Agent 框架

Open source virtual desktops for AI agents

Turn Webpage to LLM friendly input text. Similar to Firecrawl and Jina Reader API. Makes RAG, AI web scraping, image & webpage links extraction easy.

Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local video, image, music and voice generation. No telemetry.

A simple Python sandbox for helpful LLM data agents

AI-native SQL client for humans and agents. Query, explore, visualize, and open agent database work as editable SQL workspaces.

Home Assistant LLM integration for local OpenAI-compatible services (llamacpp, vllm, etc)

ICML 2026 | PALM@NeurIPS2026 Oral | Plug-and-play long-term memory for LLM agents

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution

Claude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.

Close the lid and walk away — every window, desktop and terminal on your machines, live in any browser. E2E-encrypted, no open ports, no client, no account.

AI-powered login automation. Uses Claude to classify login pages and Playwright to interact with them.

学习Agent开发的笔记，尝试让Agent从可用到可靠

A bot works with OpenAI GPT models to provide insights for your info flows.

[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models

All-in-one Web Agent framework for post-training. Start building with a few clicks!

Phi-3, -3.5, and -4 for Mac: Locally-run Vision and Language Models for Apple Silicon

[NeurIPS'26] Official Implementation for AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent(https://arxiv.org/abs/2602.03955)

GPU Profiler for AI agents

Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, Java

Agent-readable docs, verified examples, and skill manifest for @zapier/zapier-sdk

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

[ICML-2026] Official implementation of "SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience"

100+ curated Seedance 2.5 prompts with real video previews, plus an installable Agent Skill that optimizes prompts, creates storyboards, and generates videos via Seedance models.

Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.

Tactical AI Workspace Monitor & EDR

50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.

DeepEye: An Autonomous Data Agent System

MobileUse: an open-source mobile GUI agent for Android phone automation, AndroidWorld/AndroidLab evaluation, hierarchical reflection, and proactive exploration.

Bitbucket CLI with gh-like ergonomics

Bambu Lab AI (Bambu Studio AI): agent skill for 3D printing on Bambu Lab. Finds models on MakerWorld & Printables, generates or designs them in CAD, checks printability, hands them to Bambu Studio and reads printer/AMS status. For Claude Code, Codex, Cursor, Gemini CLI and any SKILL.md agent. Featured in 我的拓竹 Skill 大赏.

Alzeo is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Acer), into a private AI server in one command: measured model lanes, OpenAI and Anthropic APIs, and a local cockpit.

Agent that actually understands social platforms. Fast. Precise. Deep.

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

A multi-agent research system for the humanities and social sciences.

Govern: one Decionis verdict before a workflow step runs — a deploy, a migration, an infrastructure change, an agent's action — with a signed Decision Dossier of it. GitHub Actions, GitLab CI, Jenkins; shadow or enforce; no local policy engine.

🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models

From idea to object, and every version in between. Kiln is the open-source MCP server for 3D printing: AI agents (ChatGPT, Claude, Codex, Cursor, Gemini, Grok, Hermes Agent, or any MCP client) design, slice and print on Bambu Lab, Creality, Prusa, Elegoo, Klipper, OctoPrint and more. Git-style version control: branch, merge and undo your designs.

A 27-chapter hands-on tutorial for building an autonomous AI agent from zero in Python. Agent loop, tool system, memory, skills, MCP, multi-platform gateway, and self-evolution — inspired by Hermes Agent.

剧本分镜智能体（PenShot）：电影/动漫/短剧/小说→分镜片段→视频提示词。基于 LLM 通过 LangGraph+LlamaIndex实现任意格式剧本的自动解析，生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致，支持 MCP/REST API/Function Calls/A2A 集成。（LLM-powered text-to-video-prompt agent. Break scripts into Sora/Veo-ready shots with character consistency）

Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.

Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can explore it.

Agent-Sandbox is an easy-to-use, enterprise-grade sandbox platform for AI Agents — letting them securely run untrusted LLM-generated code, Browser use, Computer use, and deploy websites, among other tasks.

Open-source AI gateway for LLMs & AI agents, built in Rust. One OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock & more — routing, guardrails, caching, rate limits, observability.

Agentic AI 智能体开发实战

RAG ReAct Agent - A Retrieval-Augmented Generation system with ReAct (Reasoning+Acting) agent loop for intelligent question answering with multi-hop reasoning