Single-purpose tools for running local LLMs and serving MCP servers to agents. Each repository does one job and can be used on its own.
| Repository | What it does |
|---|---|
| local-llm-serve | starts OVMS, Ollama and llama.cpp on the local machine, and prepares the models they load |
| mcp-call-orchestrator-proxy | makes one MCP server safe for many concurrent clients: serialized calls, self-healing connection, exact parity with the backend |
Contributions follow CONTRIBUTING.md. All repositories are MIT-licensed.
Starts OVMS, Ollama (Intel Vulkan) and llama.cpp, and prepares the models those servers load.
Python
A resilient, call-serializing MCP proxy that sits in front of a single backend MCP server as its only client and makes it safe for multiple concurrent clients.
Python
A resilient, call-serializing MCP proxy that sits in front of a single backend MCP server as its only client and makes it safe for multiple concurrent clients.
Starts OVMS, Ollama (Intel Vulkan) and llama.cpp, and prepares the models those servers load.
This organization has no public members. You must be a member to see who’s a part of this organization.
Loading…
Loading…