Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 10 of 126
Botpress OSS – v12
Bridgic is the next-generation agent development framework for building intelligent systems.
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 is a framework for building and running general AI agents locally from your terminal
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.
LLM <-> Python agentic runtime prototype
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
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 [/ˈɑːr.dʒiː/]: Agent Runtime and Graph Intelligence 🚀
framework to build chatbot which could handle complex multi-turn conversation by engineering, like build website or app
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.
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)
Using Langroid's Multi-Agent Framework to Build LLM Apps
👷♂️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.
Self-hosted AI assistant with tool use, multi-agent orchestration, coding copilot and a lightweight Flask + vanilla JS stack.
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
The open-source agentic framework to build, orchestrate, and operate production AI agents.
Toolkit for rapid AI and agent prototyping
🐮 Build distributed, event-driven agents
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。
Implementing Skills functionality for your agents
PHP SDK for Claude - Provides complete 1-for-1 functionality of the Official Python SDK
The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) .
A complete toolkit for connecting R and LLMs
A production-ready FastAPI platform with modular components and a built-in control plane.
A pattern for building self-iterating agents using LLMs.
Implementation of Toolformer: Language Models Can Teach Themselves to Use Tools
Harness-Zero: Harness Distillation via Agent-as-Harness
An agentic runtime for system programmers - in Ruby.
Everything you need for building an agent. A Go library for the LLM tool-calling loop with budgets, hooks, skills, and tracing.
The LLMs' framework optimized for ultra-fast response times.
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。
🤖 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: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
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.
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.
Framework enabling modular interchange of language agents, environments, and optimizers
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
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.
Open-source TypeScript framework for building operational software used by humans and AI agents.
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.
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 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
A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.
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).
Agentic Agent Framework
A universal RPC layer for AI agents. Connect to any function, any language, any framework, in minutes.
An opinionated framework for building sophisticated AI Agents
🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.
smol is a smol agent
A small, provider-neutral agent harness written in Rust
IOSM v1.0 specification: reproducible methodology for continuous system improvement. Reference runtime implementation → github.com/rokoss21/iosm-cli
A framework for the creation of autonomous agent services.
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.
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。
A More Effective Agent Harness for Claude
🤖 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.
Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.
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.
State of the Art results in Intent Classification using Sematic Hashing for three datasets: AskUbuntu, Chatbot and WebApplication.
Creating Amazon Bedrock agents with Streamlit Framework
AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reasoning models.
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
A Deep-Learning multi-purpose chatbot made using Python3
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: using LLM assistant more affordably and accurately
Ruby's most capable AI runtime
An End to End GenAI Framework
General-purpose AI agent that acts via code actions through a unified execution interface.
A Deep Agent Harness framework built with Vercel's AI SDK v6
A full-stack ai agent chat project, built with langgraph+fastapi+nextjs, supporting tool invocation and RAG knowledge base
(ICML 2026) Self‑Evolving LLM Agents through an Experience‑Driven Lifecycle
An efficient durable harness for collaboration across people, models, and devices
A set of 🚀🚀🚀 components to be used with Botfront and/or Rasa
A GPU-rendered, terminal-first workspace: Agent framework, real shells, IDE, Markdown, and multiplayer — one Rust engine.
A governed, local-first AI agent for enterprise Chat, Workflows, Associate, and MCP-connected business systems.
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: Language Models for Decision Making via Adaptive Planning from Feedback
从零搭建Agent框架(Build LLM ReAct Agent from scratch)
the extensible, customizable, self-documenting, real-time multi-agent computing environment
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 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).
Lightweight C++ LLM agent framework
Portable , scalable , secure AI Agents
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.
🤖 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 을 더 쉽게 구현하기 위한 유틸 함수, 클래스를 만들어서 패키지로 배포하였습니다.
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.
Integrations between MongoDB, Atlas, LangChain, and LangGraph
Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.
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.
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
A tool calling chat bot built with Jev and no LLM.
Give every page a soul.
A langchain based tool to allow agents to dynamically create, use, store, and retrieve tools to solve real world problems
OpenAPI definitions, converters and LLM function calling schema composer.
OpenAI API Native bindings for React Native