MiroFish
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物
Category
Open-source tools, models, agents, and infrastructure for artificial intelligence.
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
Build, run and scale AI agents like API and microservices
An OpenAI-compatible gateway for hosted models, self-hosted inference, tools, and MCP servers.
An open-source proxy for agent-to-LLM, agent-to-tool, and agent-to-agent communication.
Build and run agents you can see, understand and trust.
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
An open-source framework for building, deploying, and experimenting with multi-agent applications and intelligent agent systems.
An open-source framework and SDK for building, running, and managing AI agents and agent platforms.
A lightweight Python framework for parallel, isolated, collaborative AI reasoning.
An open-source AI pair programming tool that runs in the terminal and helps developers modify, understand, test, and manage codebases with large language models.
AIGO Framework Studio is an open-source workspace for structuring and documenting AI governance activities throughout the AI system lifecycle. It provides dedicated workspaces for AI system inventories, governance classification, evaluation records, reviews and approvals, validation checks, risk and control management, monitoring plans, change and incident records, and assurance evidence. The project helps teams organize governance information, maintain traceable records, and support human review and accountability. Version 1 focuses on structured governance workflows and record management rather than claiming to automate compliance or independently certify AI systems.
Lightweight OpenHands CLI in a binary executable
claude-agent-sdk-python is an open-source project discovered through awesome-ai-agents.
claude-agent-sdk-typescript is an open-source project discovered through awesome-ai-agents.
A self-hosted LLM inference platform exposing Anthropic- and OpenAI-compatible APIs over multiple inference engines.
A modular Python framework for building AI agents and workflows from small composable components.
Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.
An open-source toolkit for fine-tuning and post-training language models.
An open-source platform for serving and deploying AI and machine learning models.
A collection of embedding and reranking models and tooling for retrieval and semantic search.
Agents that use the browser.
🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
The most Token-efficient open-source AI Agent
An open-source autonomous coding agent available as an SDK, IDE extension, and CLI assistant for building software with AI.
A retrieval model and toolkit for efficient neural information retrieval.
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
A self-hostable personal AI agent with vector memory, Composio tools, and Telegram.
An open-source coding agent available across the terminal, IDEs, and development workflows.
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
Soul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI, Telegram or More.
An open-source web crawler and scraping framework designed for AI and LLM workflows.
An open-source framework for orchestrating role-playing AI agents and building collaborative multi-agent workflows.
An open-source enterprise AI assistant with search, connectors, agents, and retrieval capabilities.
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
An open-source evaluation framework for LLM applications, agents, and RAG systems.
DeepSeek Harness: Everything is a Plugin.
Your Company Agentic Operating System
Dimensional is the agentic operating system for physical space. Command humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seamlessly with physical input (cameras, lidar, actuators).
Tools for programming and optimizing language-model applications.
An open-source framework for programming and optimizing language model systems using modular, declarative Python programs instead of manually crafted prompts.
Open-source, secure environment with real-world tools for enterprise-grade agents.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
A Python framework for building MCP servers and clients with a developer-friendly API.
An open-source web crawling and scraping platform designed for AI applications.
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
A self-hosted OpenAI-compatible LLM gateway with multi-provider routing, fallback, caching and guardrails.
Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.
OpenBitFun combines a high-performance agent runtime written in Rust with a polished desktop application. It pairs the depth of a Code Agent with open, general-purpose capabilities for work beyond software development.
An open-source testing framework for AI and machine learning models.
Google's open-source framework for developing, evaluating, and deploying AI agents and multi-agent systems.
An open-source AI agent that brings the power of Gemini directly into your terminal.
An open-source AI agent designed to automate software engineering and other development tasks through tools, integrations, and extensible workflows.
A data pipeline and transformation suite for building graph-based retrieval-augmented generation systems.
An open-source terminal coding agent for the Grok API with sub-agents and web search.
An open-source terminal coding agent supporting Grok and other LLM providers.
A lightweight open-source coding CLI powered by Groq.
A framework for adding validation and safety checks to LLM applications.
An open-source AI orchestration framework for building production-ready applications with retrieval, RAG, agents, pipelines, and large language models.
An open-source observability and monitoring platform for AI applications.
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
An open-source gateway that unifies multiple LLM providers behind an OpenAI-compatible API.
An OpenAI-compatible LLM router that selects providers based on cost, capability, privacy and health.
A Python library for extracting structured data from LLM responses using typed schemas.
An open-source AI assistant that dynamically generates tailored teams of AI agents based on your project requirements.
AI-powered personal assistant that can search, organize, and interact with your personal knowledge.
An open-source RAG-based tool for chatting with your documents. - Cinnamon/kotaemon
A Kubernetes-native platform for serving machine learning and AI models.
The batteries-included agent harness.
The batteries included agent harness.
The agent engineering platform.
An Open-Source Asynchronous Coding Agent
A visual platform for building and deploying AI-powered agents and workflows.
Open-source observability and evaluation platform for LLM applications.
A framework for building stateful, long-running AI agents and workflows with support for durable execution, persistence, human-in-the-loop interaction, and complex orchestration.
A tool for deploying LangChain applications as APIs.
Stateful agents that are like people, with memory, identity, and the ability to learn and adapt
An open-source platform for building stateful AI agents with persistent memory, identity, and the ability to learn and adapt over time.
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active - LibreChat-AI/LibreChat
A lightweight retrieval-augmented generation framework that combines graph structures with efficient retrieval.
A unified interface and proxy for calling hundreds of LLM providers through an OpenAI-compatible API.
A lightweight toolkit for pretraining, fine-tuning, and deploying large language models.
Python bindings for llama.cpp with APIs for running and serving local language models.
An open-source framework for building agentic applications and data-powered AI systems with tools for document processing, retrieval, indexing, RAG, and agents.
An intelligent inference router for LLM traffic with load-aware and cache-aware routing.
An OpenAI-compatible API gateway with semantic caching, RAG and token authentication.
A self-hosted LLM gateway and model router supporting OpenAI and Anthropic APIs.
A toolkit for compressing, deploying, and serving large language models.
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
A self-hosted AI gateway with OpenAI-compatible APIs, routing, retries and streaming.
A TypeScript framework for building AI-powered applications and agents with workflows, tools, memory, evaluations, and integrations.
A framework for building agents and workflows using the Model Context Protocol.
A proxy for Model Context Protocol servers and clients.
An open registry ecosystem for discovering Model Context Protocol servers.
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
A developer interface for inspecting and debugging MCP servers and tools.
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.
Microsoft's open-source framework for building AI agents and multi-agent workflows with support for orchestration, tools, state, and enterprise application patterns.
A programming framework for agentic AI
A reverse proxy and management layer for MCP servers with routing and lifecycle management.
Integrate cutting-edge LLM technology quickly and easily into your apps
An open-source platform for managing machine learning and AI development lifecycles.
Language model utilities built on Apple's MLX framework.
Apple's array framework designed for efficient machine learning on Apple silicon.
The official Python SDK for Model Context Protocol servers and clients
Model Context Protocol Servers
The official TypeScript SDK for Model Context Protocol servers and clients
Kimi Code CLI — The Starting Point for Next-Gen Agents
A lightweight implementation of graph-based retrieval-augmented generation.
An open-source toolkit for adding programmable guardrails to conversational AI systems.
The agent that grows with you
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
An open-source coding agent that runs locally and can use models, tools, shell commands, MCP, skills, and computer interfaces to perform development tasks.
A self-hosted AI interface designed to work with local and cloud-based LLMs.
A lightweight, powerful framework for multi-agent workflows
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
🙌 OpenHands: AI-Driven Development
A clean, modular SDK for building AI agents with OpenHands V1.
An open-source AI-driven development platform that enables AI agents to work on software engineering tasks and interact with development environments.
OpenTelemetry instrumentation for LLM applications and AI agents.
Open-source platform for evaluating and monitoring LLM applications.
Orkas is an open-source, local-first AI desktop app: a commander LLM directs specialist sub-agents, and runs your installed coding CLIs — Claude Code, Codex, OpenCode, OpenClaw, Hermes — as local sessions. Agents self-evolve via reflection and skill crystallization. BYO keys. macOS / Windows / Linux.
A framework for structured generation from language models.
A Hugging Face library for parameter-efficient fine-tuning of large models.
Open-source AI observability and evaluation platform for LLM applications and agents.
An open-source AI gateway for routing requests across large numbers of language and multimodal models.
A self-hosted gateway that routes and meters traffic across local LLMs behind an OpenAI-compatible API.
:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP. - PostHog/posthog
🚀 The fast, Pythonic way to build MCP servers and clients.
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Open-source testing and evaluation framework for LLM applications.
A Python agent framework from the Pydantic team for building production-grade AI applications with type-safe tools, structured outputs, dependency injection, and model integrations.
The first real AI developer
An open-source AI coding agent that lives in your terminal.
An evaluation framework for LLM applications with a strong focus on RAG evaluation.
An open-source RAG engine designed for document understanding and retrieval-augmented generation.
Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.
A distributed computing framework for scaling AI and Python workloads.
A self-hosted LLM gateway with intelligent routing, cost tracking and budget enforcement.
A self-hosted OpenAI-compatible LLM gateway with policy routing, rate limits and analytics.
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
A fast decision layer for routing requests based on semantic intent.
A Python framework for generating embeddings and training models for semantic search and similarity.
A fast serving framework for large language models and multimodal models.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity
Hugging Face's lightweight framework for building AI agents, with a simple architecture, code agents, tool calling, model flexibility, and Hub integrations.
The open source coding agent.
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.
An AI browser automation framework for building reliable browser agents.
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
An open-source SDK for building AI agents and autonomous workflows with Python and TypeScript, supporting multiple model providers, tools, MCP, and multi-agent patterns.
Run MCP stdio servers over HTTP streamable, SSE and SSE over stdio. AI gateway.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
An open-source research agent that uses language models and tools to autonomously work on software engineering tasks such as fixing GitHub issues.
Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]
NVIDIA's toolkit for high-performance large language model inference.
An open-source stack for building production LLM applications with observability, evaluation and optimization.
Hugging Face's toolkit for deploying and serving large language models.
OpenHuman is an open source agent harness with local-first memory, agent orchestration, and workflows
Open-source foundation of ToolJet AI - the enterprise app generation platform for internal tools, dashboards, business applications, workflows and AI agents. Build visually, from a prompt, or from Claude Code, Codex and Cursor over MCP 🚀 - ToolJet/ToolJet
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
NVIDIA's open-source inference server for deploying machine learning models.
A Hugging Face library for reinforcement learning and post-training of language models.
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
A self-hosted identity-aware AI gateway for OpenAI-compatible inference and authorized MCP access.
A toolkit for faster and more memory-efficient LLM fine-tuning and reinforcement learning.
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.
An open-source toolkit for evaluating, tracing, and monitoring LLM applications.
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
MiMo Code: Where Models and Agents Co-Evolve
An open-source inference platform for language, speech and multimodal models with OpenAI-compatible APIs.
Multiplayer agent harness for work.
A memory and context infrastructure platform for AI agents and applications.