v0.2.0 · Apache 2.0
Enables AI clients to coordinate coding agents on the user’s own computers and servers over MCP, connecting to Herdr, Codex app-server, and experimental ZCode/Amp connectors through a self-hosted relay without inbound ports.
— · Apache 2.0
ChannelTerm is an open-source MCP server that enables humans and AI agents to share live serial and SSH terminal sessions for embedded systems development and debugging. It allows AI agents to read device output, execute commands, assist with GDB debugging, and transfer files while keeping developers in control.
— · Apache 2.0
Native Model Context Protocol (MCP) server turning AI coding agents into .NET runtime diagnosticians, memory forensic analysts, and CIL binary architects.
— · MIT License
Deterministic Unit-Record Memory Engine for AI coding agents. Eliminates context-window amnesia and compaction bloat via zero-turn workspace hydration, byte-exact registers, and live context telemetry.
— · Apache 2.0
An MCP server that enables AI clients to inspect footage and audio, edit revision-locked timelines or generated source code, render with Remotion or HyperFrames, and verify results through measurements for iterative video editing.
— · MIT License
A hosted remote MCP server that gives AI agents live hotel, Airbnb/Vrbo and flight pricing tools — nightly rate calendars up to 330 nights, every booking site's price for a stay compared against the hotel's own site, guest reviews, and Google Flights search. Clients connect over Streamable HTTP with browser OAuth or an API key, so nothing needs to be installed or run locally.
— · MIT License
Enables developers to register custom tool-calling functions, execute path-safe file operations within an isolated workspace, and keep in-memory memory and audit state for AI agent workflows.
— · MIT License
Enables an AI agent to see and control the screen of an already-running macOS virtual machine over VNC, exposing four tools: screenshot, click, type_text, and key_press. This lets the agent drive a disposable VM's UI directly with its own model, without touching the real desktop or running a separate agent loop.