$ loading_
Manage llama.cpp inference servers with lifecycle, config, and orphan-process controls.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "llauncher" yet — see the docs or source repo.
Use llauncher to start a llama.cpp llama-server instance with a local GGUF model on port 8080, then return the instance status, launch arguments, and health check result.
Returns the started server details, including port, model path, running status, and accessibility check results.
With llauncher, find the service configuration named research-llm, change context length to 8192 and thread count to 8, then save and summarize the updated configuration.
Outputs the updated key configuration values and confirms the configuration was successfully saved or updated.
Use llauncher to scan the current environment for llama-server instances, identify orphaned processes not tracked by configuration management, and list their PIDs, listening ports, and recommended actions.
Returns a list of orphaned processes and recommended actions to clean up leftover services or restore managed state.
Enable persistent two-way chats between LLMs and diffusion language models.
Let AI assistants list, load, and unload local LM Studio models.
Connect Claude Code to local llama.cpp for low-cost local LLM testing.
Route coding tasks across local and remote LLMs with benchmarking and code search.
Get LLM provider recommendations, pricing, and service status insights.
Add governance, prompt scanning, and observability to local Ollama LLMs.