AI channel
AI agents

Open-source AI agents

An AI agent is a program that uses a language model to decide what to do next, calls tools such as a browser, a code interpreter or an API, and repeats until the task is done. The projects here range from frameworks for building your own agents to finished agents that write code, browse the web or run business workflows.

How to choose

Compare three things. Which models it can use: a single provider, or any OpenAI-compatible endpoint including local ones. How it limits what the agent may do: sandboxing, approval steps and permission lists. And whether it keeps memory between steps and sessions. An agent that runs code or shell commands should run in a sandbox, so check that before giving it access to your machine.

Most-starred projects

3,289–3,312 of 4,274
vibeeval

vibecosystem

★ 531

AI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution.

C#
★ 531

54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.

Python
ARCANGEL0

EVA

★ 530

EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysis, and multi-backend AI integration.

Python
★ 530

Devnors Data - Python SDK: 接口,数据API,裁判文书,Legal Case,法律法规,法条,Law Article,企业工商,Company Registry,企业年报,Annual Report,税号开票,Tax Invoice,失信核查,Dishonest Judgment Debtor,被执行人,Enforcement Debtor,关键词指数,Keyword Index,微信指数,WeChat Index,热搜榜,Hot Rank,微博热搜,抖音热搜,快递查询,Express Tracking,快递公司编号,统一查询,/v1/data/query,API Key,MCP,AI Agent

Python
★ 530

Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images

mco-org

mco

★ 530

CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.

Python
★ 530

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

Python
★ 530

Customer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.

Go
★ 529

🪝 Claude Code hooks + an installable plugin marketplace: safety, cost, observability, productivity.

JavaScript
nickvasilescu

hermes-desktop-os1

★ 529

Hermes Desktop - OS1 Edition: native macOS workspace for Hermes Agent on Orgo cloud computers and SSH hosts

Swift
only-cli

oc

★ 529

Turn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.

JavaScript
concierge-hq

concierge

★ 528

🚀 Universal SDK for building next-gen MCP servers

Python
★ 528

A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.

JavaScript
kentjuno

ainovel-cli

★ 528

CLI sáng tác tiểu thuyết AI đa agent — Bản tiếng Việt của voocel/ainovel-cli

Go
privatenumber

mac-ocr

★ 528

macOS CLI for OCR and searchable PDFs using Apple's Vision framework

Swift
stormzhang

token-tracker

★ 528

Claude Code & Codex 本地 token 追踪 — 状态栏（Codex 业界首创伪 statusline）、GitHub 风格热力图、多模型成本分析。 | Local token tracker for Claude Code & Codex — status line (industry-first Codex faux statusline), GitHub-style heatmap, multi-model cost analysis

Python
★ 527

Official Implementation for EMNLP 2024 (Main Track, Oral) "AgentReview: Exploring Academic Peer Review with LLM Agent."

Jupyter Notebook
★ 527

An in-the-wild benchmark for AI agents in the production harness.

Python
★ 527

A general framework for distilling human-created multimodal resources into reusable, executable skills that AI agents can browse, compose, and run, validated across diverse domains including web, PowerPoint, Excel, Blender, CAD, Unreal Engine 5, and REAPER-based music production.

Python
agencyenterprise

PromptInject

★ 526

PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

Python
★ 526

A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context — EARS acceptance criteria and a runnable verify command on every build step. 14 project shapes, greenfield and brownfield. EN/ES.

JimLiu

baocut

★ 526

Open-source Agent Skill that drives the BaoCut macOS app CLI (transcribe · subtitle · translate · cut) from Claude Code, Codex, and other agents

JavaScript