Tag

Framework for building multi-modal AI agents that watch, listen, and reason over live video, pairing vision models (YOLO, Roboflow, Moondream) with LLMs like Gemini and OpenAI. Agents join calls in ~500ms and keep audio/video latency under 30ms.

GitHub Agentic Workflows

Write repository automation as natural-language markdown that compiles into deterministic GitHub Actions workflows running AI agents. Agents run read-only by default and write only via sanitized safe-outputs. Works with Copilot, Claude, Codex, or Gemini.

Bridges MCP-capable AI agents (Claude, Copilot, Cursor) to 150+ offensive-security tools, letting them autonomously run pentests, vulnerability scans, and bug-bounty workflows. A decision engine picks the right tools and adapts as findings emerge.

OpenAgents Control (OAC)

Wraps the OpenCode CLI with a plan-first workflow: agents propose a plan you approve before any code is written, and a ContextScout step loads your repo's existing patterns so output matches house style, not generic boilerplate.

Defines a predictable repository-level instruction file for coding agents, giving teams one place to document workflow rules instead of each tool inventing its own context format.

Makes the spec an executable artifact: you write intent in structured markdown and AI agents generate the plan, task breakdown, and code from it. A specify CLI and slash commands drive a constitution-plan-tasks-implement workflow across 30+ coding agents.

Wraps Claude Code in a loop that re-runs it until a task is done, gating every exit behind two conditions — semantic completion plus an explicit EXIT_SIGNAL — so it never stops early. Adds rate limiting and a circuit breaker for unattended, headless runs.

Wegent

Composes AI agent teams from a Ghost+Shell+Model formula: each Bot pairs a prompt/MCP/Skills Ghost with a Chat, ClaudeCode, or Dify shell and a model like Claude or DeepSeek. Bots form Teams that run as traceable Tasks, wired to GitHub and DingTalk.

Hello-Agents: 从零开始构建智能体

Teaches AI agent principles and practice through a structured Chinese curriculum, pairing theory with runnable code so learners can build, debug, and extend agent systems step by step.

LifeOS

Converts your goals and context into verifiable agent workflows that hill-climb your Current State → Ideal State across life and work. Bundles an ISA-based criteria system, persistent memory and a Pulse dashboard into a single AI-native skill designed to run inside an AI coding harness.

Dograh AI

Build and self-host production voice agents with a drag-and-drop workflow builder, real-time telephony integration, and pluggable LLM/STT/TTS backends. Docker-first with an optional managed cloud offering for teams that want faster onboarding.

深入理解 AI Agent：设计原理与工程实践

Open-source companion to a technical book that teaches how to design, evaluate and ship LLM-based AI agents — includes the full Chinese manuscript, community translations, chapter-aligned runnable example projects, and reproducible evaluation harnesses.