Havuz

Memory OS, Hermes Agent için konuşmalar arasında kalıcı hafıza sağlayan ve ilgili bağlamı gerektiğinde prompt’a ekleyen yerel bir yazılım altyapısıdır.

Neden yükseliyor · 119 günde 1372 yıldız, projeye belirgin bir ilgi olduğunu gösteriyor. Ancak bunun nedenini veya yıldızların ne kadar yakın zamanda geldiğini verilen verilerle belirlemek mümkün değil; son 28 günde commit ve farklı yazar sayısı sıfır. README’deki kurulum kolaylığı ve çok katmanlı yaklaşım ilgi çekici olsa da benimsenme ve güncel bakım kanıtı olarak tek başına yeterli değil.

📊 电商数仓智能问数 AI Agent，最适合用于系统学习 LangGraph 的实战项目：基于 LangGraph、FastAPI、Qdrant、Elasticsearch、MySQL 与 React，完整实现元数据知识库、混合检索、自然语言生成 NL2SQL 生成校验、SQL

一个本地优先的AI知识库系统（RAG），用于把本地文档接入辅导搜索与大模型对话流程。目前支持md、txt、pdf（文本）、xlsx、cvs类型。支持mcp服务

Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP ex

开源、本地优先的 AI 长篇小说创作引擎：多智能体世界推演、按弧规划、RAG 长程记忆、逐章审核与断点恢复 | Open-source AI novel generator for long-form fiction.

Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code c

デジタル庁のガバメントAI「源内(GENAI)」を完全ローカル(ローカルLLM/OpenAI互換)で動かす非公式プロジェクト。SAML認証(Keycloak)・RAG(Qdrant)・文字起こし(Whisper)・画像生成(SD)・チーム単位ナレッジをローカル完結。

Local-first cinematic still archive for filmmakers. Search your frames by look, mood, technique or director with SigLIP semantic search; ing

AlumNet - AI-powered intelligent school history exhibition & alumni management system | AI 智能校史展示系统 — 校友星图

Open-source, real-time collaborative AI canvas - notes, mini-apps, and agents on one infinite board.

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Self-hosted AI customer-support platform — per-KB RAG on Qdrant, 13 LLM providers, SSE streaming, embeddable chat widget. FastAPI + Vite + S

面向 PRD、业务规则、SOP、流程文档和产品截图的证据型 RAG 知识库。

A Multi Agent Memory MCP That Connect Agents Across Systems and Machines

Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories retroactively when outcomes land

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

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

Self-hosted intent radar — Reverse RAG for any input stream.

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model rerankin

Knowledge graph + MCP tool server for LLM agents with hybrid retrieval, live DB sync, Korean FTS, and memory feedback.