Search

Check AI workflows against the EU AI Act and record auditable evidence

Git-native project memory for AI-assisted development

Anthropic infrastructure FinOps SDK — part of the Hyperscaler Radar suite.

ax integration for pi: structured web extraction via CSS selectors and HTTP API calls

Multi-entry web search hub for DeepSeek Harness: route ctx.web search through configurable model entries (DeepSeek official, GLM Coding Plan Zhipu web_search, future Kimi) with exactly one active entry; ships a Settings page tab for management.

Roboin's personal collection of Agent Skills.

Infrastructure plugin for dsh: provisions the kimi-webbridge daemon (auto-install with SHA-256 verification, auto-start) and registers the kimi-webbridge skill that documents the full 25-action browser protocol. Registers a thin kimi_webbridge tool (statu

Experimental project-local agent workflow skills installer

A lightweight, fully customizable, accessible, and SSR-safe user avatar component for Vue 3 and Nuxt. Supports initials, custom images, pixel-art generation (identicons), groups with overflow, and auto-contrast text. Perfect for user profiles, team displa

Model-facing long-horizon memory tools (retain, recall, reflect, memory_edit, learn) over the ctx.memory service, plus first-turn project-memory prompt injection — a standalone plugin for DeepSeek Harness with no upstream harness changes required.

A verifiable self-improvement loop for agent harnesses. Freeze the model. Evolve the harness. Promote only what proves lift.

Voice in + voice out for Pi CLI — hold-to-talk STT (Deepgram or 19 offline models) plus TTS (Kitten Nano, Piper, Kokoro, or Deepgram Aura)

DSH plugin: append each answer's token usage to the conversation

Wingman — 本地 harness 配置面板(Claude Code / Codex / dsh)。面板只绑 127.0.0.1,不自动上报使用数据;内容样本与授权的数据边界见 getwingman.dev/data。

Widget de chat com IA para Angular. Exibe um botão flutuante arrastável que abre um painel de conversa conectado à API do RM Copilot via streaming.

Machine-checkable hexagonal architecture for TypeScript/ESM. CLI: check (dag, layers, private, barrels, ports) and explain.

Google Gemini model adapter for Harnest, including multimodal input and provider-native context caching. Configure AI Studio credentials through a Harnest Connection or host provider; do not place API keys in a HarnessSpec.

Feishu and Lark text, image, and file channel bridge for DeepSeek Harness

Local-only simulator for building and testing Kick webhook integrations

Offline-first LLM + STT/TTS engine for the browser. WebGPU inference via WebLLM, audio via Transformers.js, tool calling with Zod validation.