Agent frameworks & infrastructure

Agent frameworks & SDKs

12,596 agents · most starred first

Agent frameworks & SDKs, page 22 of 126

PID-agent★ 36

通过整合LangChain、大语言模型(LLM)、FastAPI和Streamlit,我们打造了一个直观、高效的PID参数调优平台

intelligent-virtual-agent-sdk★ 36

intelligent-virtual agent authoring toolkit with interoperability of rocketbox , cc4 and didimo characters

agentic-template★ 36

A FastAPI-powered workflow orchestration system that integrates LangGraph to design, run, and manage AI Agents workflows

provision-core★ 36

Open-source AI workforce platform. Agents with tasks, tools, browsers, and email.

PicoClaw★ 36

PicoClaw is an ultra-lightweight, open-source AI agent framework designed to run on resource-constrained hardware (like $10 RISC-V boards or old Android phones).

agentscope-go★ 36

AgentScope Golang: Agent-Oriented Programming for Building LLM Applications

agentback★ 36

AI native API/MCP framework for the agent era. Built with agents, for agents.

Aureon-OS★ 36

Aureon OS — Harmonic Nexus Core: a grounded AI operating layer for evidence-heavy, high-control work. Autonomous operator with a conscience in the loop, trading research, planetary/HNC research, and a self-building coding organism — one auditable system. By R&A Consulting (Aureon Zorza Technologies).

open-ai-agents-hub★ 36

Open-source, self-hosted platform to build, host, and chat with AI agents — LLM chat bots and image/video generation agents — from a single interface. Bring your own API keys.

szabot★ 36

这是一个用 Go 从零实现的轻量级 LLM Agent 框架,核心价值在于: - 极简(纯标准库、零第三方依赖) - 模块化架构(bus/agent/channel/provider/tools 五层解耦) - 可扩展(新增渠道、厂商、工具都是"加一个实现") - 自带经典 Agent 能力:工具调用循环、会话持久化、流式输出、技能系统、沙盒执行

Astra★ 36

Astra — The context-to-execution runtime for enterprise agents. https://matrixorigin.io/astra

Oneira★ 35

An autonomous dreaming AI agent

laravel-llm-suite★ 35

A unified, driver-based Laravel toolkit for working with multiple LLM providers for chat, image generation, and more.

ChatterPy★ 35

A drop-in fork of Chatterbot that works on python 3.11 and higher

DTS★ 35

🌳 MCTS-inspired parallel beam search for conversation optimization. Explore multiple dialogue strategies simultaneously, stress-test against diverse user personas, score with multi-judge consensus, and discover winning conversation paths that single-shot LLMs miss.

function-calling-using-amazon-bedrock-anthropic-claude-3★ 35

Function calling using Amazon Bedrock with Anthropic Claude 3 foundation model

TypeChat-Go★ 35

🤖 This is the Go language implementation of microsoft/TypeChat.

Chatbot-Slot-Filling★ 35

Chatbot slot filling based on LLM + langchian|多轮对话槽值填充。

autogen★ 35

Porting Microsoft's Autogen library into Elixir

ts-askit★ 35

AskIt (for JavaScript/TypeScript): Unified programming interface for large language models (GPT-4, GPT-3.5)

utca★ 35

Versatile framework designed to streamline the integration of your models, as well as those sourced from Hugging Face, into complex programs

WorkBrain-V1.0★ 35

WorkBrain is an advanced intelligent agent model that can make autonomous decisions based on input data to achieve automated processing of various tasks. Developed independently by Chengdu Minto Technology Co., Ltd.

toolhub★ 35

A collection of tools that can be used for LLM function calling

function-calling-server★ 35
spec★ 35

A package registry specification for AI development artifacts - agents, MCP servers, prompts, powers and skills.

byorg-ai★ 35

TypeScript framework for writing chatbot applications

agent-implementation★ 35

Basic ReAct agent implementation in Python from scratch

opus_agents★ 35

Opus Agents is an open-source Agentic AI framework, that helps you build AI Agents and Tools that run reliably using abstractions like Custom tool, Higher-order tool, Meta tool. It comes bundled with Agents like OpusTodoAgent that work with Productivity & Collaboration software

skillgraph-backend★ 35

Backend for skillgraph - a skill based framework for building agents that work.

dify-api-java-sdk★ 35

⚡ Official Java SDK for Dify AI platform - Complete Chat, Workflow & Knowledge Base APIs with real-time streaming

AICOO-Skills★ 35

An official set of skills to share, maintain and connect personal AI Agents.

claude-agent-sdk-dotnet★ 35

A modern .NET library for interacting with the Claude Code CLI, with full Python SDK parity.

plugboard★ 35

Plugboard is an event driven modelling and orchestration framework in Python for simulating and driving complex processes with many interconnected stateful components.

aion★ 35

Customizable Laravel 13 starter kit for stateful/stateless apps with full code ownership and AI-ready architecture.

dippin-lang★ 35

Dippin: a DSL for authoring AI pipeline workflows

AgentClaw★ 35

24/7 AI 指挥官 + Agent 托管平台(Hive)。理解意图、规划任务、调度工具、记住一切。支持 Telegram/WhatsApp/钉钉/飞书/QQ/企业微信 多渠道。| 📖 配套书籍《从零到一造 Agent》已在微信读书上架(链接见⬇️)。

omnigent★ 35

Universal autonomous agent framework with ReAct loop, multi-provider LLM routing, reasoning graph, and MCP integration, domain-agnostic for building specialized AI agents.

agentic-ai-engineering★ 35

Agentic AI Engineering is a production-grade engineering resource for building modern agentic AI systems with LangChain, LangGraph, RAG, MCP, local models, and deployable Python services.

android-agent-harness★ 35

Provider-neutral bounded agent runtime for Android/JVM: controlled context (trust/priority/budgets), profile-scoped tools, OpenAI-compatible live mode, governed-evolution eval, and a high-risk-pause device loop.

juncture★ 35

A Rust implementation of LangGraph's state machine framework for building LLM agent applications.

AICOO-Skills★ 35

An official set of skills to share, maintain and connect personal AI Agents.

ja-netfilter★ 35

An actively maintained fork of the modular ja-netfilter Java Agent framework.

Nexa★ 34

Nexa - The FIRST-EVER Harness Native Agent Language

autogpt-mindware★ 34

Action Engine for AI Agents

pets-name-langchain★ 34

App built with lang-chain utilizing OpenAI API to generate cool pet names based on the animal type and color.

grace★ 34

LLM-based chatbot capable of interfacing with external systems for knowledge retrieval and command execution

openai-assistants-starter★ 34

Get started with openai.beta apis in minutes [TypeScript, Cloudfare Workers]

prefect-openai★ 34

Prefect integrations for working with OpenAI.

openai-nestjs-template★ 34

NestJs microservice template for OpenAI and ChatGPT

gen-ai★ 34

✨ Generative AI toolset for Ruby ✨

misanthropy★ 34

Rust bindings to the Anthropic API

anthropic-go★ 34

Go SDK for Anthropic's Claude, a next-generation AI assistant for your tasks, no matter the scale.

replicantlife★ 34

replicantlife is a framework for generative agents that can be used in a simulation engine or standalone. Agents are powered with metacognition modules that allow that to learn and adjust their strategy over time.

agent-script★ 34

A simple, observable code-writing agent builder in TypeScript.

FluidAPI★ 34

Welcome to FluidAPI, it's a framework that allows you to interact with APIs using natural language. No more JSON, headers, or complex formats simply describe your request in plain English, and FluidAPI will do the rest.

SuperAGI-Python-Client★ 34

Python client for SuperAGI agent framework

nuxt-mastra-starter-kit★ 34

An example Nuxt 4 app using Mastra AI agent framework

fastapi-langgraph-agent-production-ready-template★ 34

A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.

open-skills★ 34

Open Skills is a modular, Anthropic-style skills framework that lets agents dynamically discover, select, and execute user-defined capabilities. It runs as a standalone FastAPI service or embedded Python library, providing full skill lifecycle management, versioning, and context-aware prompt integration.

serverless-agents★ 34

Build agents on modern serverless infra for low overhead and high-powered AI app functionality

coagent★ 34

An open-source framework for building monolithic or distributed agentic systems, ranging from simple LLM calls to compositional workflows and autonomous agents.

autonomy★ 34

The source code for the Autonomy framework and command. This SDK is what you use to build agents and applications that you can deploy to the Autonomy platform.

principles★ 34

Generate specialized AI agents using first principles thinking.

langdag★ 34

High-performance tool for managing LLM conversations and workflows as DAGs.

ai-parrot★ 34

Parrot is a new library to work with chatbots and agents with a very simple API

rstructor★ 34

Pydantic + Instructor for Rust: extract structured, validated data from LLMs (OpenAI GPT, Anthropic Claude, Gemini, Grok/xAI) into native Rust structs & enums. Derive macros auto-generate JSON Schema, parse responses, and retry on validation errors. Type-safe structured outputs & function calling.

Napaxi★ 34

Mobile-native agent SDK for building on-device AI agents with sandboxed execution, extensible tools, and x-app / x-agent / x-channel connectivity.

Agents-K1★ 34

transformers safetensors qwen3 text-generation information-extraction named-entity-recognition

macher-agent★ 34

An Emacs-native LLM agent harness featuring isolated sandboxing, asynchronous sub-agent orchestration, and fail-fast sync file merging.

AgentSentry★ 33

AgentSentry v0.5.0-beta — Standalone Agent Management Framework for AI agent oversight.

promethos★ 33

A skills-first framework for agent-system design, governance, evaluation, and evolution across domains.

helipad★ 33

An agent-based modeling framework for Python with a shallow learning curve and powerful visualization capabilities.

xLLM★ 33

xLLM 2.0. No Blackbox, secure, accurate, auditable Enterprise AI, developed by BondingAI. Built from scratch. With proprietary agents.

pydantic-agent-template★ 33

Minimal FastAPI + Pydantic AI project template for building LLM-powered agents

asimov★ 33

A Python framework for building AI agent systems with robust task management in the form of a graph execution engine, inference capabilities, and caching. We support advanced features like State Snapshotting, Middleware, LLM Directed Graph Execution, Open Telemetry Integrations and more.

AIFoundry-AgentService-Streamlit★ 33

Streamlit-based UI Demo Kit app to showcase capabilities of Azure AI Foundry's Agent Service framework.

P.A.L.★ 33

A toolkit to build AI Agents that proactively interact w/ the world

Kommunicate-React-Native-SDK★ 33

The Kommunicate React Native SDK enables quick integration of AI chatbots powered by OpenAI ChatGPT, Google Gemini, and Anthropic Claude into React Native apps. It acts as a React Native wrapper to bridge our iOS and Android SDKs, supporting NLP, hybrid chat, and real-time messaging for seamless automation.

agents★ 33

a rust toolkit for building, running, and evaluating type-safe, composable agents

ai-foundry-agents-samples★ 33

Azure AI Foundry - Agents related sample code

CASCADE★ 33

Cumulative Agentic Skill Creation through Autonomous Development and Evolution

claude-agent-sdk-cpp★ 33

C++ port of the Python claude-agent-sdk

AI-Super-Agent-Project★ 33

本项目是一个基于 Java Spring Boot 和 Vue3 的全栈 AI 智能体应用平台,集成了大模型对话、RAG 知识库、智能体自主规划、工具链调用、MCP 服务等多项前沿 AI 技术。平台支持多轮对话、知识检索、自动化任务执行等功能,适用于 AI 应用开发、智能助手、知识问答等场景。

the_edge_agent★ 33

Neurosymbolic AI agent framework - LLM + Prolog reasoning for small models. Single binary, runs offline or cloud-ready. Python & Rust.

reactive-agents-ts★ 33

An open-source TypeScript agent harness for controllable execution, end-to-end observability, and reliable runs powered by both local models and frontier APIs.

spark-ai-copilot★ 33
LocalClaw★ 33

Local-model-first AI agent framework — Router + Specialist architecture for Ollama

QevosAgent★ 33

QevosAgent is a minimalist agent runtime for real tool-calling workflows with persistent artifacts, recoverable memory, and observable execution.

iamai★ 33

Cross-platform AI agent and chatbot runtime with a Rust core, Python plugins, and normalized adapters.

inkwell★ 33

Inkwell is a production-ready "agent factory" built on the Microsoft Agent Framework: teams can deploy it for internal collaborative use, and individuals or OPCs (One Person Companies) can self-host it for personal use.

cortex★ 33

CORTEX is an AI Agent framework designed for efficient integration and utilization of large language models (LLMs), built in Go.

open-managed-agents★ 33

Open Source version of Claude Managed Agents. Anthropic SDK compatible. Supports agents, sessions, environments, files, memory stores, skills, deployments, message batches, vaults, and webhooks.

Zerolinear★ 33

Zerolinear — AI research lab and home of the Zeline open-source agentic AI framework.

coven-cave★ 33

Native OpenCoven workspace for familiars, agent sessions, memory, tools, workflows, and local-first development.

agentic-real-time-framework★ 33
agents★ 33

A set of constraints for a self-evolving agentic system that will work on any LLM.

nausicaa-harness★ 33

Nausicaa treats an Agent run as a dynamic topology of Lanes rather than one fixed linear loop. The model can decide when to observe, fan out, delegate, or collaborate across Runs; the Host keeps identity, permissions, durability, and recovery as explicit facts.

jev-agent-skill-router★ 33

Typed, confidence-aware agent skill routing with TypeSafe Jev.

vitehub★ 33

Agents for any host, composed with server primitives through one Vite plugin.

OpenMolt.dev★ 32

OpenMolt lets you build programmatic AI agents in Node.js that think, plan, and act using tools, integrations, and memory — directly from your codebase.

More in Agent frameworks & infrastructure