RAG & Knowledge Bases

Hindsight: Agent Memory That Learns

Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

Not another ChatGPT wrapper. This is a local-first tool that turns your notes, web pages, PDFs and audio/video into a personal knowledge graph — running entirely on your own machine.

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

A smarter, self-hosted AI assistant — multi-user, multi-agent.

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Evidence validation and policy engine for AI-assisted biological curation

Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Cla

A minimal, extensible, agent-native knowledge base that keeps shared context current and inspectable

Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.

OpenKB: Open LLM Knowledge Base

A platform for building and running digital employees for enterprises: codify professional employees' experience, workflows, and decision criteria as configurable, approvable, observable AI digital employees ready to work at any time.

📚 Building Agents from Scratch — a tutorial on agent principles and practice, starting from the basics.

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

Python scraper based on AI

Open-source AI sales OS — self-hosted CRM with native AI agents + WhatsApp (WAHA). Open alternative to Kommo, Octadesk & Intercom for any business that sells by chat. MCP-ready, multi-tenant, LGPD.

Open-source, AI-native knowledge base & Evernote alternative with native MCP. Zero-cost on Cloudflare or Docker.

Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key.

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Open-source main repository for Understanding AI Agents in Depth: Design Principles and Engineering Practice (by Li Bojie): the full book text, compiled PDF, and chapter-by-chapter code.

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Retrieval and Retrieval-augmented LLMs

Multi-tenant AI SaaS platform — autonomous agentic routing (RAG/CNN/chat), PyTorch vision, FAISS retrieval, Celery/Redis pipelines, Stripe billing, and full observability.

World's first open-source enterprise world model.

Bilingual Flipper Zero documentation, learning paths, and AI-ready reference packs

Memory library for building stateful agents

Build, run and scale AI agents like API and microservices

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in its sleep (autoDream), visualized in a memory panel.

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.

[EMNLP-2024] Build multimodal language agents for fast prototype and production

A fast, efficient universal vector embedding utility package.

Self-evolving local knowledge-base module: Markdown as the source of truth + RAG question answering + dual-track observability + gold-standard evaluation + self-evolving feedback loop; can connect to any Agent (OpenAI-compatible).

Evidence-grounded academic research agent with claim verification, prior-work analysis, and persistent research workspaces.

Fast BM25 search in Python, powered by Numpy and Numba

Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pat

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

Your own AI workspace on your own machines: chat, agents, coding, knowledge bases (RAG) and fine-tuning with local models. Open source (AGPL-3.0).

Open-source GEO content engineering and multi-site distribution platform with AI quality inspection, illustrated admin help, hosted sites, browser-assisted publishing, and signed updates.

Open-source, self-hostable alternative to ChatGPT and NotebookLM — agents, skills, MCP, and cited knowledge in one AI workstation. Your models, your infrastructure.

Hindsight: Agent Memory That Learns

AI-powered Singapore travel assistant using RAG, LangChain, FAISS, MCP weather and currency tools, FastAPI, and Streamlit.