Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 8 of 126
Sento - Actor framework featuring actors and agents for easy access to state and asynchronous operations.
CodeAct Agent SDK with an AST-based code execution engine, enabling stop/start workflows, tool-level state management, and enhanced observability.
Plug and play embeddable AI chatbot widget and backend deployment framework
A programmable tool and agent runtime for Pi
ai-chat-app-with-agents-getstream
🌊 Simple, event-driven and stream oriented workflow for TypeScript
FastAPI Backend for a Conversational Agent using Cohere, (Azure) OpenAI, Langchain & Langgraph and Qdrant as VectorDB
使用 LangChain 1.0 构建的 Skills Agent,演示 Anthropic Skills 三层加载机制的底层原理。
A framework for agentic workflow creation and deployment
(Spring Boot 3. X Microservices framework) 基于Spring Boot 3.X 的 Spring Cloud Alibaba / Spring Cloud Tencent + React的微服务框架。🔝 🔝 点个starrred 关注更新。Chat GPT(RAG、TTS、STT、LLM)
An agent runtime for Python. Give your agent real work. Keep control: every action checked before it runs, every run survives a crash without silently redoing anything, every step on the record.
Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.
A tool for autonomous agents like OpenClaw to discover and learn skills autonomously
An Elixir API for calling Node.js functions
Build autonomous AI agents! 🌞
A plan engine for dynamic planning and reliable execution of AI agent workflows.
Ridiculous speed. Readable code.
Kotlin framework for conversational voice assistants and chatbots development
Pocket Flow: A minimalist LLM framework. Let Agents build Agents!
A decision brain for agentic systems: perceive context, compare options, and control execution.
OpenAI API build with Swift ❤️
Clojure functions to drive the OpenAI API
Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
Agent harness framework for building, running, and verifying LLM workflows
(NeurIPS 2024) AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning
Agent harness framework for building, running, and verifying LLM workflows
Agent harness framework for building, running, and verifying LLM workflows
A framework for autonomous economic agent (AEA) development
The Ruby framework for programming—rather than prompting—language models.
Go AI SDK, the Go way. One unified API across 21+ providers. Streaming, structured output, MCP support, stdlib only. Go AI SDK for AI applications inspired by Vercel AI SDK.
[ACL 2024] AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning
A simple Rust library for OpenAI API, free from complex async operations and redundant dependencies.
Hyperledger Aries Framework Go provides packages for building Agent / DIDComm services.
Client and server-side state management library
The Commercial Action Layer for AI Agents. Tools, Payments & Compute in OneShot.
🤖 Type-safe durable execution for agents and workflows. Resumable runs, append-only history, and compensable steps for TS/JS, React, Solid, Vue, and Svelte.
Skills Constitution — meta-rule governing all skill invocations across agent platforms
Hooks and components for working with OpenAI streams.
A truly natural scripting language
An agentic framework that helps developers build resilient agentic systems
Native Swift SDK for building autonomous AI agents with Apple's FoundationModels design philosophy
syntactic sugar 🍭 for langchain
Build production-grade agents with OpenAI AgentKit, a no-code platfrom.
Python library for building with LLMs. One interface across 11 providers (OpenAI, Anthropic, Gemini, DeepSeek, Ollama and more), automatic failover, Pydantic-validated structured output, embeddings with vector search, and an AI-powered router. pip install simplerllm
企业级 AI 智能体 Agent 平台,覆盖智能对话、文档知识问答、联网搜索、RAG 检索、MCP 工具协议、Skills 扩展等完整能力。三层执行器体系、双通道混合检索、组合式切块引擎、会话记忆管理、全链路可观测,每个环节都经过深 度设计和工程化打磨。
The definitive, open-source Swift framework for interfacing with generative AI.
Speculative programmatic tool calling (sPTC) for harnesses like RLM, CodeAct, etc.
Action library for AI Agent
the sane way to work with ai agent streams (type safety and stream resuming out of the box)
BondAI is an open-source tool for developing AI Agent Systems. BondAI handles the implementation complexities including memory/context management, error handling, vector/semantic search and includes a powerful set of out of the box tools and integrations.
LambChat — Enterprise Agent Infra for governed AI agents. Skills + MCP powered, Loop Agent ready, multi-tenant by design.
a chatgpt starter based on Openai Official Apis.
Bespoke Automata is a GUI and deployment pipline for making complex AI agents locally and offline
An unofficial C#/.NET SDK for accessing the Anthropic Claude API. This package is not affiliated with, endorsed by, or sponsored by Anthropic. Anthropic and Claude are trademarks of Anthropic, PBC.
运行时自扩展工具AI Self-Evolving AI Agent Framework | Decision-Loop Driven Microkernel Architecture with Hot-Pluggable Components & Triple-Layer Memory | Agent Infinite Evolution Engine that Learns from Failures
Forge is the open-source runtime for Anthropic's Agent Skills standard — built for the agent that runs next to a service, in your environment, on infrastructure you already operate. Write a SKILL.md. Compile to a portable, hardened agent. Deploy it anywhere containers run: Kubernetes, on-prem, air-gapped, embedded in CI, or as an A2A endpoint.
A multi-step reasoning pipeline powered by the Datarus-R1-14B-Preview model
Enterprise-grade fast-response Agent framework.
A simple and declarative way to control LLMs
Open source version of Claude Managed Agents. Fastest way to build and deploy reliable AI agents, MCP tools and agent-to-agent.
The AI Operating System for Delphi. 100% native framework with RAG 2.0, autonomous agents, MCP protocol, and universal LLM connector. Supports OpenAI, Claude, Gemini, Ollama, and more. Delphi 10.4+ (limited), full support from Delphi 12 Athens.
A tiny, plugin-first Python Agent Harness. Multi-LLM, MCP, Skills, and resumable sessions.
基于原生 Spring AI 的智能体(Agent)开发框架,提供 ReAct 执行引擎、分层记忆、工具调度、Human-in-the-Loop 等核心能力,形成完整的 Harness Engineering 方案,帮助开发者快速构建 AI Agent,可以快速搭建 Java 版的 Claude Code。
Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev or Decision api like luna as a System One decision layer for agent selection, supervision, corrections, and approvals.
Demonstrate once, execute anywhere — secure remote skills for AI agents.
PocketGroq is a powerful Python library that simplifies integration with the Groq API, offering advanced features for natural language processing, web scraping, and autonomous agent capabilities. Key Features Seamless integration with Groq API for text generation and completion Chain of Thought (CoT) reasoning for complex problem-solving and more.
A ReAct-Based Highly Robust Autonomous Agent (Harness) Framework.
Seamlessly integrate with OpenAI's ChatGPT plugins via API (or client), offering the same powerful functionality as the ChatGPT api + plugins!
AI integration layer for Jido agents with LLM orchestration and reasoning strategies.
Code for Arxiv 2023: Improving Language Model Negociation with Self-Play and In-Context Learning from AI Feedback
A Node-Based Frontend for CrewAI: Revolutionizing AI Workflow Creation
Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane: Centralised tools, MCPs, models, data, and policies with consistent observability and governance.
The open source Agent Harness with a Company Brain. Self-hosted AI Agents for Slack, Teams, Lark, DingTalk, WeCom, and more. An open source alternative to Claude Tag.
An AI framework for building cool things.
AI Agents with Bedrock
GigaAgent — это универсальный агент-оркестратор для решения широкого круга задач (ReAct + REPL)
🐦 Custom conversational assistants for your React app.
🤖 AI agents on autopilot. Any model. Runs local, cron, CI/CD, or Docker.
[ICML 2026] effGen: Enabling Small Language Models as Capable Autonomous Agents
Orchestration engine for long-running, tool-using AI agents
AgentSeek is an application development lifecycle toolkit for AI ecosystem apps, built by OceanBase OSS Team.
The companion AI agent that learns, adapts and gets the work done no matter the task
Open-source protocol suite standardizing LLM, Vector, Graph, and Embedding infrastructure across LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, and MCP. 3,330+ conformance tests. One protocol. Any framework. Any provider.
A local-first, Pi-powered AI agent workspace for Desktop, WebUI, and CLI
A model-agnostic Ruby Generative AI DSL and framework. Provides base classes for building Generators, Actions, Tasks, and Agents that can be used to build AI powered applications in Ruby.
🔮 Neuro.js is machine learning library for building AI assistants and chat-bots.
A lightweight AI agent and skill workflow framework built with Godot.
DSPy Go implementation
TAgent 是一个基于 Java 17、Spring Boot、Spring AI 和 DDD 分层构建的 AI Agent 工程实践项目。它不是只封装一次模型调用,而是覆盖了一次 Agent 请求从接入、路由、运行时装配、规划执行、RAG、记忆、MCP 工具治理、人工审批、执行中干预,到 SSE 流式输出和全链路观测的完整过程;v2 起新增个人 Agent 工作台、模型故障切换、附件解析、Python 沙箱、运行轨迹回放和评测驱动的持续改进RSI。
Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.
A simple and trans-platform agent framework and tutorial
🔮 Neuro.js is machine learning library for building AI assistants and chat-bots.
Reference architecture for agentic AI chatbots with Strands Agents and Amazon Bedrock AgentCore
Go framework for agentic AI app with MCP and built-in tools
HarnessMM: recursive self-improvement for harness token efficiency
Launching the "Agent Creation Toolkit", providing developers with an intuitive and efficient Development Environment, supporting the rapid construction of intelligent agents. The toolkit will integrate RAG (Retrieval-Augmented Generation) Knowledge Base and LLMOps toolchain.
🔥🔥🔥 Enterprise AI Harness, connect your data to AI