Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 12 of 126
Auto-generated Elixir SDK for OpenAI APIs with full typespecs, docs and streaming support
A low-level library for writing Go LLM agents
An opinionated C# Toolkit on top of Microsoft Agent Framework that makes life easier
CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.
A lightweight AI agent framework for vertical domain applications | 面向垂域应用的轻量级 AI Agent 框架
Core server of the SEPIA Framework responsible for NLU, conversation, smart-service integration, user-accounts and more.
A sample Chatbot in C# using Microsoft Agent Framework
AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.
Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)
An agentic workflow with a focus on reliability and developer experience
Agent Factory is an open-source studio for building, editing and chatting with AI agents. You build them from simple nodes: LLM calls, HTTP requests, JavaScript, memory and sub-agents. It runs locally with one docker-compose command, and ready-made testing agents are available in the shared agents-store repo.
Building AI Agents with LangChain, LangGraph, and LangSmith
AI Agent Nexus is an open-source platform for developing, testing, and hosting AI Agents, built with Streamlit and Gradio. It offers a user-friendly chat interface and focuses on teaching core concepts of building full-featured AI agents. The platform supports multipl AI Agent and assistant patters, and complements the book "AI Agents In Action."
agent-based reactive programming library for typescript
A simple demonstration agent using the ReACT methodology for analyzing and executing tasks.
Agent Skills to empower developers building AI applications with Weaviate.
Agent Tool Protocol
An advanced LangGraph series exploring real-world agent workflows, dynamic tools, parallel execution, long-term memory, and human-in-the-loop designs. Includes hands-on Python notebooks for building scalable, production-ready AI agent architectures.
Claude Agent SDK for Elixir – Build AI agents with Claude Code
FreeThinker is an AI agent that uses free-of-charge API open source LLMs in order to automatize tasks. That meaning that you don't required pay-per-token API keys to run it.
A collection of different implementations of the same agent to show differences in frameworks.
a2ui-vue | Vue 3 implementation of A2UI protocol. Enabling AI agents to render dynamic, interactive user interfaces in Vue applications.
Agentic-Agile Development bridges Agile process values with the capabilities of AI coding agents. It is a methodology for building software through human-agent partnerships.
This repository contains a collection of templates for building and deploying Gemini Managed Agents using the Gemini API.
Build stateful agent workflows with typed outputs, reusable tools, session forks, and ordinary TypeScript.
Agent Client Protocol Kotlin SDK
An open-source demo UI built on top of the Letta Agent SDK
Fnos 原生 Hermes Agent
DeepSeek Harness Agent Workflow
Hermes Agent Ultra (built from hermes-agent-rs core by lumioresearch, @oxterrybit). Hermes-agent feature parity at commit level. Rust Performance
Craft your own AI agent: a real Agent Skill (SKILL.md) with a job, rules and a personality. Keep your team in one folder; your AI suggests who fits and asks first. Free, private, one file.
Botfuel SDK to build highly conversational chatbots
A function calling tool can be deployed to Cloudflare Workers with openapi schema
Tools for Vercel AI SDK
Research works from Tencent AI Lab regarding self-evolving agents
Open Source Implementation of Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
A light-weight, modular, and high-performance framework for building llm agentic systems.
The next-generation AI Agent framework driven by Intent Engineering. Move beyond turn-based Function Calling to embrace code-level intent expression and embedded execution. An AI-Native, Intent-Oriented Programming Language built on Python.
This is the official implementation for AgentSPEX: An Agent SPecification and EXecution Language
Unified Agent + reusable Go agent core.
A collection of Restate examples for AI use cases: agents, A2A, MCP, ...
Open source platform for AI-native products. Pre-built AI agents with real tools and 1000+ integrations, in a Rust engine + Tauri desktop app. Free forever.
Starter kit for building an agent harness, the map, guardrails, and feedback loops that let AI agents ship software reliably.
BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand.
A seed agent: the smallest starting point from which an agent can grow
The ontology is the software. One executable business ontology: AI writes it, the runtime runs it, agents operate it, you own it. Open protocol & runtime, Apache-2.0.
AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter engineering tutorial. FastAPI / Next.js PWA / Textual TUI
Amplio: A Lightweight Agent Harness for Robust and Long-Horizon Runs
面向任务执行的 AI 工作台:模型在单个 Agent 循环里自选搜索、网页深读、地图与知识库等工具,回答来源可追溯。
A toolkit of agent primitives
A full-process dialogue system that can be deployed online
An AI agent framework built to get your agents into an application as fast as possible. Deploy on MagmaDeploy.com or self-host
Your SDK solves all of this. One interface. Unified logic. Local + hosted models. Fine-tuning. Agent tools. Enterprise-ready. Governance, RAG.Star It 🌟
Mycelium uses Maestro state machines and Malli contracts to define "The Law of the Graph," providing a high-integrity environment where humans architect and AI agents implement.
TeamClaw 是面向企业内部 AI Agent 落地的 operations control plane。它把运行时实例、Agent、Skills、模型资源、知识库、权限、审计和对话体验收口到一个多租户平台里,让团队可以在同一套界面里管理多个实例、多个部门、多个 Agent 和多个 runtime。
Unified API for running OpenCode, Claude Code, Codex agents
Enterprise-grade Next-Generation AI Agent Infrastructure
Agent framework for smart-cockpit apps · 面向智能座舱业务的 Agent 框架:零后端、权限分级、确认流、卡片编排、快慢双层、真实三方集成,加能力=加数据不加代码
OhMyHerdr native agent profiles and visual workspace runtime
基于 DeepSeek Harness 的企业级私有化 Agent 平台
💧 Query mode for agents
A seamless integration of Chainlit with LangGraph. Ideal for fast prototyping multi-LLM chatbot or AI agents.
Q-Star Agent Code: A reinforcement learning-based framework for intelligent agents using Microsoft AutoGen. It leverages Q-Star, a Q-learning variant, for dynamic decision-making. Ideal for developing adaptive AI agents in diverse applications, from service bots to advanced simulations. Includes setup and customization guidelines.
AI agent web app platform
A library for building software agents using behavior trees and language models.
Why can't an AI agent harness ship systems thinking as a skill?
Deterministic-first execution engine for agent workflows in Go: the LLM extracts at the edge, a deterministic state machine decides. Zero dependencies, no-code JSON plugins, replayable runs.
A microframework for creating simple AI agents.
AI Agent 对话平台 —— 流式对话、工具调用、子 Agent 委派、定时任务,以及每一次运行的完整审计轨迹。
Discourse AI now lives in the discourse/discourse repo
Started out as Dynamic Function Calling for OAI. Upon reviewing a research paper released (LATM) This is/has become a implementation of such system using: OpenAI and Autogen
Orchestrator Kit for Agentic Reasoning - OrKa is a modular AI orchestration system that transforms Large Language Models (LLMs) into composable agents capable of reasoning, fact-checking, and constructing answers with transparent traceability.
A microframework for creating simple AI agents.
Brain Agent for Large-Scale and Multi-Task Agent Learning
Example for connecting Linear Agents SDK with Claude Managed Agents
An easy-to-use harness for agentic projects.
面向 Agent 的轻量级工具选择与概率决策模型,基于 Qwen3.5-0.8B;DI BFCL 工具名选择准确率 77.39%。
A simple light-weight library that wraps the Open AI API.
Build AI Agents for popular LLMs quick and easy in Laravel
A light-weight framework for creating applications using LLMs
a minimalistic template for dynamic self-building AI agents
Jambo - JSON Schema to Pydantic Converter
Dartantic is an agentic framework designed to make building client and server-side apps in Dart with generative AI easier and more fun!
Agent Git: Agent Version Control, Open-Branching, and Reinforcement Learning MDP for Agentic AI. A Standalone Agentic AI Infrastructure Layer for LangGraph Ecosystems
Open source background agents
fazer.ai agents. Apache 2.0.
面向企业的轻量级 Java AI Agent 平台。涵盖Agent、Agent工作流、知识库、工具、Skill、MCP、Subagents、Prompt工程、评测、可观测性等高级AI功能
可嵌入的 TypeScript Agent Runtime —— model→tool 循环、checkpoint、interrupt 屏障,零生产依赖,可嵌进任何宿主。
A compact yet complete agent framework — small in size, full in capability.
A lightweight embedded agent framework (similar to Claude Code and OpenAI Codex).
一个用于在Unity中开发在线和离线聊天机器人的管线。A pipeline designed to create online and offline chat-bot in Unity.
[ACL 2025] Agentic Knowledgeable Self-awareness
Langbase open source Serverless AI agents, pipes, memory, and AI examples.
Lightweight social agent, with minimal dependencies
▶📚 Playbooks is a semantic programming system for AI agents
A collection of templates integrating Microsoft Teams with various AI agent paradigms.
Pure-bash LLM agent kernel — zero runtime dependencies, runs anywhere bash does.
Born for agent systems
Open bridge layer connecting local AI Agent CLIs to web, H5, mini programs, apps, IM, and custom clients.