Skip to content
LUNAROUTEDocs

Personal assistants

LunaRoute is inference for the personal agent you already run — not another assistant app. Personal agents connect like any OpenAI-compatible endpoint: point them at https://gw.lunaroute.com/v1 with your lr_ API key. Tool-using agents can also add the hosted MCP server for web search, document conversion, and images.

Personal-agent traffic gets its own concurrency allowance. See the Personal Agent Inference plan — a flat $19.99/mo for one concurrent request (GLM-5.2), scheduled as capacity becomes available, with zero data retention.

OpenClaw

Section titled “OpenClaw”
Terminal window
lunaroute setup openclaw

This merges a lunaroute provider into ~/.openclaw/openclaw.json (api: openai-completions, baseUrl: https://gw.lunaroute.com/v1, key read from ${LUNAROUTE_API_KEY}). Your existing config is preserved. Then restart the gateway and confirm with openclaw models list / openclaw models set lunaroute/<model>.

Hermes

Section titled “Hermes”
Terminal window
lunaroute setup hermes

Hermes owns its own config, so setup drives its CLI instead of writing files:

Terminal window
hermes config set providers.lunaroute.api https://gw.lunaroute.com/v1
hermes config set providers.lunaroute.key_env LUNAROUTE_API_KEY
hermes config set providers.lunaroute.transport chat_completions
hermes config set LUNAROUTE_API_KEY lr_...

Then start Hermes and pick a model:

/model custom:lunaroute:<model>

Models auto-discover from /v1/models. Your default model is never changed.

NanoClaw and other OpenAI-compatible agents

Section titled “NanoClaw and other OpenAI-compatible agents”

NanoClaw has no dedicated adapter yet — configure it as a generic OpenAI-compatible provider:

Terminal window
lunaroute setup generic     # prints the base URL and the LUNAROUTE_API_KEY export

Use base URL https://gw.lunaroute.com/v1, your lr_ key, and any model id from Models.

Mira

Section titled “Mira”

Mira is a continuous personal-entity agent (one conversation thread forever, first-person memory). Its deployment pipeline ships LunaRoute defaults, so setup depends on the install:

New install — the deploy template is pre-filled for LunaRoute; your API key is the only required value. Copy deploy/deploy-config.example.yml to deploy-config.yml, set chat_api_key to your lr_ key, and leave subcortical_api_key, embedding_api_key, and systemone_api_key empty (they reuse chat_api_key on the LunaRoute gateway). Then run ./deploy/deploy.sh --config deploy-config.yml --loud.

Existing install — paste the setup prompt from the Connect page (Connect → Agents → Mira) into a Mira chat session. Mira re-points its own model_configs routes at LunaRoute in one atomic SQL transaction and restarts itself.

Other harnesses

Section titled “Other harnesses”

See CLI for lunaroute setup on coding agents, and Harness setup for wiring the MCP toolbelt into your client.

LunaRoute documentation