HLVM Docs
HLVM is a local AI runtime. Start with the smallest path that proves your setup, then use the workflow pages when you need a specific surface.
Reading Paths
| Goal | Read |
|---|---|
| Install HLVM | Install |
| Prove the first local run | First Run |
| Run one-shot agent tasks | Ask |
| Work interactively | REPL |
| Switch or download models | Models |
| Use named assistants | Agents |
| Connect external tools | MCP |
| Connect the browser bridge | Browser Bridge |
| Expose the local runtime server | Runtime Server |
| Recover a broken install | Troubleshooting |
| Look up every command | CLI Reference |
The Short Path
curl -fsSL https://hlvm.dev/install.sh | sh
hlvm --version
hlvm ask "summarize what HLVM is in one paragraph"
The first AI call prepares HLVM's managed local runtime. Local AI uses HLVM's
managed endpoint on 127.0.0.1:11439; user-facing clients talk to the runtime
host on 127.0.0.1:11435.
What To Read Next
- New users should read Guide after installation.
- Shell-heavy users should read Ask and CLI Reference.
- Tool users should read MCP, Agents, and Browser Bridge.
- HQL users should switch to the HQL docs.