Agent runtimes, orchestration frameworks and LLM-powered applications. We look for projects with a clear execution model, observable runs and honest documentation of what the agent can and cannot do.
315 repositories in this category
Get this category's best new repositories in the weekly survey.
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.
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
Myna Recorder — a Windows macro recorder you can read and edit. Image anchors, an auto clicker, an AI assistant that writes macros, Agent mode (computer use, for short jobs) and a screen watchdog.
Open-source AI operations workspace for meetings, knowledge, decisions, tasks, risks, workflows, and organizational memory.
Reusable Codex + Claude Code skill and plugin implementing Anthropic's AI-Native SDLC: Plan → Design → Build → Test → Deploy → Maintain, with human approval gates at every handoff.
CrewOS 是一个关于企业 Agent 产品形态的公开实验。 我正在尝试回答一个问题： 当 AI 已经能够完成任务以后，它能否进一步接住长期、复杂、持续变化的真实业务？ 这里会持续记录产品原型、设计实验、思考过程以及失败的假设。 如果你也在研究类似问题，欢迎一起讨论。
Open-source AI business orchestration platform for running governed AI agents across ERP, CRM, Microsoft 365 and other business systems.
Turn repeated Claude Code, Codex, and Cursor prompts into reusable slash commands. Local Python history extractor + Agent Skill.
Continuous improvement for AI coding agents: Penelopa analyzes real Codex and Claude Code sessions, finds repeated workflow patterns, and turns them into reusable skills, checks, prompts, and recommendations.
Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, deep research, content generation, vibe coding, browser automation, governance, and admin controls.
A curated list of open-source AI agent platforms: AI coworkers and teammates, agent builders and frameworks, workflow automation platforms, browser agents, and coding agents, with licenses.