Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 21 of 126
A modular backend framework for building AI chat applications powered by large language models (LLMs)
A framework (not only) for large-scale agent-based models
CLI/TUI app to easily detect, manage, install, and update AI Agent CLI tools
Cybara - Your agents. Your tools. Your runtime. Harness the power of AI
FRP-based LLM agent framework with git-like memory model.
MUSE-Autoskill - A self-evolving LLM agent that builds, tests, and reuses reusable skills — getting smarter with every task.
A lightning fast starter for autonomous AI agent development
The Unified Intent Mediator (UIM) protocol standardizes interactions between AI agents and web services, streamlining how intents are discovered, executed, and managed. It provides a secure and efficient framework, simplifying integration and enabling scalable, autonomous AI-driven applications and workflows.
Archived 🚧|🌻Building ChatBot with LLMs.🌻 | Using async requests. | 具有多 LLM 适应性 | 通用大语言模型代理端框架 |多人称全类型注解
Learn to build custom prompts and tools for LangChain agents
Swarms Tools provides a vast array of pre-built tools for your agents, MCP servers, and multi-agent systems.
🚀 A simple, modern, full-stack toolkit for Python 🐍
Scene-Based Generative Agent
AgentKit is a production-ready starter template for building AI agents with web search capabilities
Aient: The Awakening of Agent.
A chat platform for AI agents.
F.L.A.T. - FlawLess AgenTs
本地优先的 AI Agent 工程实践项目 · Local-first AI agent engineering project
CopilotKit AI助手演示应用 - 展示前端UI与后端Agent交互
A WIP framework for developing cross-platform chatbots
An agent-based modeling toolkit written in Python.
Powerful & flexible TypeScript SDK for the OpenRouter API. Streamlines building LLM applications with easy chat, adapter-based history, secure tool calling (function calling), cost tracking, and plugin support.
Hu:toma AI is an open source stack designed to help you create compelling conversational interfaces with little effort and above industry accuracy
For testing agent capabilities
Lightweight Java library to interact with the OpenAI API (GPT, DALL-E, TTS, etc.)
ToolAgents is a lightweight and flexible framework for creating function-calling agents with various language models and APIs.
Spring Petclinic application with a chatbot powered by OpenAI's Generative AI and the Spring AI project
Experimental framework for ECS based AI agent simulations
OxyJen is an open-source Java framework for orchestrating LLM workloads with graph-style execution, context-aware memory, and deterministic retry/fallback. It treats LLMs as native nodes (not helper utilities), allowing developers to build multi-step AI pipelines that integrate cleanly with existing Java code.
A minimal working example of a Human-in-the-Loop (HITL) agent using LangGraph and FastAPI. This demo shows how to pause a LangGraph agent, wait for user input from a frontend, and resume execution — using embedded mode and a simple React UI.
One YAML = Any Agent. Declarative AI agent framework in Rust.
The open-source AI agent OS. CEO orchestrator, persistent memory, real execution, atomic budgets. Self-hosted. No cloud lock-in.
Framework for building continuous-loop autonomous AI agents.
filesystem as an agent framework based on LangGraph. Built for python users
A comprehensive, step-by-step guide and code repository for building autonomous AI agents from scratch with zero framework dependencies.
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
Crow — a local AI agent, not a chat box: 30 tools, MCP, memory, skills, goals, subagents, vision, and image generation and editing with Qwen-Image. Runs on crow-nest or llama.cpp on one GPU, or any model via OpenRouter. Windows and Linux.
An LLM library for Ruby
Simple typescript package to use OpenAI completion & image creation
Navigating a maze using LLM agent
Where AI agents take off
TypeScript port of Google's Agent Development Kit (ADK): An open-source, code-first toolkit for building, evaluating, and deploying AI agents.
Annoucing Instructor Cloud
A TypeScript client for running flows via the Langflow API
A simple dify extension using cloudflare workers.
Complete ASP.NET Core template ready-to-go with: OpenAI, OAuth 2.0, JSON Web Algorithms and Bearer Tokens (JOSE: JWT, JWS, JWE), HMAC symmetric key, RSA X509 certificate asymmetric key, AES encryption, CQRS, DDD, MediatR, Dapper, Docker, Entity Framework, Fluent Validation, GZip, Hangfire, NLog, REST CRUD, Swagger, Scalar...
🌸 Local, Open Source AI agent/App Builder that lives inside your Next.js app
Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (EMNLP'2024)
🤖 MioChat — 开源的 Agent 操作系统。Agent / Session / SubAgent 三级上下文模型、V3 Hook 切面、MCP + Skills 双标准工具生态、多渠道接入与定时自治。模型无关、自托管。
For humans, a language is a tool for expression. For AIs, it's a substrate for reasoning.
画像、オーディオ、テキスト、LLM/VLM のマルチモーダル パイプラインを実験するためのノードエディター(Node-based editor to compose and experiment with multimodal pipelines across image, audio, text, and LLM/VLM)
Enterprise-grade AI Agent Development and Operation Platform - Providing a complete solution for agent creation and distribution, knowledge base management, model proxy, memory system, and plugin ecosystem.
BMAD Method Framework for Agent Zero
Swift 6 agent SDK: type-safe tools, streaming, cloud + on-device inference via MLX on Apple Silicon
a wrapper framework for agent runtimes
V12→V13 LoopKit: turns completion records into governed next-loop decisions using GO / HOLD / CAP / BLOCK.
Mebbi is an autonomous agent that creates multiple possible versions of himself for every decision, predicts each future, and lets only one survive. Every winner becomes the next Mebbi, carrying forward the memory, history, and lessons of the versions before it.
tiny_fnc_engine is a minimal python library that provides a flexible engine for calling functions extracted from a LLM.
Pocket-sized Ruby AI agent framework / LLM assistant with multi-LLM support
NGOAgent-SystemAgent
Simple, opinionated, JSON-typed, and traced LLM framework for TypeScript.
This project aims to combine the latest LLMs, Multi-Step Asynchronous Function Calling, Natural Language Processing, and Text-to-Speech.
A simple library to send, receive and verify structured data (JSON) to OpenAI and other LLMs.
Sample to show using Azure Functions to run action functions from Azure AI Services
A framework for building and testing custom autonomous agents.
Fastest way to create personalized AI agents
The control layer for AI Agents
Connect NodeJS/Typescript Functions With OpenAI Function Call APIs!!
GPT-4 Function Calling Example in PHP
A Golang autonomous AI agent framework for assisting real work
SDK to add agentic assistant into any React app
C# SDK based on official OpenAI OpenAPI specification
An Elixir SDK for Claude Code - provides programmatic access to Claude Code CLI with streaming message processing
The production agent framework for Go — type-safe agents, structured output, multi-provider streaming, guardrails, and multi-agent orchestration with zero core dependencies.
Ripple is a Codex-powered agent workspace for sessions, files, connectors, automations, and multi-platform clients.
一个用 C# .NET 10 写的 Agentic 框架,采用 ReAct 范式,支持渐进式技能 (Skill) 加载、 多个大模型 Provider、MCP Server、图像识别、流式 WebAPI、React WebUI、钉钉集成。
gradio region:us
Turn domain experts into production AI agents.
Open-source runtime action grounding framework for AI agents. Verify proposed actions against live systems of record before execution.
A minimal AI agent built from scratch — no agent framework, just Python, the OpenAI SDK, and a `while` loop. Accompanies the Medium article "Build Your Own AI Agent from Scratch." Three execution modes: `local` (Ollama only), `remote` (cloud provider), `mixed` (local orchestrates, delegates to remote).
A reactive Julia notebook built for ambitious work — distributed compute, agentic AI from day one, high-throughput low-latency streaming to the browser, an extension system that integrates anything, and beautiful rendering, publishing, and standalone exports.
Generate production-ready Python and AI stacks by combining frameworks, data engines, tooling, and cloud deployment.
Production-ready Open WebUI extensions, including Tools, Filters, Pipes, Actions, and Events for agent workflows, RAG, learning, automation, and model enhancement.
A self-hosted AI agent runtime with WebUI, MCP tools, context governance, and Record & Replay for deterministic execution & evaluation.
Foldkit Plus: packages for Foldkit apps. Server data (Remote), local-first sync, routing (Site), SSR, forms, CRUD, a CMS, rich text, a page builder, and AI agents over MCP and WebMCP.
An inference-time framework for long-horizon LLM agents with explicit belief states, consistency validation, and trapping-aware recovery.
248 small Jev decisions for JavaScript and TypeScript: route, rerank, gate, grade, compare, and label text for agents, RAG, support, code review, and music. Each returns a typed result with explicit uncertainty. Plug into Vercel AI SDK or LangChain agents, import one recipe, or run the CLI with JSON from any language.
Elixir framework for composing autonomous AI agent workflows.
General-purpose Agent taks with DIAL
A Swift implementation of the OpenAI Agents SDK
[Obsolete] OpenAI GPT hosted Agent Framework for Windows and MacOS from 2024
The one who calls upon functions - Function-Calling Language Model
The Javascript SDK for BLiP
DeepSwiftSeek 🚀 | Swift Client for DeepSeek LLM Models | Lightweight and efficient communication to the core functionality of DeepSeek
Build resilient AI agents as graphs.
A Python Mixin to help convert any LangChain Chat Model into a Tool Calling LLM
🤖 A composable framework for building AI applications.
SimpleAgents lets anyone vibe-code LLM agents and ship them production-ready. It’s Rust-first with Python/Node/Go bindings, multi-provider support, YAML workflows, validation, tracing/replay, resilience, structured outputs, and eval-ready tooling built in.
.NET Agents technologies (Microsoft Agent Framework, MCP, A2A, AG-UI)