Category · 473 repos
AI Agents
Autonomous agents and agent frameworks that plan, use tools and finish tasks on their own. Ranked by star velocity over the last 24 hours.
Showing 301–350 of 473
Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.
An autonomous agent for deep financial research
A free AI agent & toolbox for Android | One-stop Android AI agent & toolbox
A lightweight desktop app to manage, sync, and organize AI agent skills across 50+ coding tools — Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀
Open-source, self-hosted MCP gateway: turn any REST/OpenAPI, SOAP, GraphQL, OData or SQL API into MCP tools for Claude, ChatGPT & Copilot. 262 connectors incl. SAP S/4HANA & Business One, ERP, e-commerce.
Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Feishu, DingTalk, Telegram, WhatsApp and H5 access.
Android AI agent app. Kotlin + Rust via UniFFI.
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursively self-improve through agentic workflows.
Python implementation of coding agent core mechanisms, with architecture comparison across Claude Code / Kimi Code / Codex
Lightweight Codex/Claude loop harness with strict evidence gates.
Free MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & desktop automation, built in Rust.
Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.
Agent-driven media library for your cloud drives (Quark 夸克 / 115 / 光鸭 GuangYa / 123网盘 / 天翼 Tianyi)
Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.
The official Lark/飞书 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.
AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.
A genuinely good terminal
Aixle Flow — orchestrate coding agents through durable, inspectable workflows.
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications.
Zhàzhàsū Cybersecurity · DeepSeek Harness: an open-source framework that puts penetration testing into an AI Agent. What is it? DeepSeek Harness is a plugin-based AI Agent runtime framework—here, “everything is a plugin.” Built on Cordis, it splits sessions, tools, LLMs, sandboxes, and skills into independent capabilities that can be combined like building blocks. This project comes with 103…
Agentic DFIR
Free large-model API, supporting free calls to leading models such as GPT and DeepSeek, with 10,000 free credits refreshed daily! Paid pricing is also just 10–20% of the official price!
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree
Open reconstruction of Shopify's Helix checkpoint-and-gate agentic coding workflow as a Claude Code skill pack. No signup, no paywall.
The bioinformatics agent desktop for clinicians and wet-lab scientists — built on DeepSeek Harness. One-click installers, a skill store, offline mode.
Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what it finds. MCP both ways: plug in any MCP server as a tool, or drive RedAmon from Claude Code or your o
A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Coding Agent, Tmux alternative
A sophisticated AI chatbot application built with Next.js, featuring Koa AI Agent with comprehensive Koasync knowledge, secret training capabilities, and intelligent search through GitBook documentation.
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
The MCP server for Azure DevOps On-Premise (TFS), connecting your AI agents with DevOps capabilities.
Async Python client for the Model Context Protocol with interactive CLI and reactive Web UI, connecting AI models to MCP servers via stdio and SSE
Infrastructure for continually self‑improving agents
AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.
Agentic RL Training at Scale
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.
Personal software factory built on OpenHands: agents implement, test, review, and publish draft pull requests.
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
OpenABCode is a coding agent that dynamically routes development tasks to the best-suited models
CrewMeld — Enterprise AI Digital Workforce Platform. Manage AI employees like real team members. Visual SOP orchestration, 13 LLM providers (including China-native models), 8+ messaging channels(WeCom/DingTalk/Feishu/Telegram), knowledge base with RAG, and full private deployment support. Built with
Continue Codex App sessions from a phone, tablet, or computer browser, compatible with official login, APIs, and custom model services. Self-hosted browser access to your existing Codex chats, with local/SSH sessions, approvals and notifications.
A visual workbench for Claude Code (web + desktop), also able to drive Codex / Gemini CLI / Qwen / OpenCode and other CLI agents · A GUI workbench for Claude Code and other CLI agents
Official Tonghuashun A-share financial data service, providing real-time stock quotes, historical market data, financial statements, indices, sectors, limit-up data, and more, for AI Agents, quantitative research, and application development; supports API, MCP, CLI, and Python. Official Tonghuashun (HiThink) A-share financial data service providing real-time and historical stock market data…
Open-source MCP servers that let AI agents operate real lab instruments, with safety limits, read-only modes, audit trails, and a simulator for every instrument.
Automated Benchmarking of LLM Agents on Real-World Software Security Tasks [NeurIPS 2025]
AIOS: AI Agent Operating System
Agents Office v3 (Beta) — a headless office where AI agents do real work
n8n skillset for Claude Code to build flawless n8n workflows