Search

Agent definitions, audit-trail tooling and a CLI for running a multi-agent workflow on Claude Code.

Always-on skill & plugin selector for AI coding agents. Scans installed skills/plugins, analyzes user tasks, selects the best match, asks for confirmation before invoking.

Lark/Feishu IM bot channel for DeepSeek Harness: chats drive agents, replies and approvals return as messages and cards

JavaScript and TypeScript SDK for keelwave — observability and alerting for AI agents.

通过扫码、App Manifest或机器人凭据把IM机器人接入DeepSeek Harness（支持飞书、微信、钉钉、企业微信、QQ、Slack、Telegram、Discord和WhatsApp）。

A scaffolding CLI for ML, DL, LLM, RAG and AI Agents projects.

Test whether human approval controls for AI agents actually work.

Vigil — 运维 agent harness：记住整个平台，安全地动生产（拓扑表事实层 + runbook 程序层 + 权限矩阵纵深防御）

Python SDK for AgenticSettle — verify any AI agent's output, settle with pre-paid token escrow, earn the Verified badge.

Qwen3.8-27B - AI model available on ModelScope inference platform

Local-first prompt-to-video CLI for AI agents, with deterministic scene scripts, TTS, word-synced captions, product walkthroughs, and 2D/3D rendering.

Install Pine Labs Online agent skills, payment workflow guidance, and integration safeguards into AI coding assistant projects.

DeepSeek Harness (dsh) plugin: run work as a small crew of role agents (product manager, researcher, architect, engineer, QA, code reviewer, security reviewer, doc reviewer) that talk through files on disk, with the PM as the only voice to the user.

Deterministic runtime evidence and diagnostics for direct OpenAI Agents SDK integrations.

OpenAI Agents SDK sessions backed by Citadel: encrypted at rest, with deletes that destroy the key

Strands Agents session storage backed by Citadel: encrypted at rest, with deletes that destroy the key

Control coding agents from chat, with a permission floor the trust toggle cannot reach

Autonomous AI Security Watchman for backend servers — real-time threat detection, jailbreak guards, dynamic policy engine, code healing, and premium dashboard

Local-first orchestration for personal AI runtimes.

%%hermes cell magic — talk to Hermes Agent directly inside Jupyter notebooks