Entornos de ejecución de agentes, frameworks de orquestación y aplicaciones impulsadas por LLM. Buscamos proyectos con un modelo de ejecución claro, ejecuciones observables y una documentación honesta de lo que el agente puede y no puede hacer.
497 repositorios en esta categoría
Recibe los mejores repositorios nuevos de esta categoría en el estudio semanal.
Claude Code skill for short films with no video model: 51 film styles, each a style prompt plus a demo film made entirely in code by Claude Opus 5.5 (incl. OPUSCAR 98 and the new Evidence Films). By Lemomo. · Opus5.5 x 51 种影片风格：风格提示词 + 纯代码样片 + 导演与技术指南（新增「实证影像」）
成人 NSFW 图像提示词编译器（Grok L1–L5，Flux / Pony / Illustrious / NAI / SDXL / Z-Image / Wan）。中文说明，英文提示词。
A native macOS companion for Draw Things: always-visible image and Moodboard inputs, a canvas you can draw on from an iPad (Sidecar), a local MLX LLM and plug-ins.
A self-hosted studio for generating images, video, and audio with diffusion models.
本地优先的全栈 AI 创作工作站：AI对话 · AI漫画 · 漫剧创作 · 写作台 · 知识学习五大模块；vLLM / llama.cpp / Transformers 多引擎本地推理，显存智能调度、舱壁隔离自愈、仅供学习使用，欢迎交流指正。（最新进度（除插件系统）受到协议限制，暂时无法提交到仓库）
PythonSin licencia detectadaCreado el Actualizado el mes pasado
Native macOS video editor that coding agents can drive: everything the UI does, Claude Code and Codex can do through the bashcut CLI or MCP server. Layered timeline, captions, voiceover, plugins.
OpenCardboard — local-first chat-to-edit AI video editor. Your footage never leaves your machine.
Local-first AI canvas and timeline. Any MCP agent. Open-source alternative to Higgsfield.
Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.
Lightweight, stateless privacy gateway for LLM APIs — redact secrets before OpenAI/Anthropic upstreams and restore them transparently in SSE and tool calls.
Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.
Agent skill for rigorous bug bounty report triage, validation, severity escalation, and submission-ready reporting.
ARTEX 한국어판 ·AI 기반 침해사고 대응 기능 추가 (upstream: Autumn-27/ARTEX, AGPL-3.0)
数据面具 Data Maskit — 专为大模型打造的本地隐私脱敏网关（请求自动打码，回复流式还原；支持 Cursor / Claude Code / Codex / Pi 等任意可配 Base URL 工具）
Blitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report.
Curated reverse-engineering tools and learning resources for binaries, apps, firmware, formats, and protocols.
PGX — Lightweight Postgres for AI agents. Written in Rust. Thousands of isolated databases in one runtime. 🐘
四十五门真实网课的模块合辑全书 + 思维导图复习笔记 + 逐字稿，全部由 Video2Book 从课程音频重构：518 册教材、603 篇笔记、2,286 份逐字稿，从逐讲精读到考前速查，笔记支持 Markmap / XMind 脑图导入。
Take your agent-built product live: hosting, database, domain, email, payments — on your own accounts. Open-source Agent Skill + zero-dependency Node CLI: detect → plan → approve → apply → verify. No GoLive account, backend or telemetry.
Learn to design an LLM wiki from first principles. Used as agent memory. Workshop with 3 exercises, open-source code, video, and slides. No coding skills required.
An AI + IDE WorkStation for DeepSeek & Ali Qwen harness, focus on your main work, review all the things, manage and control all the things, redefine the future IDE（Other model will support in 27Q2）
Manage upto 1000 agents using automations and workflows
Desktop-first, open-source (MIT) application for running parallel agents, and multi-step custom workflows triggered by schedules, webhooks or events from tools like Linear and Sentry, across your already-used providers.
让完全不懂技术的人拥有一台真正每天在干活的专属 AI agent ｜ Open-source consulting playbook: ship self-hosted AI agents that non-technical users actually use