Agent frameworks & infrastructure

Agent frameworks & SDKs

12,596 agents · most starred first

Agent frameworks & SDKs, page 10 of 126

v12★ 156

Botpress OSS – v12

bridgic★ 156

Bridgic is the next-generation agent development framework for building intelligent systems.

cognithor★ 156

Cognithor · Agent OS: Local-first autonomous agent operating system. 19 LLM providers, 18 channels, 145 MCP tools, 6-tier memory, Agent Packs marketplace, zero telemetry. Python 3.12+, Apache 2.0.

opperator★ 155

Opperator is a framework for building and running general AI agents locally from your terminal

anchoring-ai★ 155

An open-source no-code tool for teams to collaborate on building, evaluating, and hosting applications leveraging GPT and other large language models. You could easily build and share LLM-powered apps, manage your budget and run batch jobs.

llmvm★ 155

LLM <-> Python agentic runtime prototype

my-ai-agent★ 154

My AI Agent 是一个基于 Spring Boot 和 Spring AI 框架构建的智能代理服务,集成了现代大模型能力,提供对话记忆、多模态交互等功能。本项目通过整合阿里云灵积大模型服务,实现了RAG、MCP的等主流功能

sample-agentic-platform★ 154

A sample agentic ai platform to run agentic workflows on AWS using either EKS or Bedrock AgentCore with open source frameworks like LangChain/LangGraph, Strands, etc..

argi★ 154

ARGI [/ˈɑːr.dʒiː/]: Agent Runtime and Graph Intelligence 🚀

chatbot★ 153

framework to build chatbot which could handle complex multi-turn conversation by engineering, like build website or app

hermes-bot-forge★ 153

Hermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, routines, gateway.

ai-agent-langchain-langgraph-convex-clerk-ibm-wxtools-nextjs15★ 152

Modern Next.js 15 AI agent platform with Claude 3.5, prompt caching, and intelligent tool orchestration via IBM WxFlows (turns any data source into a tool)

langroid-examples★ 151

Using Langroid's Multi-Agent Framework to Build LLM Apps

minion★ 151

👷‍♂️High performance agent framework that can do everything. Minion is designed to execute any type of queries, offering a variety of features that demonstrate its flexibility and intelligence.

ToFu★ 151

Self-hosted AI assistant with tool use, multi-agent orchestration, coding copilot and a lightweight Flask + vanilla JS stack.

prodagent★ 150

A minimal, readable agent-framework kernel — understand how LangGraph/ADK work under the hood. 1800行代码的 agent 框架内核,理解 LangGraph/ADK 底层的工作原理

apowerb★ 150

The open-source agentic framework to build, orchestrate, and operate production AI agents.

rapid-ai-dev★ 149

Toolkit for rapid AI and agent prototyping

calfkit-sdk★ 149

🐮 Build distributed, event-driven agents

MyProject-SDAgent★ 149

2026年AI开发实战项目,基于Spring Boot 3 + Java 21 + Spring AI 构建的 AI政策通 应用和 ReAct 模式自主规划智能体LvManus,覆盖主流厂商AI大模型接入、Spring AI增强特性、Prompt工程和优化、RAG检索增强、向量数据库、Tool Calling工具调用、MCP 模型上下文协议接入、AI Agent思维链、Redis 会话/事实缓存、Ollama本地模型部署、多模态(语音、图片)识别、Tavily 联网搜索、Python 爬虫脚本 + 后端 Jsoup 网站导入、React 19 + Vite 7 管理控制台、 Docker一键部署、Nginx 反向代理。

skillkit★ 148

Implementing Skills functionality for your agents

Claude-PHP-SDK★ 148

PHP SDK for Claude - Provides complete 1-for-1 functionality of the Official Python SDK

agent-starter-kit★ 148

The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) .

btw★ 147

A complete toolkit for connecting R and LLMs

RAFA_code★ 146
aegis-stack★ 146

A production-ready FastAPI platform with modular components and a built-in control plane.

loopany★ 146

A pattern for building self-iterating agents using LLMs.

toolformer★ 145

Implementation of Toolformer: Language Models Can Teach Themselves to Use Tools

harness-zero★ 145

Harness-Zero: Harness Distillation via Agent-as-Harness

llm★ 143

An agentic runtime for system programmers - in Ruby.

agentloop★ 143

Everything you need for building an agent. A Go library for the LLM tool-calling loop with budgets, hooks, skills, and tracing.

ling★ 142

The LLMs' framework optimized for ultra-fast response times.

Art★ 141

Art 是一个开源的、一站式 AI 应用开发平台,其灵感来源于行业领先的 Coze 和 Dify。我们致力于将这些先进的 LLM 应用编排理念带入 Java 世界,为广大 Java 开发者提供一个熟悉、高效、稳定且易于扩展的 AI 应用构建环境。

chat-gun★ 141

🤖 Full-stack AI agent app built with React, TypeScript and LangGraph JS. Streaming, multimodal input, human-in-the-loop, native + MCP tools, Qwen/OpenAI-compatible LLM gateway. Ships an after-sales support agent: cited RAG with abstention, human-approved refunds, idempotent execution. OpenTelemetry + reproducible evals.

Formal-LLM★ 140

Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents

sdk★ 140

A powerful TypeScript framework for building non-deterministic AI agents with advanced cognitive capabilities like reasoning, decision-making, and inter-agent collaboration within the OpenServ platform. Built with strong typing, extensible architecture, and a fully autonomous agent runtime.

subzeroclaw★ 140

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

langchain-gradio-template★ 139
ldp★ 139

Framework enabling modular interchange of language agents, environments, and optimizers

Toolio★ 139

GenAI & agent toolkit for Apple Silicon Mac, implementing JSON schema-steered structured output (3SO) and tool-calling in Python. For more on 3SO: https://huggingface.co/blog/ucheog/llm-power-steering

ruby_llm-agents★ 138

A Rails agent framework for RubyLLM — define AI agents with prompts, schemas, caching, logging, cost tracking, and a built-in dashboard for monitoring LLM usage in production.

sixb★ 138

Open-source TypeScript framework for building operational software used by humans and AI agents.

lemon★ 138

BEAM-native platform for LLM agents: OTP-supervised per-run processes, pluggable engines and channels, contract-tested extension points, and a deterministic multi-agent sim arena.

facet-standard★ 137

The Deterministic Contract Layer for AI. Defines strict tool-calling protocols, the Token Box Model for context allocation, and type-safe execution. Treats AI behavior as compiled software, not probabilistic improvisation. Eliminating runtime failures since 2025.

GeminiApp★ 137

GeminiApp is a library that allows integration to Google's Gemini API in your Google Apps Script projects. It allows for mutli-modal prompts, structured conversations and function calling

loop.js★ 137

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

goal-flow★ 137

Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to runnable code, swap wire protocols (Dify/OpenAI).

Code★ 136

Agentic Agent Framework

agentrpc★ 136

A universal RPC layer for AI agents. Connect to any function, any language, any framework, in minutes.

agentic★ 136

An opinionated framework for building sophisticated AI Agents

airbyte-agent-sdk★ 136

🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.

smol★ 136

smol is a smol agent

tinyagents★ 136

A small, provider-neutral agent harness written in Rust

IOSM★ 135

IOSM v1.0 specification: reproducible methodology for continuous system improvement. Reference runtime implementation → github.com/rokoss21/iosm-cli

open-autonomy★ 135

A framework for the creation of autonomous agent services.

fullstack-langgraph-nextjs-agent★ 135

Production-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynamic tool loading, human-in-the-loop tool approval, persistent conversation memory with PostgreSQL, and real-time streaming responses. Built with TypeScript, React, Prisma, and Tailwind CSS.

len-ai-agent★ 135

基于 Spring Boot 3.4.5 + Java 21 + Spring Al + LangChain4j + DashScope + Ollama 的智能AI交互系统🤖实战项目,适用于AI应用开发、智能体构建等场景。项目从基础模型调用到RAG知识库问答📚再到工具规划与MCP服务集成,完整覆盖了Al Agent🧠的核心技术,包括多模型接入、上下文记忆、ReAct智能规划、多模态支持🖼️、自定义工具开发等解决方案。

claude-agentic-framework★ 135

A More Effective Agent Harness for Claude

chat-gun-react-agent★ 135

🤖 A full-stack Agent Chat Runtime for pre-production validation, built with act, TypeScript, and LangGraph JS combining streaming, multimodal, HITL, and tools with durable Task/Step execution, retry budgets, idempotency, compensation, distributed locks, context governance, OpenTelemetry tracing, model fallback, cost tracking, and Opik evaluation.

Rulora★ 135

Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.

laravel-gemini★ 134

A production-ready Laravel package to integrate with the Google Gemini API. Supports text, image, video, audio, long-context, structured output, files, caching, function-calling and understanding capabilities.

Know-Your-Intent★ 134

State of the Art results in Intent Classification using Sematic Hashing for three datasets: AskUbuntu, Chatbot and WebApplication.

bedrock-agents-streamlit★ 134

Creating Amazon Bedrock agents with Streamlit Framework

AutoCoA★ 134

AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reasoning models.

foundry-agent-webapp★ 134

GitHub Copilot enabled repo for building and deploying a web application with Entra ID authentication and integrated with Azure AI Foundry Agents.

Syzygy-of-thoughts★ 133

Syzygy-of-thoughts

Chatbot★ 133

A Deep-Learning multi-purpose chatbot made using Python3

dive★ 133

Use Dive to quickly build AI agents in Go. Build agentic CLIs or add AI to your backend Go services. Easily customized and embedded in larger applications.

EcoAssistant★ 132

EcoAssistant: using LLM assistant more affordably and accurately

llm.rb★ 131

Ruby's most capable AI runtime

genai-stack★ 131

An End to End GenAI Framework

freeact★ 131

General-purpose AI agent that acts via code actions through a unified execution interface.

deepagentsdk★ 131

A Deep Agent Harness framework built with Vercel's AI SDK v6

ai-chatkit★ 131

A full-stack ai agent chat project, built with langgraph+fastapi+nextjs, supporting tool invocation and RAG knowledge base

EvolveR★ 131

(ICML 2026) Self‑Evolving LLM Agents through an Experience‑Driven Lifecycle

NarraFork★ 131

An efficient durable harness for collaboration across people, models, and devices

rasa-addons★ 130

A set of 🚀🚀🚀 components to be used with Botfront and/or Rasa

neoism★ 130

A GPU-rendered, terminal-first workspace: Agent framework, real shells, IDE, Markdown, and multiplayer — one Rust engine.

Anna-Agent★ 130

A governed, local-first AI agent for enterprise Chat, Workflows, Associate, and MCP-connected business systems.

pi.net★ 130

Pi.NET 是 Pi 的 .NET 10 移植版。Pi 是一个极简、可扩展的 Agent harness(TypeScript monorepo,约 17.1 万行),本项目把它的核心库逐一移植到 net10.0,让 .NET 生态用上同一套能力。

AdaPlanner★ 129

AdaPlanner: Language Models for Decision Making via Adaptive Planning from Feedback

llm-ReAct★ 129

从零搭建Agent框架(Build LLM ReAct Agent from scratch)

cantrip★ 129

the extensible, customizable, self-documenting, real-time multi-agent computing environment

MTConnect.NET★ 128

Fully featured .NET library in C# to build MTConnect Agent, Adapter, and Client Applications. Pre-built Agents with Windows Installers. Support for Windows and Linux. Supports MTConnect Versions up to 2.7. Supports .NET Framework 4.6.1 through .NET 10

ruby-nano-bots★ 128

Ruby Implementation of Nano Bots: small, AI-powered bots that can be easily shared as a single file, designed to support multiple providers such as Anthropic Claude, Cohere Command, Google Gemini, Maritaca AI, Mistral AI, Ollama, OpenAI ChatGPT, and others, with support for calling tools (functions).

humanus.cpp★ 127

Lightweight C++ LLM agent framework

AgentUp★ 127

Portable , scalable , secure AI Agents

loopgain★ 127

An open-source cost controller for AI agent loops — stops a loop when it's actually converged and rolls back before it degrades, instead of running to a fixed max_iterations cap. Real-time loop-gain (Aβ) bands + best-so-far rollback. Adapters for LangGraph, CrewAI, AutoGen, LangChain, OpenAI Agents, and Claude Agent SDK; raw API for custom stacks.

ai-assisted-task-executor★ 126

🤖 A Task-Driven Autonomous Agent System as an AI-powered solution that leverages LLMs, vector search, and the LangChain framework to efficiently complete, generate, and prioritize tasks using a wide range of different concepts.

langchain-teddynote★ 126

LangChain 을 더 쉽게 구현하기 위한 유틸 함수, 클래스를 만들어서 패키지로 배포하였습니다.

CollabAI★ 126

CollabAI is an open-source & self-hosted AI operation platform for small and medium-sized businesses. It’s a customizable & team-centric platform where you can have access to custom AI agents tailored to your business needs.

langchain-mongodb★ 126

Integrations between MongoDB, Atlas, LangChain, and LangGraph

Boucle-framework★ 126

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

adam★ 126

An embeddable cross-platform AI agent library written in C. Cloud and local LLMs, tool calling, long-term memory, voice, sessions, research mode, self-evolving loops. The SQLite of agent frameworks: small, portable, just works.

ai-agent-platform★ 126

企业级 AI Agent 平台 | Spring Boot 3 + LangChain4j | ReAct 推理 + 多路召回 RAG + 语义缓存 + 多智能体协作

jev-chat★ 126

A tool calling chat bot built with Jev and no LLM.

pling★ 126

Give every page a soul.

llm-auto-forge★ 125

A langchain based tool to allow agents to dynamically create, use, store, and retrieve tools to solve real world problems

openapi★ 125

OpenAPI definitions, converters and LLM function calling schema composer.

react-native-openai★ 125

OpenAI API Native bindings for React Native

More in Agent frameworks & infrastructure