Havuz

Your AI forgets. A wiki doesn't. Turn chat-pasted text/links into a verified, translated, searchable wiki knowledge base — verify links, fil

OpenAI-compatible proxy that keeps LLM agent context small: it injects relevant memories instead of the full chat history (−51% tokens on re

Wenshu（文枢）— 面向人文社科研究的 AI 知识处理工作流：本地知识库 / RAG / 中文引文 / 理论谱系。AI knowledge workflow for humanities & social sciences: local knowledge base, RAG

FastMemory is a topological representation of text data using concepts as the primary input. It helps in improving the RAG(by replacing embe

AI Business OS: multi-agent platform with RAG, OCR, speech & workflow automation. FastAPI + LangGraph + Celery + Flutter. Production-grade,

Claude Code, natively inside Unity Editor. A dockable chat window with full project awareness, 60+ MCP tools, and zero alt-tabbing.

A local-first studio for roleplay and long-form writing: a roleplay chat with a living Narrative State, a Worldbuild that keeps your canon,

Personal AI agent on Cloudflare Workers: Durable Object per conversation, markdown memory in R2, vector recall in SQLite, fan-out deep resea

Search knowledge by what documents mean and how they look — not one or the other.

根据 Crash/ANR/OOM 等日志构建证据链，实现自动修复代码的Agent框架，并支持衔接自动测试验证、Bug管理平台 Agent framework that builds evidence chains from Crash/ANR/OOM logs, auto-fix

Free and open-source production-grade RAG platform that converts documents into conversational AI assistants. Enable private deployment for

Deterministic agentic-style multi-hop RAG at research-SOTA parity on commodity LLM APIs — no GPU, proof tree per answer.

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Self-hosted long-term memory for AI coding agents: Postgres+pgvector doc-RAG (component/constraint map + hybrid RRF + cross-encoder rerank)

Open-source AI agent platform for building, deploying, and managing AI teammates. Role-based agents (PM, Engineer, Support, Marketing) with

memweave is a zero-infrastructure, async-first Python library that gives AI agents persistent, searchable memory — stored as plain Markdown

Give your AI your whole life. Keep your private things private. Olympus runs on your Mac or Omarchy computer and works with ChatGPT, Claude,

Extracts claims from SOPs, policies and regulations, has a person approve or reject each one, then serves the approved set to agents over MC

Self-hosted AI workspace for job applications, resumes, cover letters, company research, and interview preparation.

NAS OS

Source-grounded, bilingual, local-first AI note taker: turn documents, audio, video and links into notes you can trace, edit and reuse. Ever

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST

First open-source AI knowledge layer for Togo - 62K+ documents, RAG API, fine-tuned LLM. Built for developers, startups and institutions i

Athena RAG Intelligence – AI-powered document intelligence platform with RAG, semantic search, source citations, voice assistant, analytics,

面向中文食谱问答的端到端 RAG 工程实践，覆盖数据清洗与索引构建、混合检索、多轮状态管理、结构化生成，以及基于真实大模型服务的 Live E2E 测评闭环。

End-to-end educational RAG system: dual-engine retrieval (BM25 + BGE-M3 hybrid vector search), adaptive query strategies (HyDE/sub-query/bac

Long-term memory for LLM apps that shows its work: dated facts, as-of answers, supersession, and receipts on every answer. Library, CLI, loc

Local-first RAG knowledge base for Pi agents with hybrid code/doc search, reranking, diagnostics, and large-project indexing.

Memory database for AI agents — stores typed memories (facts, preferences, events, entities, relations) with provenance, confidence, and bi-

An AI native macOS reader. Built for professional reader.

Open-source bitemporal knowledge graph — long-term memory for AI agents. Hybrid retrieval, conflict-aware ingest, GDPR forget. REST + native

迹录 Tracord —— 基于本地小模型多智能体的智能旅行规划助手 / AI travel planner with local SLM multi-agents — light up visited cities on a map, log expenses with one

Permission-aware Agentic RAG for enterprise knowledge bases — folder ACLs, hybrid retrieval, OCR, grounded citations, and secure LLM evidenc

Eight-platform full-stack AI operating system - unifies 176 LLMs via LangGraph + MCP + A2A. Multi-tenant RLS over 340 tables, RAG knowledge

Teach Data Engineers How to Think AI.

Jutian Agent 巨天agent — local-first desktop AI workbench: chat, code, swarm agents, 51 tools, free models, AI-built UI extensions. 本地优先的桌面 AI

Consensus REST API. Semantic search over 400M+ peer-reviewed research papers, including all of PubMed, for RAG, AI agents and research tools

RAG-powered document intelligence assistant built for the Midnight Hackathon AI Track. Users upload confidential documents (medical records,

Declarative Document Indexing (DDI) framework for Python. Define schemas, extract structured indices, search smarter.

🏛️ Memory OS for AI agents — every conversation becomes a catalog card (archive no · entities · evidence · trace back to the transcript). Fo

本地优先的文献知识库 RAG(DeepSeek Harness 插件):混合检索正文与图注,把模糊记忆定位到具体段落与图表,DOI 一键直达原文。Local-first literature RAG for DSH — turn a fuzzy memory into an ex

书内 BOOKNOTE · 多账户教材 RAG 学习助手 —— 回答必引原文:C/W 双引用校验、批注阅读器、长对话自动压缩、可选联网补充(MCP)

Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Curso

Excellent hybrid search in the Postgres you own.

基于本地 RAG 与大模型人格蒸馏的多平台聊天记忆系统。通过 FTS5 检索、语料清洗与长期报告生成，将聊天记录转化为高拟真的数字分身。

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

Give any MCP-capable agent persistent memory: remember/recall over a tiered store with hybrid vector + keyword retrieval. Single Go binary,

SQL-like query language and CLI for Qdrant vector search engine

Red-team your RAG pipeline for prompt injection, source-document leakage, and cross-document smuggling, in CI. The gap between RAG eval (RAG

Measure whether an embedding upgrade is worth it, bridge it without reindexing when it is, and migrate safely when you are ready.