A harness for driving a Godot 4 project from an agent: editor addons, a runtime bridge into the running game, an MCP server in front of them, and a CLI that installs and diagnoses the Godot side.

DSH Plugin Radar — open-source ecosystem radar for DeepSeek Harness plugins: continuous discovery (21k+ candidates), k8s runtime validation (13k+ tests), 15-min snapshots; the catalog is a generated artifact — 开源 DSH 插件生态雷达：持续发现 2.1 万+ 候选、k8s 运行级实测 1.3 万+、15 分钟快照；插件目录为自动生成的产物

AI Agent Network CLI — Local-first multi-agent orchestration across 6 runtimes (Claude Code CLI / Claude Agent SDK / Codex SDK / Codex app-server / Grok Build ACP / OpenCode CLI) and 8+ LLM providers. Apache 2.0.

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.

MCP server that gives AI assistants eyes and hands in the Godot editor: scene editing, input injection, deterministic game-time control, and live runtime state for agent-driven playtesting

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

A CLI that turns a goal into a pull request - and a sandbox for testing concurrent AI coding agents on the Mozaik runtime.

Claw Orchestrator — run Claude Code, Codex, Antigravity, Grok Build, OpenCode, any ACP agent and custom coding CLIs as one unified runtime. Drop into Hermes Agent, Claude Desktop, Cursor, Cline, Continue, Zed, Windsurf, Goose or any Model Context Protocol

Thea Software is an engineering verification layer for AI agents that binds code changes to explicit validation commands. It bridges conversational models to robust software runtimes, enforcing automated build checks so that code drift and unverified changes are actively rejected.

Enables AI agents to drive policy evaluation over MCP by starting executions, answering policy questions from case evidence, and reading deterministic outcomes with reasoning traces, while the runtime controls which questions are asked and how answers combine.

Enables Claude Code to delegate tasks to persistent GitHub Copilot CLI sessions via MCP, inspect pending tool requests, and approve each operation once or deny it while continuing multi-turn context. It bridges ACP runtime sessions locally over stdio without a public service or background daemon.

Embeds a runtime MCP inspector in a NestJS app so coding agents can inspect the module and provider graph, routes and their guards/interceptors/pipes/filters, logs, request traces, event listeners, and scheduled jobs through an HTTP endpoint.

Enables MCP-capable agent CLIs on macOS to reuse an installed, unmodified OpenAI Browser Runtime to drive a connected Chrome or Edge browser (or a host's in-app browser backend) through js, js_reset, and turn_ended tools. It stays a thin bridge that preserves the Runtime's approval and security boundaries, failing closed when the client cannot handle approval requests.

Enables agents to validate enterprise travel policies, audit hotel rate parity, and check carbon ESG compliance through a zero-dependency MCP server. It exposes policy and expense-auditing tools over STDIO JSON-RPC for use in Claude Desktop, Cursor, or other MCP runtimes.

Enables agents to plan multi-day travel schedules by solving itinerary graphs with TSP heuristics, fatigue decay, and opening-hour constraints, exposed over MCP STDIO JSON-RPC for agent runtime integration.

Native Model Context Protocol (MCP) server turning AI coding agents into .NET runtime diagnosticians, memory forensic analysts, and CIL binary architects.

Enables agents to run SweetScape 010 Editor Binary Templates and Scripts headlessly against local files. It provides tools to locate the editor binary, execute templates or scripts, and use controlled exit behavior for compile and runtime failures.

Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.