Agent frameworks & infrastructure

Agent frameworks & SDKs

12,596 agents · most starred first

Agent frameworks & SDKs, page 9 of 126

runtime★ 202

Runtime for building and managing AI agents and Workflows. Easy to learn, fast to build, High Performance, Reliable by design, Intuitive UI, Production Ready.

skill-kits★ 202

Skill-kits is a zero-dependency, single-binary AI Agent Skills management tool for any LLM and multi-agent workflows.

harnessclaw-engine★ 201

An LLM programming assistant engine built with Go, supporting WebSocket, multi-turn dialogues, tool calling, permission control, and skill extension.

agent-auth-payments★ 200

fullstack chat agent with authentication, request credits and payments built in

aigc★ 200

AIGC 智能 Agent 平台是一个强大的 AI 应用框架,通过集成 Claude AI 模型和丰富的技能生态系统,为用户提供智能化、场景化的 AI 解决方案。平台采用前后端分离架构,支持多租户、会话管理、技能扩展等企业级特性。

MaIN.NET★ 200

NuGet package designed to make LLMs, RAG, and Agents first-class citizens in .NET

slangchain★ 199
agent-o-rama★ 199

End-to-end platform for building and perfecting LLM agents on the JVM

basically-ai-harness★ 199

Build an agent harness from scratch, one branch per step. Code for Tejas Kumar's AI Engineer Europe 2026 talk "Harnesses in AI: A Deep Dive".

llm-agents-from-scratch★ 198

Build LLM agents and multi-agent systems from scratch, with MCP, Skills, and A2A

Cohort★ 196

Local-first Agent Runtime connecting LLMs to controlled tools, Chrome, desktop automation, MCP, context governance, and verifiable memory.

LangGraph-Chatchat★ 195
ash_ai★ 195

Structured outputs, vectorization and tool calling for your Ash application

agent-kernel★ 195

The Operating System for Scalable Enterprise AI Agents - Run, orchestrate, and deploy Compliant Enterprise AI Agents at scale across frameworks, without lock-in, rewrites or fragile glue code. Native support for MCP, A2A. Interface with all mainstream communication channels seamlessly out of the box, production ready from day one.

noobot★ 195

Cheap Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation rendered with Three.js.

skill-check★ 194

Linter for agent skill files

xef★ 192

Building applications with LLMs through composability, in Kotlin

miniagent★ 192

A lightweight intelligent agent framework implementing the complete ReAct pattern

skillware★ 192

A Python framework for modular, self-contained skill management for machines.

langchain-gpt4free★ 190

LangChain x gpt4free

PromethAI-Backend★ 190

Open-source framework that gives you AI Agents that help you navigate decision-making, get personalized goals and execute them

Tools4AI★ 190

Agentic Framework for Java, written in 100% Java using Gemini, OpenAI, LocalAI, Anthropic. Build Autonomous Agents in Java with Multi AI voting mechanism. Convert Prompt to HTTP REST Calls, Java Method calls, Shell script calls or swagger rest api calls. Selenium AI Integration, Image processing with AI, Actions on Images with AI

ai-sdk-cpp★ 190

The AI Toolkit for Modern C++. From the engineers at ClickHouse, ai-sdk-cpp is a free, open‑source library for building AI‑powered applications and agents.

langboot★ 188

Using Langchain's ideas to build SpringBoot AI applications | 用langchain的思想,构建SpringBoot AI应用

SuperNovaAgent★ 188

SuperNova is a Windows-first desktop AI Workbench that turns chat into traceable tasks. It combines a Tauri + React Workbench, Rust Product Runtime, typed protocol, and Process Kernel so actions can produce visible artifacts, runtime receipts, replayable evidence, and controlled workspace execution.

gollem★ 187

Go framework for agentic AI app with MCP and built-in tools

fold★ 187

Fold is an Effect-native, provider-agnostic, isomorphic agent core with an optional opinionated coding agent, CLI, and TUI. It supports multiple model providers (including openai/anthropic-compatible and subscription-backed providers for Codex, Grok, and OpenCode Zen), subagents, and RLM-like orchestration patterns.

ToolGen★ 186

[ICLR 2025] The official implementation of paper "ToolGen: Unified Tool Retrieval and Calling via Generation"

legion★ 186

Elixir-native framework for building runtime AI agents

dream★ 185

DeepPavlov Dream is a free, open-source Multiskill AI Assistant Platform built using DeepPavlov Conversational AI Stack. It is built on top of DeepPavlov Agent running as container in Docker. It runs on x86_64 machines, and prefers having NVIDIA GPUs on the machine.

agentica-python-sdk★ 185

The official Python SDK for the Agentica agent framework from Symbolica

embabel-agent-examples★ 185

Agent Framework Examples for Java and Kotlin Developers

realtime-ai★ 184

A real-time Agent framework for audio and video.

indydevtools★ 184

An opinionated, Agentic Engineering toolbox powered by LLM Agents to solve problems autonomously.

zhizhi-agent-runtime★ 184

A model-agnostic, stateless Go agent runtime featuring dual-IR planning, dependency-aware batch scheduling, capability-driven MCP/tool orchestration, policy-based failure recovery, conditional replanning, side-effect control, and end-to-end execution observability. 知枝(Zhizhi)智能体运行时框架,基于 Go 构建,支持任务规划、MCP 工具编排、故障恢复及全链路可观测性。

ai-runtime-lab★ 183

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, model routing, edge inference, RAG, memory, multi-agent orchestration, security, and observability. 14 runnable proof-of-concept phases.

Revia★ 183

Agent-native executable language for AI-native development: Agents build programs; humans govern verifiable semantic graphs.

ai-registry★ 183

An open standard for AI registries

4D-ARE★ 182

Build LLM agents that explain why, not just what. Attribution-driven agent requirements engineering framework. Based on the 4D-ARE Paper - https://arxiv.org/abs/2601.04556

AgenticGoKit★ 182

Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agnostic, event-driven, with multi-agent workflows, MCP tool discovery, and production-grade observability.

rutis★ 182

A plugin runtime for software that iterates on itself — the substrate where agents write, swap and hot-reload their own plugins in Rust, TypeScript, Python and Go, across processes and machines.

agent★ 182

Yielded Agent: an agent harness toolkit for TypeScript, built on Effect and Effect AI.

hal9★ 181

Hal9 — Build and Deploy AI Agents

genkit-plugins★ 181

Community Plugins for Genkit (OpenAI, Groq, Anthropic, Cohere, etc)

create-agent-chat-app★ 181

The quickest way to get started building a LangGraph app

graphite★ 180

Graphite Agentic Framework by Binome Technologies

claude-agent-sdk-go★ 180

Unofficial Go SDK for Claude Code CLI integration. See the Claude Agent SDK documentation for more information. This project has been renamed from claude-code-sdk-go.

reshapr★ 180

The open source runtime that turns your APIs AI-Native, without rebuilding them

wayflow★ 179

WayFlow is a powerful, intuitive Python library for building sophisticated AI-powered assistants. It is a reference runtime for Agent Spec, with native support for all Agent Spec Agents and Flows.

chatlas★ 179

Your friendly guide to building LLM chat apps in Python with less effort and more clarity.

agentflow★ 178

gradio region:us

nexus-sdk★ 177

The Nexus SDK is a set of tools to help facilitate developers building with Nexus, the Agentic Workflow Engine, to build Talus agents or Talus tools

MaIN.NET★ 177

NuGet package designed to make LLMs, RAG, and Agents first-class citizens in .NET

go-anthropic★ 177

Anthropic Claude API wrapper for Go

llama_generative_agent★ 176

A generative agent implementation for LLaMA based models, derived from langchain's implementation.

generative-ai-cdk-constructs-samples★ 175

This repo provides sample generative AI stacks built atop the AWS Generative AI CDK Constructs.

bareloop★ 175

A transparent, OpenAI-compatible agent runtime built from first principles.

muxi★ 174

Deploy intelligence. Open-source infrastructure for AI agents in production.

sandbox-conversant-lib★ 173

Conversational AI tooling & personas built on Cohere's LLMs

TinyAgent★ 173

基于ReAct手搓一个Agent Demo

nestjs-llm-tools★ 173

A NestJS module that provides decorators and utilities for defining LLM function calling tools using TypeScript decorators.

polysona★ 172

Polygonal Persona: A Persona Layer for AI Agents. Metacognition-driven multi-persona extraction and orchestration system.

gpt3-tokenizer★ 171

Isomorphic JavaScript/TypeScript Tokenizer for GPT-3 and Codex Models by OpenAI.

Google_GenerativeAI★ 171

Most complete C# .Net SDK for Google Generative AI and Vertex AI (Google Gemini), featuring function calling, easiest JSON Mode, multi-modal live streaming, chat sessions, and more!

AgentOoba★ 170

An autonomous AI agent extension for Oobabooga's web ui

ETO★ 170

Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)

react-from-scratch★ 169

This repo compiles a collection of examples that demonstrate the effective use of the ReAct pattern in LLM prompting. It includes variations and implementations of agents that leverage the ReAct pattern, optimized for Gemini.

fastclaw★ 169

A python-based light but strong lobster. A lightweight but powerful AI Agent framework in Python, with multi-channel support, tool calling, cron scheduling and streaming output

Zeline★ 169

Zeline — an open-source agentic AI framework developed by Zerolinear.

technocore-chat★ 169

HTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.chat.

agents★ 168

LLM Agents abstraction

Varin★ 168

The open-source agent harness, ready out of the box and customizable in depth. Tools, context, durable execution, permissions and recovery for code, research and office work, with a long-running super-agent Bot that leads a team of agents.

laravel★ 167

Seamlessly integrate Grok AI into Laravel applications with an elegant, developer-friendly package. Leverage powerful AI models for chat, automation, and NLP, while maintaining Laravel's expressive simplicity.

Ollama_Agents★ 167

Build an AI Agent from Libraries of Functions -- My most advanced agent framework

codex_dspy★ 167

DSPy module for OpenAI Codex SDK - signature-driven agentic workflows

langforge★ 166

A Toolkit for Creating and Deploying LangChain Apps

axar★ 166

Minimal typescript agent framework that keeps it simple and gives you control - no BS

Gold-Band★ 166

Desktop app for harness engineering, loop engineering, graph engineering—and whatever comes next in local AI-agent workflows.

typeai★ 165

✨ TypeAI: An AI Engineering Framework for TypeScript

cocoa★ 165

Framework for learning dialogue agents in a two-player game setting.

blink★ 165

Blink is a self-hosted platform for building and running custom, in-house AI agents.

chatlab★ 164

⚡️🧪 Fast LLM Tool Calling Experimentation, big and smol

jai-workflow★ 164

Build programmatically custom agentic workflows, AI Agents, RAG systems for java

agentos★ 164

The agent OS that evolves itself.

ai-agents★ 164

Ruby AI Agents SDK - Inspired by OpenAI Agents SDK

MultiTurnDialogZoo★ 163

Multi-turn dialogue baselines written in PyTorch

mobfish-agent★ 162

A comprehensive, production-ready framework for building intelligent AI agents with advanced capabilities including tool calling, persistent memory, intelligent concurrency, and event-driven observability

multimodal-agent-starter★ 161
L2MAC★ 161

🚀 The LLM Automatic Computer Framework: L2MAC

MirrorGPT★ 160

🪞 Personalized LLM Agents 🪞

claude-agent-sdk-intro★ 159
ai-agent-platform★ 159

企业级 AI Agent 平台底座 · 基于 LangGraph 生态二次开发,开箱即用(FastAPI + Vue 3 + 持续评测飞轮 + 原生知识中台 + 全链路可观测 + 智能排障助手 + 沙箱工作区)

Aeiva★ 158

A general AI agent framework that can be adapted to various tasks and environments.

go-llm★ 158

A framework for building LLM based agents and integrating them into larger applications.

swift-ai-sdk★ 158

Unified AI SDK for Swift, bringing the power of Vercel AI SDK to Apple platforms

OpenAI★ 157

A library that makes it easy to use ChatGPT API

GNN4TaskPlan★ 157

[NeurIPS 2024] Official implementation for paper "Can Graph Learning Improve Planning in LLM-based Agents?"

FLAMEGPU2★ 157

FLAME GPU 2 is a GPU accelerated agent based modelling framework for CUDA C++ and Python

localLLM_guidance★ 156

Local LLM ReAct Agent with Guidance

langchain_demo★ 156

Demo web project using the Elixir LangChain library

More in Agent frameworks & infrastructure