RMCP runtime for provider-backed agents with CLI, REST, HTTP MCP, plugins, and scaffold support.

Oh My Pi bash runtime ported as a deepseek-harness tool plugin: persistent shell session, output minimizer, managed background jobs, command interception

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries + a relevance index + a cited synthesis + Q&A. Plus audio/video transcription, deep web research with citations & branded HTML reports. 13 commands, no Node runtime.

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.

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

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.

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

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 AI clients to observe foreground browser viewports, read filtered page evidence, and run guarded reusable site-pack procedures through the same local runtime as the CLI.

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 local MCP clients to expose and execute typed tools through a bounded native runtime with Ed25519 admission, per-session budgets, rate limits, schemas, and cached outputs.

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

Enables MCP clients such as Codex and Claude to plan natural-language or timed actions, generate and revise skeletal motion locally through a Kimodo runtime, and review results with diagnostics, candidate comparison, and interactive 3D previews. Provides checked handoffs of verified exports into Blender and Unreal Engine.

Enables MCP clients to drive a separately installed OrcaSlicer instance through a local stdio server, covering slicing jobs, profile and 3MF/settings editing, raw CLI options, artifact inspection and an optional desktop adapter for GUI actions. It also provides job queuing, status tracking and runtime detection of the installed binary's capabilities.