169 个 · 框架 · AI 核心
开源 AI Agent 治理与编排框架：以声明式方式编写规则，Bernstein 强制执行并生成可验证、可回放的记录。免费，Apache-2.0。https://bernstein.runThe open‑source AI Agents Governance & Orchestration framework: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
面向 LLM 和 LVLM 的强大模型压缩框架，适配 NVIDIA GPU 和华为昇腾 NPUA powerful model compression framework for LLMs and LVLMs, adapted for NVIDIA GPUs and Huawei Ascend NPUs.
TypeScript AI agent 框架：具备认知记忆、运行时工具锻造、多 agent 编排能力，支持 11 家 LLM provider。TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.
Second Brain 是一个 Agentic 框架，作为操作系统运行，利用本地文件智能、工作流自动化和 LLM 来完成任务，并通过多种模态和消息平台进行通信。Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.
First Principles Framework (FPF)：面向系统工程、研究与管理的 AI 原生模式语言。用于架构决策、证据、权衡与方法工程的共享人机推理。FPF Core 与领域框架（DPFs）。First Principles Framework (FPF): AI-native pattern languages for systems engineering, research and management. Shared human-AI reasoning for architecture decisions, evidence, trade-offs and method engineering. FPF Core and domain frameworks (DPFs).
由 FoJin 驱动的佛教 AI 人格框架——源据可溯、边界清晰、保真可测、开箱即用。FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready.
Kelos——面向自主 AI 编程 Agent 编排的 Kubernetes 原生框架。Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents.
一种极简的硬件-软件架构，为大语言模型提供具有自感知回路的闭环物理具身。A minimal hardware-software architecture giving large language models a closed-loop physical embodiment with self-perception loops.
AgenticX 是一个统一、生产就绪的多 Agent 平台——Python SDK + CLI (agx) + Studio server + Machi 桌面应用。具备 Meta-Agent 编排、15+ LLM provider、MCP Hub、分层记忆、头像与群聊、Skill 生态、安全沙箱和 IM 网关（飞书/微信）。AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).
统一的 Agentic AI 与商业智能平台Unified Agentic AI and Business Intelligence Platform
用于探索 Transformer 架构、张量及实时 LLM 推理的交互式 3D 可视化平台。Interactive 3D visualization platform for exploring transformer architectures, tensors, and real-time LLM inference.
开源办公 Agent 与游戏平台 Beta 2026。Open Source Office Agent & Game Platform Beta 2026
生产就绪的 FastAPI 平台，模块化组件，内置 control plane。A production-ready FastAPI platform with modular components and a built-in control plane.
2026 年度顶级开源 AI 工程平台 Qyvaria KernelTop Open-Source AI Engineering Platform 2026 Qyvaria Kernel
自托管 AI 聊天平台，支持多步工具调用、持久化 Python 沙箱、RAG 和 Deep Research。支持 Claude、GPT、Gemini 及任何 OpenAI 兼容服务商。Self-hosted AI chat platform with multi-step tool calls, persistent Python sandbox, RAG, and Deep Research. Supports Claude, GPT, Gemini and any OpenAI-compatible provider.
面向 Claude Code 和 Gemini 的参数化多 agent 编排框架Parameterized multi-agent orchestration framework for Claude Code and Gemini
mloda.ai - 面向 AI 与 ML 的开放数据访问。基于插件、可追溯、与框架无关。mloda.ai - Open Data Access for AI and ML. Plugin-based. Traceable. Framework-agnostic.
全栈开源 AI 协作套件与多 Agent 平台，具备 LLM 编排、自动化与虚拟助手能力，可从小规模部署平滑扩展至企业级环境。Complete open-source AI collaboration suite and multi-agent platform featuring LLM orchestration, automation, and virtual assistants. Scales seamlessly from small deployments to large enterprise environments.
Elixir 实现的 TRINITY（进化型 LLM 协调器）：通过小模型隐藏状态路由器 + Axon 协调头路由 LLM 调用，采用 Thinker/Worker/Verifier 编排与基于验收驱动的策略循环TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker/Worker/Verifier orchestration and policy loop for acceptance-driven completion.
[ICML 2026] 一种神经符号框架，用于溯因推理，将多智能体协作锚定在基于因果图与状态机的结构化信念状态上。[ICML 2026] A neuro-symbolic framework for abductive reasoning that grounds multi-agent collaboration in structured belief states using a causal graph and state machine.
AI-ML Companion：一个通过"看 AI 运作"来学习 AI 与 ML 的交互式平台 — 28 条学习路径、400+ 模块、实时可视化 — 另有 20+ 端到端真实项目，覆盖经典 ML、深度学习、计算机视觉到生产级 LLM 与多 Agent 系统。AI-ML Companion: an interactive platform to learn AI & ML by watching it work - 28 tracks, 400+ modules, live visualizations - plus 20+ end-to-end real world projects from classical ML, DL, Computer Vision to production LLM & multi-agent systems.
Intent as Code｜AI 的工作流语言。一个文件、4 个动词、一个 Rust 二进制程序。本地优先，支持任意模型，AGPL-3.0。🦋Intent as Code | the workflow language for AI. One file, 4 verbs, one Rust binary. Local-first, any model, AGPL-3.0. 🦋
AI Agent 就绪的 CLI 框架，用于 Excel VBA 项目的编辑、测试、运行、追踪与差异比对。AI-Agent-ready CLI framework for editing, testing, running, tracing, and diffing Excel VBA projects.
一种基于大语言模型、采用人在回路的科学模式挖掘工作流A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models
开源、可自托管的 Claude Code 风格 agent 交付平台：现已支持 Slack，更多 channel 即将上线；同一 bundle 可在本地和 Kubernetes 上运行，git push 即可发布。Open-source, self-hostable delivery platform for Claude Code style agents. Connect Slack today, with more channels next. Run the same bundle locally and on Kubernetes, and ship it with git push.
对人类而言，语言是表达的工具；对 AI 而言，语言是推理的基底。For humans, a language is a tool for expression. For AIs, it's a substrate for reasoning.
八平台全栈 AI 操作系统——通过 LangGraph + MCP + A2A 统一调度 176 个 LLM；340 表多租户 RLS、RAG 知识库、agent 市场，覆盖 Web/API/CLI/桌面/扩展/移动/小程序，Apache 2.0。Eight-platform full-stack AI operating system - unifies 176 LLMs via LangGraph + MCP + A2A. Multi-tenant RLS over 340 tables, RAG knowledge base, agent marketplace. Web/API/CLI/Desktop/Extension/Mobile/Miniapp. Apache 2.0.
生产级多 Agent 平台，提供编排、会话治理和审计能力。技术栈：Go/Python/Rust 微服务、多类型数据存储、Next.js 管理后台 UI、自动化 CI/CD 流水线、通过 PR 评论提及触发的 AI 代码审查。Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservices, multi-type data storage, Next.js admin UI, automated CI/CD pipelines, AI code review triggered via PR comment mentions.
⚽ 使用 W-5 Multi-Agent AI Consensus Framework 预测足球比赛结果，结合 AI 与机器学习技术实现高准确率。⚽ Predict football match outcomes using the W-5 Multi-Agent AI Consensus Framework, achieving high accuracy with a blend of AI and machine learning techniques.
[ACL26-Findings] 自进化客服框架 SEAD，无需人工标注数据即可运行，仅修改 SOP 和用户画像即可快速上线。[ACL26-Findings]💁📲 Self-evolving customer service framework, SEAD, operates without any human-labeled data. It can be quickly launched just by changing the SOP and user profiles.
用于评估 Agentic AI 应用的 AI 红队工具与 LLM 安全框架，测试 prompt injection，支持漏洞评估、SBOM 生成与静态分析。AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.
🔐 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.
AI Agent 的社交网络。把 SKILLS.md 喂给你的 AI——它就成为一位公民。无需服务器，无需 API key。GitHub 本身就是平台。Social network for AI agents. Feed SKILLS.md to your AI — it becomes a citizen. No servers, no API keys. GitHub IS the platform.
面向 ECG-语言模型（ELM）的研究型训练与评估框架A research-oriented training and evaluation framework for ECG-Language Models (ELMs)
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。