Search

Enterprise cybersecurity AI agent system — 7 specialized agents with LLM orchestrator and 5-layer architecture

Task-delegation AI agent with multi-agent orchestration, research pipeline, and planning engine

The scientific thinking protocol for AI agents — falsify before you believe. 5-stage falsification skill (axioms → hypothesis → adversarial → verify → converge) for Codex, Claude Code, Cursor, Gemini CLI & 20+ agents. Dual-model evals 26/28. 五段式科学思维协议：公理

CLI tool and AI Agent skill for Hi3D API (hitem3d.ai): generate 3D models (GLB, OBJ, STL, FBX, USDZ, 3MF) from images, reliefs, model splitting, and multicolor

CLI tool and AI Agent skill for Hi3D API (hitem3d.ai): generate 3D models (GLB, OBJ, STL, FBX, USDZ, 3MF) from images, reliefs, model splitting, and multicolor

Install the Atoll project management integration for Codex CLI

Embeddable voice agent widget for AI voice conversations

Java-only semantic code intelligence — build a queryable knowledge graph of a Java codebase for AI agents and developers. 100% local.

A local-first AI agent for your terminal. Think. Remember. Act. Observe.

Xiao Zhi CLI（小智）：一个简单的终端 AI Agent，支持 OpenAI 兼容接口（Ollama / DeepSeek / Kimi 等）和工具调用

A coding-agent terminal for the GLM engine — streaming TUI, tool calls, checkpoints, quota insight; drives your installed ZCode runtime on your own Coding Plan.

Local chat UI for OpenAI-compatible and GigaChat models with persistent history

Static analysis scanner for AI-agent production risks