Search

Compound-path and cross-release analysis of what an AI agent is permitted to do

移动端AIAgent智能助手

AI智能体聊天卡片组件

Multi-agent reasoning system

Multi-agent collaboration framework

A framework for automating HarmonyOS / OpenHarmony devices through LLM agents

MCP server for AI agents to read, edit, inspect, and validate local HWPX documents.

Agentic Research Discipline (ARD) — grounded, verifiable AI research with a .research/ substrate tier. ARD is the plugin's internal, empirically-warranted discipline (ard-core/).

Why is your agent bill so high? Profile LLM agent traces: token waterfalls, re-sent-prefix waste, prompt-cache simulation, and cache-breaker detection with concrete fixes. Pure stdlib; the demo needs no API keys.

Turn successful AI agent sessions into reusable agent skills. Distill Claude Code transcripts into SKILL.md playbooks with evals-ready drafts.

Packaged Claude Code / Codex skills for teams

Command-line interface for Clipy — list, search, and read your screen recordings' transcripts, AI summaries, and key moments from the terminal.

Autonoma test planner - generate E2E test cases for any frontend codebase.

Portable AI-agent skills for the deliverables knowledge workers ship — diagrams, ADRs, PRDs, runbooks, decks, reviews — installable into Claude Code, Cursor, Kiro, and any IDE that takes custom instructions. One command per skill or per role-based pack.

Turn websites, browser sessions, desktop apps, and local tools into deterministic CLI surfaces for humans and AI agents.

Lightweight SDK to track AI agent tool calls, costs, and latency.

Stateful LangGraph workflow that reviews Git diffs with a reviewer-verifier loop and deterministic checks.

Python SDK for Votrix Managed Agents (VMA)

npm for your coding agent. Install packs of skills, subagents, and hooks into any repo, for every major agent.

Provider-agnostic LLM adapter with streaming and multi-turn support