Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 38 of 126
✨ AI Agent that uses tools and functions to autonomously complete multiple tasks.
AI agentic setup. Backend-agnostic, RAG, tooling
AI Code Mentor is a runtime environment designed for building applications with integrated autonomous AI agents.
Universal AI Consciousness Genesis & Navigation System
A high-performance, native C# implementation of the Universal Tool Calling Protocol - enabling AI agents to discover and communicate directly with tools without wrappers or middleware.
FlexiAgent is a simple and easy-to-use framework for creating LLM agents. The agent supports structured output and includes built-in practical agents such as a text2sql agent, allowing for quick deployment in applications.
This is a repository for the Crew AI agents with full stack development using JS(Basic).
AI agents, trained by the minds that move the world.
Tool for executing C/C++ code snippets with Langchain Agents.
Java implementation for LangChain
基于LangGraph构建的智能体系统,通过FastAPI暴露OpenAPI接口,实现智能体编排功能。
🚀 Community-driven Naver integrations for LangChain! Seamlessly connect Naver's search, translation, and AI services with LangChain to build powerful AI-driven applications
Sample project to connect Microsoft teams via (Power Automate) to Google Vertex AI project
Generate production-ready multi-agent AI projects from plain English. Supports CrewAI, LangGraph, WatsonX Orchestrate, CrewAI Flow, and ReAct with built-in sandbox verification, OllaBridge/Ollama inference, and enterprise wizard UI.
Self-hosted agent platform with inference routing across local and cloud hardware, multi-model benchmarking, NVIDIA Openshell sandboxing and STAMP'ed policy-governed agent runs.
A template for development with the open-autonomy framework.
ReAct Agent Builder framework from Delegasi
A lightweight starter kit for building and deploying AI agents with Microsoft Foundry Agent Service, featuring Azure integrations, Bicep infrastructure-as-code, and azd deployment for quickly going from prototype to production.
Agentic Framework examples for SAP Gen AI Hub via LiteLLM
Evaluating emerging Agentic AI frameworks
A compact, schema-first standard for the boundary between cognition and execution.
a groundbreaking multi-layered cognitive architecture for artificial intelligence (AI) that integrates several advanced concepts to create a unified framework for self-optimizing intelligence.
A completely front-end driven AI agent project, requiring no server resources.
Exoclaw agents on Temporal — durable AI agent execution
It provides an intent-aware orchestration system that routes user requests to appropriate development workflows (SDD, SDR, Support), manages AI agent integrations (OpenCode), and installs capability packs for persistent memory, documentation lookup, and skill-based task execution.
Projeto de alunos do 2º Semestre de Análise e Desenvolvimento da FATEC
Python wrapper for the OpenRouter API
Generate Anthropic Claude tool use schemas based on type annotations and function docstrings.
Community Plugins for Firebase Genkit.
This is a comprehensive large model service platform designed to facilitate rapid deployment and application of large model services in small and medium-sized enterprises. The platform mainly includes large model service and application modules, data management modules, and development documentation modules.
The #1 AI-native monorepo template — Next.js + Expo + FastAPI + LangGraph + Supabase with 90% code sharing
AI agent powered by MCP, LangGraph, LangChain, RAG, OpenAI, and PostgreSQL
Self-improving AI agents that run 24/7 on Claude Code. Discord, Telegram, Slack. One command setup.
Production-grade AI Agent orchestration scaffold based on Agno + AgentOS. Supports 8 model providers (OpenRouter/OpenAI/Google/Anthropic/Alibaba/Volcengine), multi-agent Teams, and conditional Workflows.
Haira: The programming language for AI agents.
Yet another AI agent framework — but this one's named after me, so it's automatically better.
Build a 100% local AI Agent which uses Google to research topics
The League of Agents (OpenLOA): An extensible orchestration framework for creating personalized AI agents with modular tools and custom interfaces. (智能体联盟 (OpenLOA):一个可扩展的编排框架,用于通过模块化工具和自定义界面创建个性化 AI 智能体。)
Explore Functions, Tools and Agents with LangChain along with LangChain Expression Language
Asyncio-native Actor framework for Python agent systems — supervision, middleware, pluggable mailbox
This project is a Recipe Builder solution that leverages Semantic Kernel and agentic AI. It includes multiple agents: the Recipe Builder Agent, the Vegan Substitution Agent, and the Gluten-Free Substitution Agent.
Simple Node.JS based AI agent
Python Library for using Arcade tools with the OpenAI Agents SDK
🐧 is currently a work in progress... Stay tuned!
Shared system prompts, tool definitions, and API provider management for macOS AI agents
🧠 Autonomous AI Assistant & Agent — where every action is constrained, governed, executed, and cryptographically receipted.
Community-driven repository of reusable OpenClaw agents and sub-agents with validation workflows, fixtures, and tests.
Build Rust CLIs that AI agents can discover, call, and learn from. No MCP server needed.
A pure Python implementation of ReAct agent without using any frameworks like LangChain. It follows the standard ReAct loop of Thought, Action, PAUSE, and Observation. The agent utilizes multiple tools, including Calculator, Wikipedia, Web Search, and Weather. A web UI is also provided using Streamlit.
🚀 Build and explore multi-agent AI workflows with ready-to-use projects for document serving, Q/A bots, and orchestration.
Composable Python SDK for building single-agent and multi-agent AI systems.
🔥 Open-source AI Agent Builder — Create, share, and run AI agents with MCP, tool-calling, and any AI provider (OpenAI, Anthropic, Gemini, Ollama)
Marketplace for AI agent skills and plugins - development, productivity, operations, marketing and beyond
Autonomous AI agents you deploy in 30 seconds across any channel. Zero-config CLI, 37 channel adapters, HEXACO personality and cognitive memory powered by AgentOS, five-tier prompt-injection defense.
HALO (Harness-Agentic Loopback Orchestration) — A 3-layer AI agent orchestration framework for TDD-based development with RTM-driven traceability
a methodology for autonomous projects that ship themselves (hands off)
An extensible, policy-minded agent harness in pure Rust. Any LLM via one trait. Concurrent tools, policy guardrails, session memory, eval harness, and TUI included.
A provider-agnostic Swift API for chat, embeddings, image generation, agents, and retrieval.
ManusClaw: The ultimate autonomous AI agent framework. Unleash self-reasoning CLI beasts to execute code, browse the web, and dominate tasks without limits. No GUIs, pure power.
TypeScript Agent execution-layer SDK. You write the model and tools, it runs the loop.
A declarative AI agent framework built on RuleGo
🪶 The C language implementation of LangChain
A Microsoft Foundry templateI reach for every time. It keeps evolving alongside new Microsoft announcements, but the structure always reflects practices I've found efficient and reliable.
A unified programming language for building production AI agents without tool fragmentation.
The open-source Agent alternative — 34 tools, local RAG (FTS5+vector+RRF), Prompt Caching, MCP/LSP/Skill/Hook, all in one cross-platform desktop app. Apache-2.0.
AgenticNET is an open-source, Azure-native platform for building, deploying and operating enterprise AI applications with .NET. It combines intelligent routing, RAG, reviewer loops, infrastructure automation and full decision traceability into a single production-ready platform.
Open Agent Toolset Protocol (OATP) - universal spec for AI agent tool discipline, structural instrumentation, and deterministic execution. Vendor-agnostic interop layer for available tools and the procedures that define tool operability.
The Agent Reliability Stack: fit, guard, snap, vet, cast. One landing page for all 11 npm + 6 PyPI packages.
基于生命周期钩子的轻量级 AI Agent 框架 — 插件即文件,全异步,零 SDK 依赖
A human–AI collaboration framework that works with LLM nature, not around it — natural language and purpose make RAG and agent orchestration unnecessary. Home of the Pang Principle.
Enterprise-ready platform for sovereign AI. Build custom agent profiles, manage skills and MCP integrations, share memory across users, and run fully isolated autonomous agents at scale
Bodhi — a local-first AI agent workbench in Rust: desktop app, Bamboo runtime, Jiandu shared memory, Nova computer use and Magpie IM bridge.
Goal-Oriented Action Planning for LangGraph
An Agentic Framework that forces System 2 thinking from LLMs and reduces Token Burn.
A hybrid AI assistant framework linking structural workflow engines and reasoning LLM agents through LangGraph-powered session control and task switching. 混合 AI 助手框架,通过 LangGraph 驱动的会话控制与任务切换,连接结构化工作流引擎与推理型大模型智能体。
gradio region:us
W-Agent 是面向 Python 开发者的开源 Harness 开发框架,借鉴 Spring 的依赖注入、切面与生命周期,用注解、配置或显式代码装配自己的 Agent 执行系统。
Ship enterprise-grade cloud agents with security, memory, telemetry, and highly accurate search that scales
Anthropic Skills + Structured Programming. For loops, control flow, full VM
One agent SDK, hand-ported to 8 languages — JavaScript, Python, Go, Java, C#, Elixir, Clojure, Rust — every port held to the same spec by a CI-enforced cross-port conformance suite, all eight at full tier. MCP · skills · native · HTTP · built-in · A2A tools behind one interface. Docs: https://muthuishere.github.io/toolnexus/
Ready-to-use AI agents for AgentsKit — shadcn-style: copy the source into your project. registry.agentskit.io
The React framework for building agents into real apps — one definition serves humans (streamed HTML, zero client JS) and agents (markdown, JSON, MCP), nothing duplicated. Web-standards core, deploys to Cloudflare Workers.
Composable Agent Infrastructure — HTTP/WebSocket Gateway, Persona Runtime, Semantic Memory, Real-time Vision, and BERT/VLM Inference in C++20
A TypeScript implementation of the Microsoft Agent Framework programming model, with semantic parity to the official .NET, Python, and Go implementations. Independent community project.
Agent orchestration toolkit for Rust (under development)
Foundgine lets callers express intent while your application decides what's allowed, safe, and executed
Reference implementation of Ratchet: a minimal hygiene recipe for self-evolving LLM agents (arXiv:2605.22148)
Persistent proactive self-improving AI teammates with memory, skills, and schedules.
Chat with AI agents to build, manage, and orchestrate custom tools, dashboards, and it's all powered by cats.
Local-first Agent OS — project management, agent orchestration, docs, memory, and developer tooling. Runs on PGlite. SaaS-ready.
Prolog Agent Framework, Reusable Agent Skills, MCP Server Pattern, Neurosymbolic AI, and Safe Multi-Engine Execution (Scryer, SWI, Trealla, Tau).
THE UNIVERSAL AGENT SKILLS LIBRARY
An autonomous AI Operating System for coding, automation, creative generation, and intelligent task execution.
AI transformation infrastructure. A self-hosted knowledge base, agent board and MCP connection for putting AI to work inside a business. Run it in-house, license it as a consultant, or have us set up your server and run it for you. Works with Claude, Codex, Grok or open-weight models. Apache-2.0.
An open registry of 76 fully specified AI agent skills — taxonomy, canonical schema, composer, governance model, and a fleet runner that deploys hundreds of agents against one objective and rehearses them against their own definitions.
An AI operating framework for agents and assistants to improve reasoning, decision-making, execution, and practical outcomes.
基于 TRSS-Yunzai 的 AI Agent 插件框架:LLM 对话·工具调用·长期记忆·MCP·工具进化 | A modular AI Agent runtime for TRSS-Yunzai with self-evolving tools
ARA — Agent Runtime Architecture: Java 21 framework for building autonomous AI agents and multi-agent systems. LLM integration, tool calling, deterministic I/O contracts, RAG and human-in-the-loop. On Maven Central (io.github.xmor).
Adapters required to use Nous Research Hermes 2 Pro as a function calling LLM
手搓 openclaw