Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 23 of 126
OpenAI functions + Chainlit + Streaming responses. Chain multiple functions in one query.
Pocket Flow: A minimalist LLM framework. Let Agents build Agents!
🧠 Create chatbots easily with Bot Framework! 🤖
A Swift library for integrating with the OpenAI Assistants API, enabling the creation and management of assistants, message processing, and AI runs.
Easy to use, scalable admin portal for deploying and managing AI Assistants
Dynamic, highly customizable language agents framework
This demo application showcases the implementation of Spring Boot microservices, highlighting their powerful features and capabilities, with a particular emphasis on integrating OpenAI for advanced AI functionalities.
Unofficial Go SDK for the Anthropic Claude API.
Build domain AI assistants with annotated dialogue examples - 通过标注对话示例,低成本构建可靠智能体
Stella - A scalable platform for creating and managing AI agents
The multi-backend, multi-modal micro-framework for AI agent development, orchestration, and deployment
A self-hostable base for building and running custom agents that's heavily inspired by Claude Code on the web.
Medusa Skill Framework for AI Agents.
Lyzr Agent Framework is the first and only agent framework to natively integrate Safe AI and Responsible AI modules in its core agent architecture
Go SDK for Claude agents
Minimal runtime for Recursive Language Models (RLMs) inspired by the MIT CSAIL paper "Recursive Language Models".
AgentOS is a lightweight, single-file implementation that provides a robust foundation for building autonomous AI agents. It implements the core concepts outlined in Karpathy's Agent OS architecture while maintaining simplicity and extensibility.
⚡ Production-ready LangGraph interrupt template with modern web interface | Human-in-the-loop AI workflows | FastAPI backend + Next.js frontend
可自托管的 Go AI Agent 服务,集成多模型、工具调用、RAG 知识库、长期记忆、MCP、技能和任务自动化,支持桌面客户端、API 与多平台 IM 接入。
AI toolbox for grounding LLMs on Langium DSLs with evaluation, constraints, and agent skills
gradio region:us
Digital Life · Life Engineering — A runtime framework for persistent, autonomous LLM agents
Eight-platform full-stack AI operating system - unifies 176 LLMs via LangGraph + MCP + A2A. Multi-tenant RLS over 340 tables, RAG knowledge base, agent marketplace. Web/API/CLI/Desktop/Extension/Mobile/Miniapp. Apache 2.0.
CPU-oriented Python library for discrete Active Inference experiments in radCAD and cadCAD: deterministic grid worlds, multi-agent transitions, generative-model helpers, and fail-closed validation.
Autonomous agent loops for Hermes Agent: the autoresearch harness and the health/improvement maintenance loops.
Run LangGraph and LangChain apps behind a FastAPI runtime with a standalone agentseek-api CLI
Add an agent to your app in minutes
Open-source AI agent framework for PHP. Tools, memory, security guards and a ReAct loop built in. Works with Laravel, Symfony, WordPress, Drupal, Magento, Joomla, OpenCart, PrestaShop. Any LLM provider. MIT.
Argolink-focused agent workflows and provider-neutral integration for GPT-6 Sol.
Autonomous framework for long-running agents: a charter guides Claude Code, Codex or Pi through an actor, critic and scribe loop for hours.
a tiny, exploitable chatbot that can use tools
Starter template AI chatbot, built with Next.js and Humanloop
Neuroscience Inspired Agent Reasoning Framework
Lightweight AI agent library. Turn Python functions/classes into AI tools instantly. No verbose configs or complex abstractions.
Langchain desktop app @multi-Agent
OpenMindedChatbot is a Proof Of Concept that leverages the power of Open source Large Language Models (LLM) with Function Calling capabilities to provide comprehensive and flexible responses to user queries.
Building AI Agents with Typescript and OpenAI Agent SDK
CloudLLM is a batteries-included Rust toolkit for building intelligent agents with LLM integration, multi-protocol tool support, and multi-agent orchestration.
Y-Agent Studio 是一个面向 企业级应用 的Agent开发套,Y-Agent是其中的核心模块。 包含了:支持智能体编排、RAG、流程日志、单元测试、流程测试、语料生产等垂直领域非常需要的功能。 智能体编排可以在同一个流程中,同时支持多智能体协作和流程混合编排。
Text-first toolkit for building reproducible, composable LLM workflows as plain files in OCaml.
A demo Phoenix LiveView application showcasing the Sagents's multi-conversation agent architecture.
Ubiq-Genie is an open-source framework for integrating AI capabilities into social VR platforms. It offers a modular approach for server-assisted VR applications, enabling new types of collaborative VR experiences such as conversational agents driven by large language models and voice-driven diffusion-based texture generation.
An AI Agent framework in Go for building Agents with RAG, Knowledge, Memory, Tools
A standard SDK for building agent-facing apps across MCP, CLI, React, and AI tool stacks.
Unified multi-layer caching library for AI/agent pipelines — LangChain, LangGraph, AutoGen, CrewAI, Agno, A2A
🦅 Open-source AI agent runtime in Rust — Self-hostable with persistent memory, self-improving skills, MCP support, built-in cron, multi-platform messaging & production gateway.
FastAPI backend blueprint for AI agent apps: DDD, SQLAlchemy, Taskiq, admin UI, RAG infra, and Claude/Codex collaboration harness.
Zeno Agent 是一个面向企业(toB)的服务端 AI Agent 平台,基于 Spring Boot + LangChain4j 1.11.0 构建。平台的核心能力在于:每个 Agent 可以独立配置自己的工具集、知识库和 Skill 库;通过 GLOBAL/PERSONAL 双模式 MCP 架构,既支持企业统一管控的服务端工具,也支持用户私有的客户端工具(密钥不离开浏览器);配合工具渐进式加载和 Skill 渐进式注入,突破 LLM 上下文窗口限制,让 Agent 可以绑定上百个工具
MultiTable is an open-source AI agent framework and meta-harness that gives you a common orchestration layer over LLM providers
gradio region:us
AI Agent for WordPress — agentic AI loop with tool-calling via the Abilities API
Runnable examples integrating Circle Agent Stack with LangChain, Claude Agent SDK, OpenAI Agents SDK, Vercel AI SDK and Google ADK.
Sage is a skills framework that makes AI agents think before they act, stay focused under complexity, and deliver outcomes you can trust. Built for product and engineering teams, open to any domain.
Autoregressive Thought Generation Agent Framework
A multi-model Agent runtime built on Spring Boot 4 / Spring AI 2.0: model routing (Anthropic / DeepSeek / OpenAI / custom), thinking toggle, Task subagents, hot-pluggable Skills, Docker sandbox + Code Interpreter, MCP tools, dify/n8n integration, RAG with pgvector, Human-in-the-Loop approvals — all streamed as structured SSE events.
A modular local AI agent built with Python and Ollama, featuring tool calling, memory, web search, document processing, embeddings, and RAG.
AgentMake AI: a kit for developing agentic AI applications that support 24 AI backends and and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong) Supported backends: anthropic, azure, azure_any, cohere, custom, deepseek, genai, github, github_any, googleai, groq, llamacpp, mistral, ollama, openai, vertexai, xai
🦞 Build on Crustocean
This is an example Gen AI app built with Langgraph.js, Next.js and Vercel's AI SDK
A fluent Laravel package for integrating with OpenAI, Anthropic Claude, Mistral, and Cohere AI services. Features a modern builder API, typed responses, streaming support, database-backed conversations, a RAG knowledge base system, an embeddable chat widget, and first-class testing support.
Autonomys Agents is an experimental framework for building fully autonomous AI agents on the Autonomys Network and beyond.
Linq's Function Calling Agent utilizing DeepSeek-R1
Lugha is a PHP Generative AI Framework to build chatbot, RAG systems and AI-powered applications
Micro-agent framework for Caido
AI agent framework
Liz is a lightweight framework for building AI agents
Augmented AI decision framework
Easily create tools from zod schemas to use with OpenAI Assistants and Chat Completions, inspired by tRPC
Making LLM Tool-Calling Simpler.
Framework for Java and Groovy Agents
An open-source chat text to control actions agentic workflow framework/showcase powered by Agently AI application development framework.
:expressionless: Core yetibot utilities, extracted for shared use among Yetibot and its various plugins
Autoregressive Thought Generation Agent Framework
OpenAI model implementation for the ADK-Go
Self-hosted multitenant platform for AI agents and Telegram bots with event-driven architecture
Simulation Streams is a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows.
Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
Make stochastic AI systems durable with one decorator
Real, runnable Flue agents on Cloudflare. Examples teach one product at a time; recipes compose. Every snippet ships an E2E test that deploys an ephemeral Worker, asserts, and tears it down.
A scalable AI chatbot platform built with FastAPI and LangGraph, featuring multi-agent orchestration, multi-tenant vector storage, cross-chat memory, and voice call capabilities through LiveKit integration.
Auto-evolving LLM Agent Harness - Benchmark-driven evolution via Claude Code + self_evolution.md guide
AI 原生多租户 SaaS 开发框架 — FastAPI + Vue 3 + PostgreSQL,内置 AI Agent、RAG、插件系统、RBAC、异步任务等核心能力,助力快速构建行业 SaaS 应用。
A local-first desktop application for AI agent workflows.
Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully yours.
Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source
Agent-first multi-tenant Next.js template (rules, sub-agents, skills, Better Auth, Prisma)
Moved to PostHog/coherence — development continues there as @posthog/coherence.
Content agent template for the eve agent framework
Qavor 是面向开发者的 AI Agent 构建、扩展、运行与观测全栈平台。后端 Go + CloudWeGo Eino,前端 Vue 3 + Vite,整合模型管理、Agent 编排、RAG 知识库、MCP/Skill 工具扩展、Redis 异步队列与 SSE 流式服务,并提供内置链路追踪与数据总览。
LangGraph agent template with MCP.
Agent Builder API - Backend service for Agent Smith extension
Create, customize, and launch autonomous AI Agents in your browser. 🤖🚀
Lightweight AGI: Building General AI with Golang and Flexible Language Models
Convert Python code into JSON consumable by OpenAI's function API.
This is an unofficial C# library for the OpenAI API. As there are no official libraries available, we have created our own to help C# developers interact with the API easily.
An elegant NodeJs library for openai api.
🦞 Advanced GPT agent on Crustocean
This repository contains a basic Node.js example demonstrating how to call functions using the OpenAI API. The example showcases a conversation with the OpenAI GPT-3.5 Turbo model, including making function calls and processing their responses.
A robust framework for building AI agents with multi-provider LLM support