designs and implements a medical intelligent Q&A system based on a knowledge-graph RAG and a large language model. Using the DiseaseKG medical dataset, it builds a domain knowledge graph in Neo4j containing 44,000 entities and 310,000 relationships. It combines BERT named-entity recognition and intent recognition by a 32B model with precise graph retrieval and controlled answer…

Beautiful, AI-native markdown IDE and LLM wiki

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

Open-source Zi Wei Dou Shu charting engine — based on the system in Ni Haixia's The Book of Heaven, with complete charting algorithms, a Four Transformations system, a pattern knowledge base, and original classical-text data.

Obsidian knowledge graph for MIT-18.06 linear algebra

A local emulator for enterprise SaaS APIs — Slack, Gmail, Google Drive, GitHub, Jira, Notion, S3 and more — with the real response shapes, pagination, auth and per-document ACLs, over a corpus you supply.