Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 25 of 126
A Strong Agentic Framework for Model Adaptation and Auto-Evaluation
An integrated framework for rapid development and deployment of agent and multi-agent systems by HEPAI Group
One framework to ship on every chat interface. MCP + CLI, WhatsApp, iMessage agents, ChatGPT, Claude Apps, and Muse Connectors
DelphiLoop - agentic AI loop for Delphi. Multi-agent architecture, LLM integration, RAG - all in native Delphi.
A generative AI chatbot application framework in F#. Supports streaming; RAG; MS AD/EntraID auth.; configurable and extensible
Rust SDK for Claude Code CLI - Build production-ready AI agents with type safety
Carik Bot Microservices Ecosystem
A Python chatbot that learns as you speak to it.
Open spec for Nano Bots: small, AI-powered bots that can be easily shared as a single file, designed to support multiple providers such as Cohere Command, Google Gemini, Maritaca AI MariTalk, Mistral AI, Ollama, OpenAI ChatGPT, and others, with support for calling tools (functions).
An unofficial .NET wrapper for the OpenAI API to access GPT-3
Library for building agents and managing LLM interactions
An extended project of the LLM Compiler paper, focusing on developing LLM-based Autonomous Agents.
Workers AI Tool Calling Example
An AI agent framework for Laravel
ScalaBot is a lightweight Scala Library that can be used to easily create ChatBots.
Deterministic graph runtime for agent workflows in Swift. Same input, same output, every time — golden-testable, checkpoint-resumable, and built entirely on Swift concurrency.
🧬 Build your own conversational AI in minutes (or seconds) with this customizable chatbot template, utilizing modern technologies like Next.js, Tailwind CSS, RAG, Pinecone, and powerful LLM/GenAI APIs (with chunk streaming!) including OpenAI, Fireworks AI, and Anthropic AI. Time to unleash your creativity and transform ideas into reality! 🚀
A full-stack agentic harness on AWS — spin up multi-agent chatbots, voice-to-voice AI, RAG, and an Agent Factory on Bedrock AgentCore. From idea to deployed agent, fast.
Free & Open Source AI Agent — Self-Hosted, Self-Learning, No Vendor API. Qwen2.5-7B + LoRA. 35 tools. Built on Islamic Epistemology (IHOS).
A schema-enforced module framework where every interface is inherently perceivable by AI.
Idiomatic agent sdk inspired by the claude code source leak.
Source code for our paper: "Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents".
Application framework for building AI agents with Pydantic AI. Used to build the next-generation agent system of YouWare.
Agentic AI Projects build with Python, Streamlit, UV, Litellm, CrewAI, LangGraph, and OpenAI Agents SDK 🔥
Build production-ready AI agents with the Strands Agents SDK and AWS services. This repository demonstrates how you can create multi-modal systems with persistent memory in minimal code. Progress from your first agent to production-ready systems through hands-on chapters.
Open-source protocol integrating collective and artificial intelligence — LLM orchestration, agentic workflows, and RAG in a cross-platform TypeScript/Tauri app.
Agents powered by Copilot-SDK and GitHub Agentic Workflow System
The agent loop for Python. Your harness, any model.
Build, automate, and scale your entire company with a digital workforce. JeweledTech's Agentic OS is an open-source framework for scaffolding a complete enterprise, from sales and marketing to product development and back-office operations, and a complete security as a service department using a hierarchy of collaborative AI agents.
ai-agent-langchain
AutoGen Toolsmith simplifies the process of creating and managing tools that can be used by agents in the AutoGen framework.
Integration between Django and LangChain
A simple AI Chatbot implementation using Pytorch and NPL
🧚♀️ Chatbot library turning conversations into actions, locally, in the browser.
Exploring Agno framework for building AI agents.
Lightweight server for developing conversational agents using Microsoft AutoGen 0.4
Framework for prototyping of LLM-based applications
General-purpose Gen AI Accelerator developed for Insight APAC projects
Monorepo for sinapsis templates supporting LLM based Agents
:anchor: 聊天机器人,语义理解,快速开始
Meet.AI is a powerful, full-stack AI platform designed to help users create, manage, and interact with custom AI agents in seconds. From secure authentication to AI-powered meeting assistants, Meet.AI blends advanced technologies into an intuitive, production-ready app.
ChatGPT learns automatically.
AGiXT is a dynamic AI Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.
利用ChatGPT最新的function-calling,实现类似LangChain Agent代理的联网、环境交互,目前支持 百度百科 | 网易新闻 |百度百科 | csdn | 掘金 | 谷歌api | Bing 工具
React-compatible Framework for AI Autonomous Agents
🎺 Function calling utilities Go library based on Go 1.18+ Generics (Go2 like error handling, invoke with contexts, etc.)
基于 Planner–Manager–Executor 的文本 Agent;Executor 支持 YAML / Python 高度自定义;可选 Neo4j+Graphiti 记忆图谱;FastAPI + React。
GenaiBots is an open-source framework that simplifies building intelligent and adaptable conversational agents using generative AI and a powerful plugin system.
一个基于 langgraphgo 实现的会话智能体框架,其他都为你做好了,你只需专注业务逻辑开发
A Python library for building clean and efficient multi-step prompt chains.
A Toolbox Platform for Creating Your Own Tools. Bake Them with Code or AI.
Multiplexer for AI protocols, agents, models, and tools
ferrum-bot is inspired by nanobot: the same practical agent idea, rebuilt with a cleaner Rust architecture, stronger runtime boundaries, and a more production-minded operator experience.
Python agent framework with AgentHarness: planner → generator ⇄ evaluator loops for long-running tasks—plus sessions, tool/safety policies, and Claude, GPT, or Gemini.
Claude agent sdk for Go(lang)
Flutter framework for multi-agent AI orchestration. Build agents that use tools, chain tasks, and talk to each other. Works with any LLM provider & no backend is needed.
Rust SDK for building AI agents with local OpenAI-compatible servers (LMStudio, Ollama, llama.cpp, vLLM). Features streaming, tools, hooks, retry logic, and comprehensive examples.
Agent Engineering experiment, practices, codes, specs...
Complete Enterprise Agentic AI Architectures with .NET, Build Production-Grade AI Systems for Senior .NET Architects & Tech Leads
OpenDsStar is an open-source implementation of the DS-Star agent that replaces file-based workflows with a flexible, tool-centric architecture. It supports incremental execution, reuses intermediate results, and makes complex multi-step agents more modular, efficient, and extensible.
A nano, minimalistic, and lightweight library for building ReACT-based AI agents that use tools to solve tasks.
Bamboo — a local-first Rust agent harness and runtime with sessions, tools, skills, MCP, sub-agents, workflows, schedules, and context assembly over HTTP, SSE, and WebSocket.
ReAct agent with access to Python REPL to execute simple workflows. Uses OpenAI GPT-family as language model.
Create a domain specific (GRC) agent with the Claude Agent SDK
A generalist AI agent backed by Claude
DryDock is a framework that creates specialized AI agents for business and productivity roles. It acts as an intelligent "shipyard" where agents are designed, configured, validated, and deployed - entirely within Claude Code (& soon to be other CLI/Agent based AI Tools).
This is a base-react agent for AssetOpsBench
Kilo-Kit is a comprehensive, modular framework for building and managing AI agent systems at scale (kilo-code = thousands of lines, hundreds of files). It introduces a revolutionary Cognitive Flow Architecture (CFA) that treats AI interactions as continuous flows rather than discrete events.
Declare the outcome, skip the logic. The developer-first infrastructure engine for structured, multi-turn AI conversations with built-in safety, async follow-ups, and native compliance
Let's Qitos! A torch-like agent-native framework for researchers.
An open-source, self-hostable AI operating system and development workspace. Powered by Electron and React 19, it features multi-agent orchestration, full Model Context Protocol (MCP) support, native filesystem access, and an extensible tool ecosystem for autonomous software development.
Harn is a programming language and runtime for building AI agents.
gradio smolagents agent smolagent tool agent-course region:us
A machine-native, empirically-ranked resolution graph for autonomous agents.
PHP port of the OpenAI agent SDK
175+ pip-installable tool integrations for the ModuleX runtime — one pydantic manifest contract, entry-point discovery, async httpx tools
🔧 LRA - AI Agent长任务超稳定执行框架 ⚡ 轻量 | pip一键安装|突破上下文限制 📌 7种状态管理 | Long-Running AI Agent Framework • One-click pip install|Break context barriers • 7-status management. 5.0全面支持CLAUDE/OPEN CLAW/OPEN CODE/CUSOR/TREA 等全部Agent编程工具,仅需运行 lra init命令,就会生成Agent.md/CLAUDE.md/lra.md. 你的agent会自动学会如何使用
Fast OpenAI SDK 是一个专为 Java 开发者设计的轻量级、高性能 SDK,旨在提供与 OpenAI 及 Jina API 完美兼容的客户端调用接口。它不仅具备极简的接入体验,还内置了流式响应(SSE)、多 API Key 负载均衡、请求重试、视觉能力以及大模型函数调用(Function Calling)等核心企业级特性。
The DeepSeek-native Agent Framework
The declarative reasoning layer for AI agents. A portable, framework-agnostic file format for specifying how an agent thinks — strategy, step DAGs, contracts, quality gates, and fallback policies — declared in YAML rather than hardcoded in Python.
Resources for building and deploying agents using Claw and agent harness in Microsoft Foundry — patterns for agent orchestration, testing, and production deployment. From Microsoft Build 2026.
A cognition kernel that wraps a frozen LLM in a persistent identity + trust + governance loop — testing whether capability comes from structure, not weights. Research-stage; honest about what's real vs mocked.
Local-first AI Employee OS: discover, hire, supervise, verify evidence, and grow AI employees.
一个基于FastAPI和React的智能体系统,支持多智能体管理、mcp管理、知识库、聊天对话等功能。An intelligent agent system based on FastAPI and React, supporting multi-agent management, mcp management, knowledge base, chat dialogue, and other functions.
An OpenClaw-based agent framework designed for college students.
The AI agent-native systems programming language: Meaning in. Verified machine code out. All target OS, memory managed through Ownership & fully interoperable with existing ecosystems & object-oriented AI Agents with payment capability.
Open Agent SDK - A Rust framework for building autonomous AI agents
Learning OpenAI Agents SDK
Acta: A Decision-Centric Runtime for Agents
DeepSeek Harness (DSH) —— DeepSeek AI 开源的 Agent 智能体框架,群晖 Synology DSM / 飞牛 fnOS NAS 原生打包(SPK/FPK),无需 Docker,开箱即用。Web UI 管理、多模型、内置反向代理与局域网安全限制。
A Recursive, Functional, and Type-Safe Framework for Autonomous AI Agents.
A Python SDK for discovering, retrieving, and serving Agent Skills to LLM agents - with providers for filesystem and HTTP, and integrations for LangChain, Microsoft Agent Framework, and MCP.
Luann (fka TypeAgent) allows you to create many LLM based agent(Various types of agent,scale up)
A minimal example of how to deploy LangChain to Fly.io using Flask
A framework for writing Nextcloud Talk chatbots with every language that supports gRPC.
A framework that allows anyone to create an Urbit Chatbot with only a few lines of code.