Havuz

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies

Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, deep research, content generation, vibe coding, browser a

Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual i

本地优先的全栈 AI 创作工作站：AI对话 · AI漫画 · 漫剧创作 · 写作台 · 知识学习五大模块；vLLM / llama.cpp / Transformers 多引擎本地推理，显存智能调度、舱壁隔离自愈、仅供学习使用，欢迎交流指正。（最新进度（除插件系统）受到协议限制，

Deuz SDK, TypeScript ile model entegrasyonları, agent ve swarm çalıştırma, memory ve retrieval gibi yetenekleri tek framework'te sunuyor.

Neden yükseliyor · 118 günlük yaşına rağmen 697 yıldız ve son 28 günde 126 commit dikkat çekiyor; ancak farklı yazar sayısının 1 olması, bu hareketliliğin tek geliştiriciden geldiğini gösteriyor. Yükselişin özel nedeni mevcut verilerden bilinmiyor.

Goink 桌面 AI 小说创作助手，对话式写作 + 自动状态追踪 + 本地语义搜索。跨平台开箱即用。AI Agent Novel Generator.

📊 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

A filesystem designed for agents, with SOTA retrieval, automatic memory profiles, sync engine. Drop any file type (pdf, images, videos), and

FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready.

基于LangChain、LangGraph、FastAPI和React的RAG项目，主分支为基于知识图谱的知识管理平台，base-rag分支为完整的向量RAG项目供学习使用

LightningRAG is a full-stack Vue + Gin starter with a decoupled frontend and backend, plus built-in, extensible RAG (retrieval-augmented gen

Your First LLM-Wiki Conversation Knowledge Base

全流程 智能招投标 Agent：标书生成 · 招投标解读 · 标书检查 · 标书文档ai排版 · 商机发现 一键完成。 21 项合规检查 · 多模型切换 · RAG 知识库 · OCR 抽取。 从招标公告到可交付 docx 文档，全流程 AI 自动化。

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a

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

基于 LangChain/LangGraph 的 ReAct Agent，结合 RAG 检索、工具调用与 Streamlit 界面，面向智能客服与报告生成场景。

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

和《偶像大师 闪耀色彩》偶像实时语音/文字对话的 AI 分身：日语原声 + 中文字幕、回忆原作剧情、跨角色共享记忆；支持 Google/GitHub 登录与自带密钥，Docker Compose 一键部署（参考 LAPLACE Eidolon）

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

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with

Dynamic-memory-first collaborative AI framework for long-form story generation, chapter planning, and coherent narrative writing

Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with d

Exam Cram Coach · 跨会话记忆与讲义溯源防幻觉的极速备考教练 | AI exam-prep tutor for Claude Code, Cursor, Codex, Antigravity: teaches from slides with page citat

Buddhist Digital Text Platform — 10,500+ texts, 613 sources, trilingual cross-canon, AI Q&A (RAG), knowledge graph, full-text search

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI pe

Extract Bilibili videos into learning-oriented Markdown notes with full subtitle and comment archives

台灣法律 MCP 伺服器 + CLI（免費、免金鑰，連接時登入法律偵探帳號）：2,277 萬筆裁判書、行政函釋、憲法法庭裁判，附引用查核。Free Taiwan legal MCP server for Claude/ChatGPT/Codex: sign in with a D

推量牛 BullFlow — 开源企业级 RAG 解决方案：从企业知识库、营销内容自动化生产到全域内容分发 | Open-source enterprise RAG solution: knowledge base → automated marketing content →

LLMInternSkill: LLM internship resume and job-search Codex Skill for resume polish, JD tailoring, evidence guard, interview grilling, and Pr

Open-source AI meeting notes for Mac. Records mic + system audio with no bot, transcribes on-device or via OpenAI / Deepgram / Groq, identif

Companion Space, kişisel materyallerle RAG tabanlı yazılı ve sesli çalışma oturumları sunan, self-hosted anime companion uygulamasıdır.

Neden yükseliyor · 40 günlük bir repoda 363 yıldız görünürlük ve erken ilgiye işaret ediyor; ancak bu ilginin nedenini veya gerçek kullanıcı benimsemesini mevcut verilerle doğrulamak mümkün değil. Son 28 günde 1 commit ve 1 farklı yazar olması, yıldızların sürdürülen geliştirme kanıtı olmadığını gösteriyor.

Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbol-aware edits, seman

基于 RAG（免微调）从聊天记录唤起语气与回忆：让曾经对话的温度，延续为往后的陪伴。 | Zero-finetuning RAG to revive tone and memories from chat logs: Let the warmth of past conversa

Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.

Local-first AI learning workspace — ask, note, review and create around your own materials. Wiki KB, Agents, Skills, creation tools.Priva

🔎 深度研搜对话式多智能体 AI Agents，最适合系统学习 DeepAgents 的实战项目｜AI Deep Research Agent 实战 · LangGraph + RAGFlow + Tavily + FastAPI + WebSocket 从0到工程化落地。前后端

The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, C

Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server fo

轻量级本地知识库 RAG 问答系统 · Streamlit + LangChain + Chroma，支持知识库上传与检索增强问答

AI-enabled Intelligent Document Processing for Python: 12+ LLM backends, Pydantic schemas, self-hosted OCR (Nanonets-OCR2-3B), auto-schema d

Open-source AI customer support system. AI-first support, human-ready operations.

Unified Agentic AI and Data Platform

🌱 Argus 是一个基于 RAG 架构的开源知识库平台，后端采用 Java 21 + Spring Boot + MyBatis-Plus + PostgreSQL/pgvector，前端采用 Vue 3 + TypeScript + Element Plus，AI 层基于 S

Long-term memory for any AI agent. One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Self-host free or use Uteke Cloud.

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite fi

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat p

Build your own LLM-native WIKI (knowledge library). Search, extract, summarize, Q&A with contextual RAG, layered knowledge graph, and reinfo

UmaDev: A coding agent that works like a real dev team, commanding the Claude Code / Codex / OpenCode you already use.

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self