Frameworks & SDKs

Open-source AI agent framework that turns LLMs into persistent, proactive personal AI agents with multi-channel messaging (Signal, Telegram, Discord, WhatsApp), cron scheduling, memory systems, MCP integration, skill plugins, sub-agent spawning, and browser automation

Web search, scrape and crawl API for AI agents. Turns any website, including JavaScript-heavy pages, into clean LLM-ready markdown or structured JSON, with browser actions (click, scroll, type), PDF and DOCX parsing, an MCP server and an autonomous agent endpoint. Open source (AGPL-3.0) and self-hostable

AutoGPT provides accessible AI tools for building and using AI agents, offering a comprehensive framework including Forge for agent creation, agbenchmark for performance evaluation, a leaderboard for competition, a user-friendly UI, and CLI for seamless integration and management github | github profile

February 2026 release making human oversight a native workflow primitive: suspend execution at critical decision points, expose review-and-edit UI mid-flow, and route subsequent execution based on human action (approve/reject/escalate). Demonstrates how HITL transitions from bolt-on approval gates to first-class execution-graph nodes with stateful pause/resume backed by Celery workers and Redis Pu

Langchain integrates various providers like Anthropic, AWS, and OpenAI, and offers tools for components such as LLMs, chat models, and data analysis, supporting functionalities from Alpha Vantage to YouTube github | docs

Open-source browser agent (Python and TypeScript) whose loop injects serialized DOM state each step, exposes browser actions as registered tools, and runs the same code against a local Chrome or a cloud browser. It has grown from a minimal reference into a full framework (~70k lines of Python across agent, DOM, tools, MCP, and sandbox modules) — study it for production DOM-to-context serialization

ByteDance's open-source SuperAgent harness built on LangGraph: orchestrates sub-agents with isolated contexts, persistent multi-tier memory, Docker/K8s sandbox execution, and on-demand skill loading for long-horizon tasks that span minutes to hours. A concrete reference for composing supervisor coordination, scoped delegation, and real execution environments into a single deployable harness

18 Lessons to Get Started Building AI Agents

Mem0 is an intelligent memory layer for Large Language Models that enhances personalized AI experiences by retaining and utilizing contextual information across various applications. github | website | docs | discord | twitter | github profile | linkedin

Microsoft's multi-agent conversation framework with a complete AgentChat layer covering agent loop, tool integration, termination conditions, and human-in-the-loop. The most comprehensive open-source reference for large-scale multi-agent harness design

Dual-layer harness orchestration: Crew handles autonomous agent delegation, Flow provides event-driven deterministic control (branching + shared Pydantic state). The clearest open-source example of mixing autonomous and scripted execution in the same harness

Generates agent-native CLI harnesses for any software, giving agents structured JSON access to applications that were never designed for automation. The CLI-Hub registry and auto-generated SKILL.md files turn tool expansion into a package-manager experience — solving the "long tail" of agent tool coverage without a custom wrapper per program

Flowise simplifies the creation of applications leveraging large language models (LLMs) by providing a drag-and-drop interface for customizing AI workflows, offering easy installation, Docker support, development tools, and documentation for integrating various functionalities such as authentication, streaming, and custom tools to enhance AI agents' capabilities github | website | docs | github pr

LlamaIndex offers a variety of tools for building data agents, with top downloads including IonicShoppingToolSpec, OpenAPIToolSpec, WikipediaToolSpec, GmailToolSpec, and GoogleCalendarToolSpec, enabling seamless integration with user-defined functions, query engines, and third-party services github | website | docs

by Anthropic - Anthropic's official, curated directory of high-quality Claude Code plugins, installable from within Claude Code

LangGraph is a Python library facilitating the construction of stateful, multi-actor applications with LLMs, enabling cyclic coordination across multiple computation steps, particularly suited for agent-like behaviors, while also providing streaming support, and various guides and examples for implementation and usage github

Build multi-modal Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

Open-source personal agent harness: desktop app and Rust library with built-in memory, token compression, and instant tool search, efficient enough to run hundreds of agents on a $10 server.

(31.1k ⭐) - Reference agents, skills, and data connectors for the financial-services workflows

A cutting-edge framework that compiles declarative language model calls into self-improving pipelines, enabling the systematic and efficient optimization of LM prompts and weights within complex systems github

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral) github | website

Start building LLM-empowered multi-agent applications in an easier way. github

(20.6k ⭐) - Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork & Claude Code

Workflow layer for OpenAI Codex CLI: stronger default sessions, reusable skills, native hooks, HUD/status surfaces, project guidance, and team-style execution commands.

Build Real-Time Knowledge Graphs for AI Agents

Industry-standard API spec. Foundation for agent tools

Lightweight multi-agent framework built around handoffs and guardrails; the production successor to Swarm. Complements LangGraph for harnesses where delegation patterns are simpler than full graph orchestration

HuggingFace's deliberately minimal agent library (~1,000 lines of core code): the entire harness — tool validation, memory, monitoring, sandbox isolation (E2B, Docker, Pyodide) — is readable in an afternoon. The code-agent pattern (model writes Python that calls tools, eliminating JSON round-trips) is a concrete alternative loop design worth understanding

TypeScript-native agent framework (from the Gatsby team) with 22K+ stars and 300K+ weekly npm downloads. Connects to 40+ providers through one standard interface, with built-in workflows, RAG pipelines, and agent orchestration. The @mastra/deployer handles serverless deployment, and the eval system supports LLM-as-judge out of the box. The strongest alternative to Vercel AI SDK for teams that need

Microsoft C# SDK to integrate cutting-edge LLM technology quickly and easily into your apps

Beads - A memory upgrade for your coding agent

The fast, Pythonic way to build Model Context Protocol servers 🚀

Haystack is an end-to-end LLM framework facilitating the construction of applications powered by LLMs, Transformer models, vector search, and more, offering flexibility, transparency, and extensibility, with features including retrieval-augmented generation, document search, question answering, and semantic search, along with a diverse user base including companies like Airbus, Apple, and Netflix

Official Agent Skills specification and documentation repository

NVIDIA reference stack for running always-on AI agents more safely in sandboxes, with network policy, hardening, routed inference, and lifecycle controls

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team

Google's code-first agent framework with built-in multi-agent orchestration, tool registration, session state, and eval pipeline. Its Runner and AgentTool patterns are the reference implementation for wrapping sub-agents as tools in a larger harness

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

June 2026 harness-first redesign built around the Capability primitive: a single composable unit bundling instructions, tools, lifecycle hooks, and model settings. The split between a small stable core and a fast-moving pydantic-ai-harness lets capabilities graduate as they prove essential, while deferred loading keeps unused tools out of the context window

Suna - Open Source Generalist AI Agent

Expose pipelines from RocketRide, a self-hosted, open-source AI pipeline tool with multi-LLM support, as tools

Self-healing browser harness that connects an LLM directly to your real Chrome via CDP. The critical design decision: the agent itself writes missing helpers and domain skills into the harness during execution, so the scaffold improves every run rather than requiring manual updates. At ~1k lines across four core files, it is the clearest published demonstration of an editable harness that learns f

Rust - Open-source Agent OS built in Rust. 137K LOC. 14 crates. 1,767+ tests. Zero clippy warnings

CAMEL (Communicative Agents for Mind Exploration of Large Language Model Society) is an open-source library designed for studying autonomous and communicative agents, facilitating research in understanding their behaviors, capabilities, and potential risks through scalable techniques and cooperative frameworks, including role-playing, with extensive documentation, examples, and datasets, while als

SuperAGI is an open-source framework facilitating the development, management, and operation of useful Autonomous AI Agents with a variety of features and toolkits available, including a graphical user interface, action console, and multiple vector databases github | github profile

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc

Handles frame management, streaming media coordination, and pipeline orchestration between ASR/LLM/TTS services for sub-800ms Total Turn-Around Time voice interactions. The missing harness primitive for voice agents: manages backpressure, handles frame queueing, and exposes a simple async interface for real-time constraints. Critical infrastructure for building responsive voice-first agents

GPT-powered pentesting. Automated reasoning

Outlines is a robust text generation library designed for agentic AI developers, featuring support for multiple model integrations, advanced prompting with Jinja, efficient structured generation through regex, JSON schema, context-free grammars, and more, enabling the creation of predictable and structured AI agent outputs github | website | discord

The open-source hub to build & deploy GPT/LLM Agents ⚡️

Microsoft open-source framework for building, orchestrating, and running AI agents with workflow primitives

Google's declarative runtime for running autonomous agent workloads at cluster scale: Kubernetes-style task specs, sandboxed workspaces, and network fencing.

Instructor, a Python library, facilitates working with structured outputs from large language models (LLMs), offering features like response model specification, retry management, validation, and streaming support, primarily aimed at enhancing workflows of AI agents utilizing LLMs github | website

Gorilla - Training and Evaluating LLMs for Function Calls (Tool Calls)

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

React components rendered by AI at runtime

YC-backed production harness that compiles multi-agent objectives into deterministic execution DAGs with state persistence, crash recovery, cost enforcement, and human-in-the-loop oversight. The most complete open-source reference for running agent workloads in production rather than demos

An open source TypeScript Framework for building AI agents with built-in LLM observability. github

Awesome list of tools and projects with the awesome LangChain framework

The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)

Praison AI is a low-code, centralized framework leveraging AutoGen and CrewAI to simplify creating and orchestrating multi-agent systems for LLM applications, emphasizing customization and ease of human-agent interaction github | demo | website

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources…

AWS's open-source, model-driven agent SDK that treats the loop, tool binding, and guardrails as first-class primitives. Supports Bedrock, Anthropic, OpenAI, Gemini, and Ollama with native MCP, built-in observability, and multi-agent patterns — the missing AWS open-source harness framework alongside Bedrock AgentCore

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents. github

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

(7.3k ⭐) - The official Python SDK for Claude Code

GPT Computer Assistant is an unofficial app that brings ChatGPT functionality to Windows and Linux, allowing for screen reading, microphone use, system audio interaction, clipboard management, script execution, and more github

Open-source browser infrastructure for AI agents with session-backed automation, extraction, screenshots/PDFs, an AI-native CLI, and a reusable steel-browser skill

AWS open-source framework for orchestrating specialist agents with intent routing and multi-agent collaboration patterns

(5.8k ⭐) - Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

Swarms orchestrates multi-agent collaboration for production-grade applications, solving issues like short memory and high costs, with customizable tools for specific needs, currently used by RBC, John Deere, and AI startups github | discord | docs

Python & Command-line tool to gather text and metadata on the Web - Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

TypeScript-native multi-agent orchestration that automatically decomposes a natural-language goal into a task DAG, parallelizes independent nodes, and synthesizes results. With only three runtime dependencies, built-in MCP support, token budgets, retries, and context compaction, it is the lightest production-grade harness layer for Node.js backends

AppAgent is a mobile-friendly LLM-based multimodal agent framework developed to operate smartphone apps, enabling human-like interactions for a wide range of applications without system back-end access github | github profile

Superagent is an open-source AI assistant framework backed by Y Combinator, facilitating the integration of large language models (LLM) and generative AI into applications, supporting various use cases such as question answering, chatbots, and content generation github | github profile

canonical spec, SDKs, issues, proposals, and reference materials

by Anthropic - An official AI-powered security-review GitHub Action that uses Claude to analyze pull-request diffs for vulnerabilities

IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.

Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated

Python framework for building agents from small typed parts, built on Instructor and Pydantic, with built-in OpenTelemetry tracing

Collection of AI-related utilities. Welcome to submit issues and pull requests /收藏AI相关的实用工具，欢迎提交issues 或者pull requests

An awesome & curated list of best LLMOps tools for developers

🚀 2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化

Experimental graph-first programming language where agents inspect and edit code through a compiler-derived ProgramGraph (node IDs, graph hashes, types, effects, ownership) instead of fragile text patches. Collapses the typical agent loop of edit-format-reparse-check-fix into a single compiler-validated semantic operation — a reference design for making code manipulation a structured tool interfac

Desktop app for evals, RAG and fine-tuning

AgentVerse is an Apache2-licensed Python framework for deploying multiple LLM-based agents in various applications, offering task-solving and simulation frameworks for collaborative task accomplishment and behavior observation among agents github | github profile

AG2 (from AutoGen creators) is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

High-quality datasets, tools, and concepts for LLM fine-tuning

35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.

A simple yet powerful agent framework that delivers with open-source models

The Ruby AI framework.

Open-source LLM safety evaluation including CyberSecEval

ModelScope-Agent - An agent framework connecting models in ModelScope with the world

A framework for Claude Opus to intelligently orchestrate subagents. github

Optimizing inference proxy for LLMs

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

Agentic components of the Llama Stack APIs. github

kagent is a kubernetes native framework for building AI agents