Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 33 of 126
【已停止维护】原名 BIT · 本地优先的桌面端 AI Agent 工具中枢(工具注册 / MCP / 技能 / 远程 API)— 已更名「触手怪 Tentacle」,新仓库见 yxpil/BrainTentacle
An Effect-native agent execution kernel: sessions, runs, turns, steering, follow-ups and typed lifecycle events on top of Effect AI.
Agent-First Repository is a human-governed software environment designed so AI agents can execute engineering work efficiently while deterministic controls constrain their authority, verify their output, and preserve human accountability.
aihub 是面向 JDK 8+ 的 Java 大模型客户端。它只做一件事:把各厂商的 HTTP / SSE API 收成同一套 Java 调用。
A lightweight, embeddable, data-centric scripting language whose reach extends from JSON/FD data all the way down to runtime-compiled C and raw machine code.
Server-side agent runtime in TypeScript — streaming chat, tool calling, knowledge-base retrieval, and answers with citations. Ships with a web app and an admin console.
TypeScript SDK for durable agents, workflows, and custom execution kinds. Built by Swirls.
Crie agentes de IA como você cria personagens. App estático — HTML, CSS e JavaScript, sem build e sem backend.
Build, test, and observe AI agents inside your .NET applications.
Official module library for the start CLI
Polyant is an enterprise AI platform by Exelab for putting agents to work in business processes, at scale.
Neurosymbolic reasoning foundation for trustworthy agents.
Template for building and publishing Strands Agents extensions (tools, model providers, plugins, interventions, and more) in Python and TypeScript
SOAT — open-source infrastructure for production-ready AI agents.
A Lisp for AI: a persistent environment that humans and agents drive, extend, and grow over time.
🚀 Educational & minimalist DeepSeek Harness (DSH) architecture implementation powered by Cordis microkernel. 极简版 DeepSeek Harness 架构实现与学习指南。
Open-Source Agentic Harness for Reliable Task Completion, even on small local models. 💻🧠🤖
A Jev-driven general-purpose agent harness for faster, lower-cost execution, with built-in side-by-side experiments against LLM-only agents.
FlipperClaw: A pocket LLM agent. Flipper Zero as the UI. ESP32 as the brain. No cloud. No other device. Inspired by MimiClaw
Open-source tool-calling platform for AI agents: 80+ integrations with OAuth, MCP server deployment, memory and agent flows.
Jev for Hermes: skill discovery, multi-skill advice, adaptive reasoning effort, model recommendations, typed assessments, session re-ranking, and computer use.
A self-hosted AI factory with continuous context
Agent App is application that AI agent can build, evolve, and operate. A collaboration space for both humans and agents.
Self-evolving agent framework on DeepSeek Harness (dsh): 40 Cordis plugins, 4 presets, memory · reflection · gates · metrics · an auditable evolution loop.
LLM Function Calling Demo for YouTube video 🎥
A Java SDK for Rasa action server
A simple and efficient .NET library for accessing Anthropic's Claude AI API. This community-provided library allows you to easily integrate Claude's powerful AI capabilities into your C# applications.
Rust library (with an optional CLI) implementing the Agent Life Cycle framework
Claude Code-like AI agent framework for your app. Planning, task tracking, clarifying questions - one dependency, stateless, serverless-ready.
Baby AGI Scala Port
Autonomous LLM agent microservice for Laravel - multi-provider (OpenAI, Gemini, Claude), built-in tools, remote tool callbacks, real-time SSE streaming
Website Link
Agent View Layer (AVL): producer-owned text/agent-view companions for AI agents, CMS plugins, and agent-ready web discovery.
Plain Java Agent with Claude LLM
AWS Bedrock AgentCore with Langbase
Framework for configurable AI Agents
🧰 Agent Skills - Create, manage, and execute reusable code-based tool compositions for AI agents.
Research workspace on harness engineering, coding-agent shells, and automation workflow systems.
Powering Agent Chains by Constraining LLM Outputs
Python framework for LLM middleware tools. Build once, run anywhere: LangChain, ChatGPT Plugins, Fixie.ai, etc.
The Open eXecution Protocol Specification
This project is created just to demonstrate how functions can be used for creating multi tool agent. All credits to Sam Witteveen.
A collection of advanced LangChain modules and utilities in Python, enhancing LLM applications with custom tools, memory management, and RAG integrations. Includes code examples and tutorials for building sophisticated AI-driven workflows and applications.
Experimental langchain utilities
Comprehensive agents and an interactive UI built using conventional web dev stack.
Template for Deploying a LangChain Node App with Edgio.
A custom chat agent implemented using Langchain, gpt-3.5 and Pinecone. Implements memory management for context, a custom prompt template, a custom output parser, and a QA tool.
基于 LangGraph 实现的聊天机器人,接入 DeepSeek、Qwen、智谱 AI 多个 LLM 模型,支持在线搜索和文件解析。
langchaingo wrapper implementations for Amazon Bedrock
Production-ready agentic AI framework. High-performance, lightweight, simple. Built-in safety, memory, and 4 reasoning patterns. Ships to production fast.
Functional Python agent framework with MCP support, enterprise security, immutable state, and production-ready observability for building scalable AI systems.
create pydantic models dynamically
Develop a production-ready Stateful Agentic AI System that remembers, reasons, and deploys tools using LangGraph and Groq. This project involves building a modular application with a Basic Chatbot, a Tool-Augmented Agent, and an AI News Aggregator, emphasizing end-to-end implementation and professional deployment.
Declarative agentic harness with guiderails and state management
A cross-language, lightweight, portable, modular, locally hosted AI assistant framework designed to optimize your workflow through natural language, enhancing efficiency and productivity in your daily tasks.
Helper to deploy your bot as a serverless function (AWS Lambda)
Python SDK for Clause, 语义理解服务
Simple intent parser for python 3
An AIML interpreter library for .NET applications
Intents-Based Chatbot with Streamlit
.NET conversation modelling library for building bots with Bot Builder SDK V4.
CLI to create chat bots with JSON schema
A Feed Forward Neural Network which a ReLU activation, Cross Entropy Loss & Adam Optimizer
OLAMI API Quickstart C# .Net Framework Samples
A small library for building LLM powered applications through string composition
A GPT-based system that generates and executes high-level plans, using specialized "agents" that augment LLMs with better reasoning and external information sources
library that makes it easy to use OpenAI's Realtime API in Unity.
The full-stack powerhouse with premium integrations, designed for scalability. Ideal for production-grade apps, SaaS, and teams.
An unofficial OpenAI SDK for WinRT applications
A community maintained Kotlin library to access OpenAI.
A powerful and easy-to-use PHP SDK for the OpenAI API, allowing seamless integration of advanced AI-powered features into your PHP projects.
OpenAI API client for Android and coroutines functionalities.
A starter to build and ship GPT powered full stack apps using Next.js, Tailwind CSS and Typescript.
openapi provides an easy-to-use interface for interacting with the OpenAI API in R, allowing users to generate responses to natural language prompts and process them for various tasks.
from everything import anything
Python framework for building LLM workflows and pipelines with memory, rules, and chain of thought reasoning.
A Dinner generator agentic workflow built with Inngest and Weaviate
llama-index-go is a data framework for your LLM applications for Golang
Neuron AI PHP Framework documentation
OnIt is an AI agent harness for automation.
Serialize your functions with tools-rs!
Converso is a LangChain extension that streamlines data acquisition and action execution through natural language
HyperFlow is a framework for building agents that rewrite and test their own improvements.
Panos is an open source alternative to Manus
Prolog-Agent/SPAMI/Autonomous BDI+LLM agents
JavaScript/TypeScript conversation modelling library for building bots with Bot Builder SDK V4.
Native Swift agentic loop for the Anthropic Messages API — run Claude as a coding agent in macOS/iOS/visionOS apps without Node.js or CLI dependencies
An AI development platform that allows users to build custom AI models through an API, supporting chatbots, music generation, and coding tools to streamline creative and technical workflows.
An open-source framework that grants AI agents continuous digital life by transforming idle time into self-driven evolutionary loops.
AI productivity platform — 'AI that works like software, not chat.' Hosted SaaS + open-source local-first app with 8+ model providers, agentic workflows, and a declarative DocProcessor engine.
A Go boilerplate for building LLM-powered agents with tool calling, multi-agent workflows (Eino), and human-in-the-loop support.
A composable multi-agent AI framework for Go that makes it easy to build production-ready AI applications.
Self-hosted Java/Spring Boot AI agent framework with FSM-based ReAct loop, extensible modules, Telegram assistant for personal/group chats, REST/Web UI, OpenRouter/Ollama, and Spring Boot starter.
Autonomous recursive self-improvement engine. Subagent-first iteration loop: Plan → Modify → Verify → Keep/Discard → Learn → Repeat. Optimizes any measurable goal overnight.
A simple and efficient AI Agent assistant
A cross-language, cross-platform framework that gives all AI Agents the ability to "Jiezhu" (接住/Catch) — to catch you steadily, emotionally, unconditionally.
All-in-one Agent platform
LLMOps API 是一个基于 Flask 的 API 服务,用于构建、管理和部署基于大语言模型的智能体应用。该项目集成了 LangGraph 和 LangChain,提供了一套完整的工具链,用于创建具有状态、多角色的智能体应用程序。
Streaming-first multi-provider LLM client in TypeScript with home-made tool calling