576 个
🔐 Replayable RAG —— 本地优先、可审计的知识推理平台。Graph-RAG + 仅追加审计日志 + 确定性矛盾仲裁 + 人类把关的自演化。可逐字节回放任意历史知识状态。100% 本地（Ollama）。MIT 许可。🔐 Replayable RAG — a local-first, auditable knowledge-reasoning platform. Graph-RAG + append-only audit log + deterministic contradiction arbitration + human-gated self-evolution. Replay any past knowledge state byte-for-byte. 100% local (Ollama). MIT.
可复现研究仓库的 GitHub 模板 — 两层 Python 3.10+/uv monorepo，将通用基础设施与各项目代码分离，附带 pytest 覆盖率门槛（基础设施 60%、项目 90%）、17 阶段构建流水线、通过 pandoc/LaTeX 的 markdown-to-PDF 渲染，以及 24 个标准示例。GitHub template for reproducible research repos — two-layer Python 3.10+/uv monorepo splitting generic infrastructure from per-project code, with pytest coverage gates (60% infra, 90% projects), a 17-stage build pipeline, markdown-to-PDF rendering via pandoc/LaTeX, and 24 canonical exemplars.
EnterpriseRAG-AI：面向 AI Agent 工作负载的 Linux 原生、eBPF 驱动的安全与治理网格。EnterpriseRAG-AI: The Linux-Native, eBPF-Powered Security & Governance Mesh for AI Agent Workloads
面向 AI 编程 agent 的无向量代码检索——基于 Tree-sitter 图，按业务意图（@intent、@domainRule）搜索代码，通过 MCP 为 MSA 构建。Vectorless code retrieval for AI coding agents — search code by business intent (@intent, @domainRule) over a Tree-sitter graph. Built for MSA via MCP.
隐私优先、AI 原生的 Agent，面向电商及其他场景，基于 LangGraph workflow 以低代码/无代码方式图形化创建 skill、任务和 agent。支持跨网络部署 agent。Privacy-first, AI native agents For E-Commerce (and beyond), create skill (langgraph based workflow), tasks, agents, graphically with low code or no code. Deploy agents across network.
🎵 专属你的私人数字调音师|AI 音乐搜索推荐 Agent | 基于大模型 + 知识图谱 + 双模型声学向量的本地智能音乐推荐系统 | LLM-powered Music Recommendation Agent with Hybrid RAG, Neo4j, and Long-term Memory
面向 AI agent 的基于证据的评估——将每条断言与 agent 真实工具输出进行核对（受约束、基于证据的模型判断，而非整体式 LLM 评判的猜测），并附带置信区间。Evidence-grounded evaluation for AI agents — verifies each claim against the agent's real tool outputs (constrained, evidence-grounded model judgment, not holistic LLM-judge guesswork), with confidence intervals.
面向 AI Agent 的 Markdown 优先的长期记忆基础设施。通过 MCP 在 markdown/代码文件上实现 BM25 + 语义混合检索。Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.
邮件的大脑：MailFathom 将 IMAP 邮箱转变为自托管、AI-native 的服务。邮件同步至你自己的 PostgreSQL，建立索引以支持搜索与检索，并通过 Model Context Protocol 提供给 AI agent。具备语义检索、问答与受控的写入工具。基于 .NET 10，AGPL-3.0-only 许可。A brain for your mail: MailFathom turns IMAP mailboxes into a self-hosted, AI-native service. Mail synchronizes into your own PostgreSQL, is indexed for search and retrieval, and is served to AI agents over the Model Context Protocol. Semantic retrieval, answering, and gated write tools. .NET 10, AGPL-3.0-only.
AI 争论，代码结算，亏损留在账面上。一个由 Agent 驱动、面向香港及美国市场的真实券商账户：每个交易决策都必须经过辩论，并由模型无法触碰的代码完成结算。将同一决策工作流安装到你的 Agent：OpenClaw、Claude Code、Codex 或 DeepSeek Harness。AI argues. Code settles. The losses stay on the page. A real HK + US brokerage account run by agents that must debate every call, settled by code the model never touches. Install the same decision workflow into your own agent: OpenClaw, Claude Code, Codex, or DeepSeek Harness.
工厂本体驱动的数据问答框架（开源，Apache-2.0）：把中小企业台账/MES/ERP 变成可自然语言问答的语义知识图谱。CSV进答案出，确定性规则引擎+本体GraphRAG+向量混合检索，本地化数据不出厂，换行业只换词典。
开源 AI 虚拟财务部门 —— 与数据对话：NL2SQL 查询、财务建模（DCF/WACC/LBO）、RAG 文档问答、多 Agent 辩论、报告、预算、资金管理与税务。FastAPI + LangGraph + React。Open-source AI virtual finance department — talk to your data: NL2SQL querying, financial modeling (DCF/WACC/LBO), RAG document Q&A, multi-agent debate, reporting, budgeting, treasury & tax. FastAPI + LangGraph + React.
为赫尔辛基大学师生打造的 LLM 聊天工具，用于教育与研究。LLM chat built for University of Helsinki staff and students, for education and research.
RAG 管道的回归测试与配置扫描，附带统计学指标以判断变更是否真正带来改进。Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.
SharpAI 是基于 llama.cpp（通过 LlamaSharp）构建的可嵌入 Embedding、补全与模型管理平台，内置 Ollama 兼容的 Web 服务。SharpAI is an embeddable embeddings, completions, and model management platform using llama.cpp via LlamaSharp, with a built-in Ollama-compatible webserver.
运行 Ollama 本地 LLM 服务的 Docker 镜像。默认安全，所有 API 请求需 Bearer token（首次启动时自动生成）。OpenAI 兼容 API。支持首次启动模型预拉取、NVIDIA GPU (CUDA) 加速和持久化模型存储。多架构：amd64、arm64。Docker image to run an Ollama local LLM server. Secure by default, all API requests require a Bearer token (auto-generated on first start). OpenAI-compatible API. Supports first-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Multi-arch: amd64, arm64.
自托管 MCP 服务器，让你的 Obsidian/markdown 知识库可被任意 MCP 客户端检索——涵盖文本、PDF、Office 文档、图片与音频。基于类型化、可治理语料库的混合检索，5 万条笔记下仍可达亚秒级响应；文件保持纯 markdown。Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.
Namaste AI — Akshay Saini（NamasteDev）主讲的 Namaste AI 课程的手写笔记、AI 概念与真实项目。学习 LLMs、RAG、AI agents、prompt engineering，并构建 AI 驱动的应用。Namaste AI — Handwritten notes, AI concepts, and real-world projects from the Namaste AI course by Akshay Saini (NamasteDev). Learn LLMs, RAG, AI agents, prompt engineering, and build AI-powered applications.
面向 Node.js 与 TypeScript 的 AI firewall。阻止 prompt injection、音频幻觉与 RAG 数据爬取。零依赖。MIT 许可。AI firewall for Node.js & TypeScript. Stop prompt injection, audio hallucinations, and RAG data scraping. Zero dependencies. MIT
Katra — AI Agent 的认知记忆即服务。开源认知记忆基础设施，支持 MCP 协议。Katra — Cognitive Memory as a Service for AI Agents. Open-source cognitive memory infrastructure with MCP protocol support.
为 AI Agent 准备的考试评分知识脑：粘贴文档 URL，即可获得基于 MCP 的可搜索知识脑，并附带测量分数与已知缺口。AGPL。Exam-scored knowledge brains for AI agents: paste a docs URL, get a searchable brain over MCP with a measured score and known gaps. AGPL.
Overleaf 的替代品，在 LaTeX 代码编辑器内置类 Antigravity 的 agentic AI，每个项目免费支持不限数量的协作者。An Overleaf alternative with an inbuilt agentic AI (like Antigravity) in LaTeX code editor..with unlimited collabrators for each project for free
Agent 原生研究工作空间。确定性 CLI，将 arXiv / PDF / LaTeX / Zotero 论文导入 Obsidian 兼容的知识图谱，支持本地混合搜索（BM25 + 向量），具备声明级溯源，并提供每晚文献雷达。Agent-native research workspace. A deterministic CLI that ingests arXiv / PDF / LaTeX / Zotero papers into an Obsidian-compatible knowledge graph, with local hybrid search (BM25 + vectors), claim-level provenance, and a nightly literature radar.
墨西哥开放法律情报：覆盖联邦、州、市三级来源的 3 万+ 部法律 · 350 万+ 可检索条文 · 三语界面（西班牙语 · 英语 · 古典纳瓦特尔语）· 一方 RAG 聊天 · OpenAPI + SDK · 为市民、会计师、律师与 AI Agent 像代码一样导航墨西哥法律。Open legal intelligence for Mexico. 30,000+ laws across federal, state, and municipal sources · 3.5M+ searchable articles · trilingual UI (Spanish · English · Classical Nahuatl) · first-party RAG chat · OpenAPI + SDKs · built so citizens, accountants, lawyers, and AI agents can navigate Mexican law as code.
潜伏在终端与桌面里的幽灵 AI 编程 agent「Wraith」· A ghost-themed AI coding agent for terminal & desktop
Gebo.ai —— 开源、企业级、与 AI 供应商无关的平台Gebo.ai The open source Enterprise AI vendor agnostic platform
面向 AI Agent 的类脑持久化记忆：混合检索、知识图谱、睡眠-巩固生命周期、专家路由（HMoE），以及基于图 Laplacian 扩散的衰减、巩固、自动链接与谱检索子系统。提供 65 个 MCP 工具，本地运行，无需云端。Brain-like persistent memory for AI agents. Hybrid search, knowledge graph, sleep-consolidation lifecycle, expert routing (HMoE), and a graph-Laplacian diffusion subsystem driving decay, consolidation, auto-link, and spectral retrieval. 65 MCP tools. Local, no cloud.
阿拉伯语优先、开源、自托管的 AI Agent 框架——支持群体编排、长期记忆与人机协同安全机制。运行于 Telegram、Discord、Slack、Web 与 TUI。Arabic-first, open-source, self-hosted AI agent framework — swarm orchestration, long-term memory & human-in-the-loop safety. Runs on Telegram, Discord, Slack, Web & TUI.
面向 LLM Agent 的本地优先上下文引擎——在检索路径上无需 LLM 调用即可检索、权衡并压缩代码库到上下文窗口。采用 SQLite 知识存储，支持 CLI + HTTP + MCP，提供 know/miss Agent 契约。Local-first context engine for LLM agents — retrieves, weighs, and compresses your codebase into the context window with no LLM call on the retrieval path. SQLite knowledge store; CLI + HTTP + MCP; know/miss agent contract.
本仓库包含用于执行不同任务的 Gen AI 项目temThis repository contains Gen AI projects that performs different tasks
为 AI Agent 设计的记忆系统，学习真正起作用的教训：在行动瞬间注入经验，依据结果归功，以反证挑战。本地优先、多 Agent、测试门控。Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.
DeepThink-AIOS 是一个完全本地化的多 agent 系统，配备双沙箱代码/逻辑验证、ChromaDB RAG 记忆与动态 VRAM 多路复用。DeepThink-AIOS is a fully local, multi-agent System with dual-sandbox code/logic verification, ChromaDB RAG memory, and dynamic VRAM multiplexing .
在工作发生的地方就地捕获团队知识，由 agent 归档，并以可核验的引用形式给出回答。A team's knowledge, captured where the work happens, filed by an agent, and answered with citations you can check.
面向本地 AI Agent 的免费跨平台 UI，可在移动端、桌面端或无头 Docker 上编排 Ollama、嵌入式 GGUF 模型、DuckDB RAG 及 MCP 工具，无需 YAML 配置。A free, cross-platform UI for local AI agents. Orchestrate Ollama, embedded GGUF models, DuckDB RAG, and MCP tools on mobile, desktop, or headless Docker without YAML configs.
CPersona — 持久化 AI 记忆服务器，具备 3 层混合搜索、置信度评分和 30 个工具，MIT 许可。CPersona — Persistent AI memory server with 3-layer hybrid search, confidence scoring, and 30 tools. MIT licensed.