AI Agent Framework

Connect any AI agent to Slack, Teams, and WhatsApp with the Channels SDK

an ambient intelligence library

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure

OpenAgents - AI Agent Networks for Open Collaboration

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications

A Python SDK for Vertex AI, a fully managed, end-to-end platform for data science and machine learning

Build realtime multimodal AI agents with Node.js

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid

notebooklm-mcp-cli is an open-source GitHub project focused on MCP and tool-calling integration, developer-centric engineering workflows

OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving

An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides

Give your AI agent an @address in the AI agent network to discover matches and start meaningful conversations

Give AI agents 31 web tools through one MCP server

Run and coordinate coding agents on an infinite canvas

Run multiple CLI coding agents on Mac and orchestrate sessions through a local API

Build Mac work automations and orchestrate coding agents across isolated worktrees

Multiplayer terminal session sharing for Claude Code, Codex, and other CLI coding agents

Developer toolkit that lets AI understand document structure and edit rich-text documents in place

FlutterFlow macOS collaborative project space where humans, terminals, dev tools, and AI agents work on one canvas

Headless iOS release pipeline for AI agents to build signed releases, push TestFlight builds, and submit to the App Store

Open-source AI workspace for building, deploying, and managing agents and workflows

Build Chrome extension code, manifests, and packaging files through AI chat

Google CLI and skills package that lets coding agents scaffold, evaluate, and deploy Google Cloud agents

EU-hosted OpenAI SDK-compatible AI agent gateway with 300+ models and governance controls

Open-source TypeScript runtime for self-organizing AI agent teams

Low-level agent orchestration framework from the LangChain ecosystem for controllable, persistent, reliable agents

Open-source framework for quickly building LLM applications and AI agents with any model provider

Open-source AI data framework for documents, data connectors, RAG, workflows, and agent applications

Open and enterprise platform for building, deploying, and managing multi-agent workflows

Microsoft open-source programming framework for agentic AI, multi-agent applications, and conversational workflows

Official OpenAI Agents SDK with tools, handoffs, guardrails, sessions, MCP, and tracing

Type-safe Python agent framework from the Pydantic team for structured outputs, tools, and multi-provider models

Open-source visual agentic systems development platform for AI agents, RAG, and LLM orchestration

Open-source TypeScript AI agent framework for building, orchestrating, and observing agents with tools, memory, RAG, workflows, and VoltOps

AI agent skills management platform for team creation, review, distribution, versioning, and audit

Behavioral infrastructure API platform that gives AI agents social intelligence

Open-source homeserver OS with a built-in AI agent

Build Claude Code-style web agents with UI, voice and memory. No-code workspace to add Skills + MCP integrations and deploy instantly

Agent37 offers managed OpenClaw hosting so users can launch dedicated agent instances with full terminal access in seconds

Spine is the world's first truly agentic platform designed to manage and orchestrate the next generation of AI

Open-source AI agent harness built with humans in mind

Spawn coding agents that run infinitely in the cloud with AI SDK, Gateway, Sandbox, and Workflow SDK

Agent harness framework built with LangChain and LangGraph

Open-source autonomous agent framework for multi-role AI systems

Open-source AI agent assistant with multi-IM and multi-LLM support

LLM-powered agent runtime with dynamic DAG planning and concurrency

Cockpit is the operating system for AI agents with native file system, infinite memory, and cloud orchestration

Imbue builds AI-era developer products for running parallel agents safely in containers with rapid environment switching

Superset runs 10+ coding agents in parallel on your machine so teams can keep shipping while tasks execute concurrently

Build AI agents with natural language, package them in branded client portals, and charge monthly subscriptions

MuleRun is the AI agent that gets work done

Beezi AI is an orchestration hub for AI software development with smart ticketing, model routing, and usage-cost analytics

BAND is an interaction infrastructure layer that enables governed real-time collaboration between distributed AI agents and humans

Agentic coding suite that combines multiple agent system with AI code review and AI agent orchestration

InsForge is the backend built for agentic development, offering primitives AI agents need to build fullstack apps that scale

Secure and elastic infrastructure for running AI-generated code

Composio offers just-in-time tool calls, delegated auth, sandboxed execution, and parallel runs across 1,000+ integrations for AI agents

Enterprise MCP server runtime and management platform for agents

MCP integration platform focused on reliable and scalable tool usage for AI agents

Integration layer for AI agents to call OpenAPI, MCP, GraphQL, and custom JavaScript functions in a secure runtime

Jentic Mini is a free, self-hosted execution layer for AI agents to access real APIs safely with encrypted credentials and scoped permissions

Cloud runtime for AI agents that decouples memory, keys, and skills from agent engines

Platform for building, shipping, and running AI agents from prototype to production

Platform to compose, run, and automate multi-step AI developer workflows

Cross-agent messaging for CLI agents such as Claude Code, Codex, and Gemini CLI over SQLite

Fetch.ai agentic economy ecosystem and discovery infrastructure for autonomous agents

Browser action layer for AI agents to extract live web data, take browser actions, and complete real web tasks end to end

Visual meta-harness for developers and agents that uses drawing-style specs and tests to clarify and validate agent behavior

Open-source VanillaJS agent UI library for embedding streaming, themeable AI chat widgets with tool use and zero framework dependencies

Open-source web terminal multiplexer for managing multiple coding agents

Deploy a managed background agent from one coding-agent prompt

Cloud infrastructure for AI agent tools, functions, environments, and integrations

Open-source unified interface for running Codex, Claude Code, Hermes, and other agent harnesses on your infrastructure

Team platform for publishing and governing AI skills and MCP servers

Medley plugin for coordinating multi-agent Claude Code missions

Marketplace for agent apps that run inside Claude

Google DeepMind embodied-intelligence model connecting perception, reasoning, dexterous manipulation, and whole-body robot control

Cloud service for launching long-running Claude Code, Codex, and other AI agents on demand

Shared cloud canvas where teams and multiple AI coding agents work in one repository

Tag and invoke any ACP agent from Slack, Telegram, Discord, and GitHub

Manage agent skills, tools, context, and permissions in your own Git repository

Configure MCP servers once and share one local gateway across every AI agent

Local, visible browser for AI agents with policy gates and approval controls

Turns existing machines into a multi-provider fleet of AI agents

Lets AI agents investigate and operate existing cloud and Kubernetes infrastructure under controls

Durable AI chat backend with no timeouts, resumable streaming, and recovery across refreshes

Local harness orchestrating CLI agents such as Claude Code and Codex as persistent personal and team clones

Unified API for live search, page fetching, cloud browsers, and multi-step web automation for AI agents

Local-first ownership layer for agentic work that keeps automations, workspaces, and agent graphs under user control

Manage Marble CMS posts, fields, content, and media directly from Claude, Cursor, and Codex

Claude orchestrator that gathers Jira, Slack, GitHub, and Notion context for delivery workflows

Route each agent step to the lowest-cost model that clears its quality bar using full-trajectory context

Generate, host, and secure MCP servers for databases, APIs, third-party apps, and files using natural language

HIPAA-compliant data backend for healthcare AI apps with MCP connectivity between agents and business databases

The cloud for AI agents

Bring any AI agent into Slack, Teams, and Discord

A multi-agent marketplace where proof decides who wins

A spatial canvas IDE for AI coding agents

An open-source AI gateway that turns traffic into a better model

Behavioral learning that makes AI agents better over time

An AI agent that connects to tools and gets real work done

Discover Harness plugins and use a hosted agent workspace

Use a dedicated model for small decisions inside agent harnesses

Simulate an AI-agent community reacting to hypothetical scenarios on Mac

Ship AI agents in minutes with agent-native infrastructure

Turn open-weight models into downloadable AI applications

Build reusable bots on top of existing coding agents

Build, govern, and scale enterprise AI agents on Google Cloud

Give existing AI agents an open-source desktop face, voice, and entry point

Add hosted cloud AI agents to hardware or software products through one API

Route AI agent tool calls through approval rules before execution

Keep governed agent memory locally with evidence-aware recall

Give multiple AI agents a shared memory repository

Turn team rules and skills into reusable agent configuration

Open-source self-hostable runtime for managed AI agents with Docker sandboxes, REST/SSE APIs, MCP tools, and encrypted vaults

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10

TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML

The agent that grows with you

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Semantic version control — entity-level diffs, blame, and impact analysis on top of git. 26 languages via tree-sitter. Built for coding agents

SPEC-First Agentic Development Kit for Claude Code — 24 AI agents + 52 skills with TDD/DDD quality gates, 16-language projects, 4-language docs. Go CLI, zero deps

Development platform to debug, chat, inspect, and evaluate MCP servers, MCP apps, and ChatGPT apps

High-performance AI coding agent CLI written in Rust with zero unsafe code

Lightweight coding agent that runs in your terminal

Warp is an agentic development environment, born out of the terminal

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction

ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI

A native Emacs buffer to interact with LLM agents powered by ACP

A curated list of awesome AI tools, libraries, papers, datasets, and frameworks that accelerate scientific discovery — from physics and chemistry to biology, materials, and beyond

🇹🇼 Let the world fully understand Taiwan | An open-source, AI-friendly knowledge base about Taiwan

The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthroughs here. Fully peer-to-peer. Join from your browser or CLI

Enterprise AI bastion host for secure AI API and MCP access, with unified proxying, RBAC, audit logs, rate limiting, and cost tracking across OpenAI, Anthropic, Gemini, and self-hosted LLMs

A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files

The sandbox agent framework

Unified TUI and CLI to index and search your local coding agent session history across 11+ providers (Codex, Claude, Gemini, Cursor, Aider, etc.)

CLI for Apple's Messages.app so your agent can send and receive text messages/iMessages

The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills

Run production apps without thinking about infrastructure. On your server or ours. Fully agentic

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities

Garry's Opinionated OpenClaw/Hermes Agent Brain

Production-ready platform for agentic workflow development

From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack

Orchestrate coding agents remotely from your phone, desktop and CLI

An open-source AI agent that lives in your terminal

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running

The AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad

omo; the best agent harness - previously oh-my-opencode

Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration

Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compound insight commands

Platform for AI-powered software engineers

Orchestration-builder SDK for multi-agent coding workflows

Tool to build & run portable, lightweight, self-contained virtual machines

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integration, and native Claude Code / Codex Integration

Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents

The coding agent built for the web. stagewise is a purpose-built browser for developers with a coding agent built right in

GitHub Agentic Workflows

Unofficial Python API and agentic skill for Google NotebookLM. Full programmatic access to NotebookLM's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents like Claude Code, Codex, and OpenClaw

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes

Infrastructure for supervised, self-improving agent organization. Feishu/Telegram mobile phone runs Claude Code or Kimi Code (dual engines, two native subscriptions are used directly), sharing memory, Agent factory, scheduled tasks, and communication bus

The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetings, and more, with 200+ commands and 20+ AI Agent Skills

Asterinas aims to be a production-grade Linux alternative—memory safe, high-performance, and more

Infrastructure that's powering E2B Cloud

Coding Agent Harness

The Future of Data Engineering — A CLI SQL client for the modern data stack, enabling AI-native context engineering for data

A multi agent desktop application built with Rust and Tauri

Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read

Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source

:orange_book: Subscribe to the latest front-end technology articles based on RSS and automatically classify them

Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 11 quality gates

Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat

Multi node agent orchestrator - build faster and better

A Unified Virtual Filesystem For AI Agents

The Application Engine for the AI Era. A multi-threaded, AI-native runtime with a persistent Scene Graph, enabling AI agents to introspect and mutate the living application structure in real-time

Fork() for AI agent microVMs. Spawn 100 children in ~100ms from a warm parent; BRANCH a live VM in ~150ms. KVM-isolated, snapshot CoW

Capability-based agent runtime with fine-grained policies . Brokering access directly within the agent's operating context, with zero setup and zero latency

Kimi Code CLI is your next CLI agent

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows)

425 plugins, 2,810 skills, 200 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI package manager

Copy any UI element for your agent

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

MaaEnd Assistant: An automated tool for "Arknights: The End" based on visual AI

Deep dive into Claude Code's source code— learn from the best agent implementation out there

Open-source local workbench for multi-agent software development

Framework to build resilient language agents as graphs

Octos - Agentic Operating Systems

LeanCTX — the Context OS for AI development. One local binary that compresses, remembers, routes, and verifies every token between your code and the model. 63 MCP tools, 10 read modes, up to 99% token savings. Works with Cursor, Claude Code, Copilot, Windsurf, Codex, Gemini

📜 Entire CLI hooks into your Git workflow to capture AI agent sessions as you work. Sessions are indexed alongside commits, creating a searchable record of how code was written in your repo

The Agent-Ready Backend for MongoDB

from vibe coding to agentic engineering - practice makes claude perfect

A clean, modular SDK for building AI agents with OpenHands V1

Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and engineering standards

Free, extensible, privacy-focused desktop AI agent

Web search, scraping, and interaction context for any MCP client

Build a company AI operating system on Cloudflare