Agent frameworks & infrastructure

Agent frameworks & SDKs

12,596 agents · most starred first

Agent frameworks & SDKs, page 16 of 126

FinchBot★ 66

FinchBot is an AI Agent framework that empowers agents with true autonomy, built on LangChain v1.2 and LangGraph v1.0. With fully async architecture, agents gain the ability to self-decide, self-extend, and self-evolve

openclawnet★ 66

🐾 OpenClawNet — Build an AI Agent Platform in .NET 10 (Reactor live series materials)

copilot-sdk★ 66

Copilot SDK for building Production-ready AI Copilots for any product. Connect any LLM, deploy on your infrastructure, own your data. Built for speed and control.

hermes-rs★ 66

A high-performance Rust implementation of the Hermes-Agent orchestration loop for LLM-driven tool execution.

base★ 66

BASE is an open framework and proposed standard for shaping AI through conversation—turning the way you work into a durable, portable method you control across tools and models.

openinsight★ 66

Enterprise Agent Operating System — AI employees that learn your business and deliver outcomes. Self-hosted, open core.

shinkai-node★ 65

Shinkai allows you to create AI agents without touching code. Define tasks, schedule actions, and let Shinkai write custom code for you. Native crypto support included.

MajBot★ 65

Open source Java Chat Bot project.

open-message-format★ 65

OMF is a compact, user-friendly specification that defines a lightweight API contract between client and server for building conversational agents, and defines a standard schema for the "messages" object, which contains user and assistant interactions.

meta-prompt★ 65

A re-implementation of Meta-Prompt in LangChain for building self-improving agents.

PolyGPT★ 65

PolyGPT is an autonomous agent that can learn new capabilities on-demand.

Benevolent_AGI★ 65

Experiment to create an agentic autonomous AGI with benevolent programming

aiide★ 65

Pragmatic framework to build LLM Copilots

pydantic-ai-rlm★ 65

Pydantic AI RLM - Handle Extremely Large Contexts with Any LLM Provider

beam_weaver★ 65

Elixir-native LangChain, LangGraph, and DeepAgents for traceable LLM apps: OTP workflows, tools, memory, human-in-the-loop, streaming, custom clients/adapters, minimal deps, and WeaveScope tracing.

langchain-oracle★ 65

The Oracle LangChain integration provides official LangChain support for Oracle’s Generative AI and AI Platform services, enabling developers to build intelligent, secure, and scalable applications powered by Oracle’s cloud technologies.

LangGraph.js-MongoDB-Example★ 65

Uses LangGraph.js with MongoDB Atlas to build a stateful conversational AI agent with vector search-backed tool calling, served via an Express.js REST API.

MindAct★ 64

AI Agent + Specific Knowledge = A true Autonomous AI

rmodel★ 64

rModel is a framework for building LLM applications with agentic workflow

IntelliJava★ 64

Integrate with the latest language models, image generation, speech, and deep learning frameworks like ChatGPT, DALL·E, and Cohere using few java lines.

cigs★ 64

🚬 cigs are chainable Ai functions for typescript. Call functions with natural language and get a response back in a specified structure. Uses OpenAI's latest Structured Outputs.

CallingGPT★ 64

Build your own ChatGPT plugin platform with GPT's function calling ability | func call by GPT

DeepFlow★ 64

An Agent development framework that integrates MCP

langchain-chatbot★ 64

This code is an implementation of a chatbot using LLM chat model API and Langchain.

Self-Learning-Agents★ 64

A lightweight Python library that allows any LLM agent to self-improve through feedback, without retraining models.

langgraph-agent★ 64

It shows case studies of the LangGraph agent.

binex★ 64

Debuggable runtime for AI agent workflows. DAG pipelines, artifact lineage, and replayable runs.

genassist★ 64

GenAssist combines orchestration, runtime, analytics, and learning — in one open platform.

arkalos★ 64

Arkalos is an easy-to-use Python framework for data analysis, building data apps, warehouses, AI agents, and training LLMs with elegant syntax. It just works.

DelphiAnthropic★ 64

The Anthropic API wrapper for Delphi leverages cutting-edge models, including Anthropic's advanced Claude series, to deliver powerful features for chat interactions, vision processing, caching, efficient batch processing, connector MCP, skills and managed agents.

universal-intelligence★ 64

◉ Universal Intelligence: AI made simple.

dana★ 64

Domain-Aware Neurosymbolic Agent (Dana), an agent-native programming language

par★ 64

PAR: Programmable Agent Runtime — OCaml 5 agent framework with multi-provider LLM

millrace★ 64

A configurable runtime for creating governed agentic loops to reliably enable autonomous execution of complex multi-step workflows.

nestjs-agentic★ 64

The NestJS-native runtime for governed AI agents

agent-one★ 64

Best flexible, extensible, and free open-source AI agent

darwin-gpt★ 63

A minimal self-replicating agent based on GPT-3.5/4

radkit★ 63

Rust Agent Development Kit

chippr-agi★ 63

AGI using nodeJS and ECS

nex-agent★ 63

Your own self-evolving AI agent powered by Elixir/OTP

ai-elements-remix-template★ 63

The startkit remix template with ai elements, supports ACP agents and vercel gateway

function-calling-extension★ 63

An example extension in go using function calling and confirmation dialogs

chatbot-sdk★ 63

A SDK for building and deploying your own chatbot using NextJS in Vercel. This chatbot SDK helps you to build a gpt chatbot using the OpenAI Assistant API, in few clicks you can get a chatbot deployed in Vercel and Iframable in your website for any use case. Created by OpenAssistantGPT.

hello-world-agents★ 63

Sample .NET app using Microsoft Agent Framework to showcase collaborative AI agents (e.g. writer + editor) with web & console interfaces.

hazeljs★ 63

HazelJS Agent OS — durable TypeScript agents (DNA, Skillgate, Gatekeeper, crash-safe HITL) in your Node backend

polaris★ 63

A Rust framework for building AI agents using ECS-inspired architecture and graph-based execution.

Ameko★ 63

Ameko — LESS CHAT, MORE AUTOMATIC. A 24H self-evolving AI agent that aggregates free models into one OpenAI-compatible API, picks its own tasks, writes real code, and verifies results. Local-first, free forever. AGPL-3.0.

buddyme★ 62

Lightweight agent framework with layered personality evolution, three-tier skill loading and heartbeat memory system.

Parallax★ 62

Parallax is ALL YOU NEED? 他山之石,可以攻玉:如何让你的AI Agent更加可靠?How to Make Your AI Agent Truly Reliable?

aster★ 62

星尘云枢 - 星尘汇聚,智能成枢。生产级 AI Agent 平台,原生支持多语言执行(Python/TS/Bash),Go 性能基底。

lean-agentic★ 62

A hybrid programming language combining Lean4's formal verification with blazing-fast compilation, actor-based agent orchestration, AI-driven optimization, and vector-backed agent memory.

maxo★ 62

🐍 Асинхронный Python-фреймворк для разработки ботов MAX Bot API (max.ru)

matrix-core★ 62

Matrix by PaxLabs is a production-grade framework for building autonomous AI agents that go beyond chat! Reasoning, using tools, writing and executing code, navigating files and the web, and securely carrying out real-world workflows, including payments, on-chain operations, and smart contracts, through natural language.

Deep-agents-With-Langchain★ 62
hermes-self-evolution★ 62

A self-evolving harness framework for Hermes Agent. Evolution + Critic + Verifier + Gardener cooperate to make your Hermes instance measurably more useful over time. Generic, MIT-licensed, ships empty.

CenterOS★ 62

🎯 CenterOS — The Lightweight AI Operating System! A simple, cloneable framework that turns your AI into a personalized system for automating your business, life, and everything else.

assistant★ 61

Appwrite's AI assistant 🧠

rivescript-go★ 61

A RiveScript interpreter for Go. RiveScript is a scripting language for chatterbots.

LLMEasyTools★ 61

Tools for LLM agents.

codenano★ 61

Lightweight AI coding agent SDK. Same power, 97% less complexity. Build custom AI coding agents in 1 minutes

antflow★ 61

AI agent platform enhanced with Agent OS architecture inspired by Claude Code, built on DeerFlow

llm-ant-farm★ 61

My version of the Stanford experiment "Generative Agents: Interactive Simulacra of Human Behavior" in Python using a local LLM.

policy-synth★ 61

Policy Synth is a TypeScript class library designed to streamline and enhance decision-making processes through multi-scale AI agent logic flow.

rs-utcp★ 61

Official Rust implementation of the UTCP

vobase★ 61

The app framework built for AI coding agents. Own every line. Your AI already knows how to build on it.

matlab-ai-agent-sdk★ 61

​​Build and run AI agents in MATLAB

sema★ 61

A Lisp with first-class LLM primitives, implemented in Rust

ScouterAI★ 61

gradio agent-demo-track region:us

LangGraph-GUI-backend★ 60

LangGraph-GUI backend with fastapi

leapstacks2★ 60

Deploy AI chatbots, RAG systems, and agents in under 7 minutes on AWS.

openai-fsharp★ 60

OpenAI - F# - A library that allows you to interact with OpenAI API in an easy, fluent, and typed way!

talos★ 60

Easily create LLM automation/agent workflows

instinct.cpp★ 60

instinct.cpp provides ready to use alternatives to OpenAI Assistant API and built-in utilities for developing AI Agent applications (RAG, Chatbot, Code interpreter) powered by language models. Call it langchain.cpp if you like.

vertebra-rb★ 60

XMPP agent framework

langchain-agents★ 60
workspine★ 60

Workspine: plan, execute, and verify AI-assisted work from files in your repo, across sessions and agents.

guaca★ 60

A quiet group of AI agents on your own machine. Works out of sight, tells you only what matters. AGPL, self-hosted.

openai-java★ 59

OpenAi GPT API for Java. Including all API from OpenAI except deprecated. It especially includes stream client and jtokkit with function calculation. Including Baidu AI.

llmdantic★ 59

Structured Output Is All You Need!

alter-nlu★ 59

Natural language understanding library for chatbots with intent recognition and entity extraction.

agent-io★ 59

A Rust SDK for building AI agents with multi-provider LLM support.

aiXplain★ 59

aiXplain enables python programmers to add AI functions to their software.

claude-code-go★ 59

Go SDK for Anthropic Claude Code CLI – unofficial Claude Code Go agent SDK

ContextAgent★ 59

[NeurIPS'25] ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

synkora-ai★ 59

Open-source AI agent platform for building, deploying, and managing AI teammates. Role-based agents (PM, Engineer, Support, Marketing) with custom tools, knowledge bases, and 50+ integrations. Self-hosted, multi-provider LLM support, no vendor lock-in.

llmdantic★ 59

Structured Output Is All You Need!

springai-agentdemo★ 59

Java 后端从零学会 Agent 开发的实战项目:先用 Spring AI 2.0 把对话、RAG、工具调用、记忆逐个跑通,再读透真正的终端编码智能体 springai-code-tui。核心公式:Agent = 模型 + 工具 + 记忆 + 循环。

chatbot-startkit★ 58

This repository holds files for the simple chatbot wrote in TensorFlow 1.4, with attention mechanism and bucketing.

cleverbotfree★ 58

Free alternative for the Cleverbot API

agentai★ 58

Text to Python Objects via a LLM Function Call

FastAgent★ 58

"FastAgent: Simple, Fast, and Strong LLM Agents"

agent-kit★ 58

Agent Kit is a comprehensive AI agent development framework that integrates Claude Agent SDK, providing a complete solution from frontend to backend. This project aims to help developers quickly build, deploy, and scale production-grade AI Agent applications.

gptme-agent-template★ 58

Agent workspace template for gptme. Create persistent autonomous agents that build, learn, research, socialize, and assist you with whatever you need.

Symbiont★ 58

Symbiont lets teams build production agentic applications where every action is governed, every tool is verified, every agent has identity, and every decision leaves an audit trail.

wenzagent★ 58

纯 Dart 实现的 AI Agent 管理框架

foundation-protocol★ 58

A Python runtime for multi-entity AI collaboration — agents, humans, and tools on a shared protocol layer.

SynapsCLI★ 58

A terminal-native AI agent runtime built in Rust. Interactive chat, parallel agent orchestration, and autonomous supervision.

centaurloop★ 58

半人马环 Centaur Loop:AI 员工的最小工作单元框架。把复杂岗位拆解为可由 AI 接管、由人类治理、由反馈和记忆持续进化的循环工作流 / The smallest work unit for building AI employees.

ai★ 58

React components for building agentic AI applications.

agent-artificium★ 58

A general agent harness for long term autonomous work, continual learning, and self-improvement.

More in Agent frameworks & infrastructure