Single Agent Frameworks141 / 464 projects

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

AI Agent Framework, the Pydantic way

Open-source Agent Operating System

Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

Multi-Agent Harness for Production AI

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

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.

Build autonomous AI agents in Python.

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, DeepSeek, or local models).

IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.

Build distributed, production-grade, long-running agents.

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

A simple yet powerful agent framework that delivers with open-source models

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

A framework-agnostic, git-native standard for defining AI agents

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.

🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.

Ship your code, on autopilot. An open source agent that lives on your machines 24/7 and keeps your apps running. 🦀

A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code

The control plane for AI coding agents.

Personal AI desktop agent for Windows, macOS, Linux, Android & iOS. Set a goal, it works on its own. Teams (pair two desktops, agents + humans), Agent2Agent, Workflows, Codework, multi-agent orgs, desktop + browser automation. 15+ AI providers, BYOK. No Docker, no terminal. Agent Skills (SKILL.md). Migration importer. Recurring autonomous tasks.

Standards for building agents, better

AI video agents framework for next-gen video interactions and workflows.

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

The agent framework where every run is durable, replayable, and resumable by default.

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.

Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.

🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.

Search, understand, reproduce, and improve an idea with ease

PhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference.

LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. Scheduled tasks support.

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

Waku Waku! Waku agent is your personal AI agent, on your own laptop, in code you can read in an afternoon — harness + loop + memory + eval

Self-hostable channel-native AI teammate for Slack. Open source alternative to Claude Tag. LLM-agnostic.

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared memory, and multi-agent evolution. Accepted at COLM 2026.

The foundation layer for agentic intelligence.

Blades is a Go-based multimodal AI Agent framework.

Agents daemon that hides nothing

Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.

Repeatable agentic engineering. The workflow layer that turns AI coding agents into a disciplined factory: durable specs, fresh-context workers, adversarial cross-model reviews, receipts. Everything in your repo, zero dependencies. Claude Code · Codex · Cursor · Droid.

Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.

The .NET library to build AI agents with 30+ built-in connectors.

The AI agent with a wallet — spends USDC autonomously to get real work done. Apache-2.0, TypeScript.

TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.

Daydreams is a set of tools for building agents for commerce

The most autonomous agent framework. No approval loops. No babysitting. Configure once, forget forever.

The most autonomous agent framework. No approval loops. No babysitting. Configure once, forget forever.

面向 OA、ERP、CRM、工单等企业系统快速构建智能体，让 AI 在权限、审计与治理约束下安全调用真实业务能力。Build agents quickly for enterprise systems such as OA, ERP, CRM, and ticketing, enabling AI to safely call real business capabilities under permissions, audit, and governance controls.

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

A fast and minimal framework for building agentic systems

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).

A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.

Make AI actually work for you - A personal agent that writes its own tools and repairs itself.

AutoHarness: Automated Harness Engineering for AI Agents

Agent Framework Samples - showcasing ways in which agent framework can be utilized.

A Production-Ready Framework for Building Composable AI Agents

Build AI agents that run for hours, not seconds. Async-first Python harness: auto context-compaction, cost budgets & death-spiral guards, persistent cross-session memory, self-evolving SKILL.md, /goal long-task loop, 40+ tools, 20+ models, MCP/ACP. Ships a CLI + Web Gateway out of the box.

Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration.

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

Build, test, and deploy intelligent AI agents the Laravel way

Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).

A framework for autonomous economic agent (AEA) development

Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbol-aware edits, semantic search, code health, fast grep/glob, bash compression, background tasks, PTY.

An agent design team you control: 10 agents that run an inclusive design process while you direct.

Record, replay, and improve AI agents in production, built on ZenML

Open-source Claude Managed Agents API implementation and self-hosted Claude Tag-style agent runtime. Drop-in compatible; runs on Cloudflare Workers/Durable Objects or Node.js. Apache 2.0.

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider, OpenHands, DeerFlow. Companion to Designing AI Agents (Manning) by Jia Huang.

SuperNova is a Windows-first desktop AI Workbench that turns chat into traceable tasks. It combines a Tauri + React Workbench, Rust Product Runtime, typed protocol, and Process Kernel so actions can produce visible artifacts, runtime receipts, replayable evidence, and controlled workspace execution.

Trend-to-Video Agent Framework for publish-ready short video packages

AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).

The AI automation platform, self-hosted. Describe the job in chat and LiveContext builds it: readable workflows, scoped AI agents, and small apps your team uses. Chat, Workflow, Agent and App on one canvas.

DSPy Go implementation

Deploy intelligence. Open-source infrastructure for AI agents in production.

GBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.

A web dashboard and runtime for orchestrating AI coding agents

Minimal typescript agent framework that keeps it simple and gives you control - no BS

Explore the must-have external ready-made toolkits to integrate with your AI agents built with Python and TypeScript

The agent OS that evolves itself.

Ultimate Multi-Agent OS for Autonomous AI NPCs 2026

Multi-Agent AI Task Orchestrator 2026

Multi-agent AI scientist that turns experimental data into > publication-ready research papers.

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

The local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.

An open-source Digital Worker platform for reliable execution and continuous co-evolution.

The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) .

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers

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.

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

A general-purpose Python framework for building LLM agents and multi-agent systems. "Four lines of code, an agent with memory."

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

Mozaik is a TypeScript runtime for concurrent AI agents

A Python-based framework for building multi-agent systems with LLMs. Currently in pre-launch alpha.

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.

Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate agents that can do everything a human can do.

Open-source enterprise AI workforce platform — containerized roles, declarative skills, MCP tools, policy-driven security, K8s-native scheduling

Reliability harness for long-running OpenClaw agents: persistent state, strict task contracts, scheduled execution, and external validation.

An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation.

A multi-agent event planning workflow built with Microsoft Agent Framework - combining Semantic Kernel's enterprise orchestration with AutoGen's multi-agent patterns.

Adaptive Agentic AI Reasoning using Microsoft Agent Framework -- Join the Discord for suggestion or support ! https://discord.gg/ebgy7gtZHK

Open-source voice agent OS. Rust runtime, AI-driven builder, sub second latency. Self-host everything.

Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.

一个多智能体协作应用平台，支持多策略 Agent 调度、多工具编排、RAG 检索增强、会话记忆与执行过程持久化，能够按业务场景动态组织多智能体分工协作，完成复杂任务拆解、工具调用与结果汇聚，提升运维和分析场景的自动化与智能化水平 项目wiki：https://zread.ai/OWWZO/ai-agent

Modular Python SDK and monorepo for AI agents, LLM integrations, tools, parsers, embeddings, vector stores, and extensible application workflows.

Constitution-first AI orchestration: one Charter (YAML) defines mission, budget & rules. CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP. Think. Audit. Execute.

self-extending sandboxed agentic harness. a loop, two tools and an llm

Lilium AI: The ultimate personal AI agent framework for autonomous computer control. Featuring browser automation, shell execution, and multi-channel integration (WeChat/Telegram/Discord).

AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.

Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

'Personal AGI' that thinks on its own. Autonomous cognitive cycle, earned autonomy, 60+ tools. It decides what to do without being told.

AI-powered browser automation for Go — describe tasks in plain English, let the agent handle the clicks.

Teleton: Autonomous AI Agent for Telegram & TON Blockchain

An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.

14 AI executives powered by legendary minds (Musk/Buffett/Simons/Feynman) — deploy your virtual C-Suite in one git clone.

🐕 Self-hosted security-first AI agent · 28 providers · 11 chat channels · WebUI · 3-level memory · task-schedule · automation · skills · MCP

EdgeCrab 🦀 A Super Powerful Personal Assistant inspired by NousHermes and OpenClaw — Rust-native, blazing-fast terminal UI, ReAct tool loop, multi-provider LLM support, ACP protocol, gateway adapters, and built-in security hardening.

A TypeScript Agent Framework Driven by Tool Invocation

MOTO Autonomous ASI Deep Research Harness by Intrafere - creative novelty-seeking researcher with autonomous Lean 4 proof generation. For S.T.E.M. users; run for days at a time once pressing start - no interaction needed! Agents working in parallel from either local host LM studio, OpenRouter, OAuth or all 3. No internet needed. Star us for more!

The composable standard reasoning agent

Built for OpenClaw and beyond, Chat Selfie lets your AI Agent send emotional selfies in every conversation, with mood-aware replies, heartbeat pushes, and flexible image generation.

Autonomous AI Company OS — 14 AI agents loop 24/7, ship real software

Multi-agent AI framework that writes full-length novels with persistent story state, a deterministic continuity engine, and a five-role editorial pipeline.

Multi-model AI agent runtime. Define agents in YAML, connect 6 LLM providers, orchestrate with ReAct/Plan&Execute/Fan-Out/Pipeline/Supervisor/Swarm patterns, and deploy as REST/WebSocket API with RAG, memory, MCP tools, guardrails, and OpenTelemetry observability.

A terminal-first AI coding agent. Open-source, observable, and built for developer control.

Autonomous AI agent for Instagram — generates reels, carousels, memes, quote cards and posts them on autopilot. Free-tier LLM router, commercial-safe licences, 8-feature anti-detection layer, 671 tests. Single VPS deploy.