InferenceCustom Endpoints

Set Up an OpenAI-Compatible Endpoint

View as Markdown

Use the custom OpenAI-compatible provider for servers that implement /v1/chat/completions or a compatible /v1/responses API. Examples include vLLM, TensorRT-LLM, llama.cpp, LocalAI, and other compatible servers.

The agent connects to inference.local inside the sandbox. OpenShell forwards that traffic to the endpoint configured during onboarding.

Start the Server

Start the compatible server before onboarding. The following example starts vLLM on port 8000.

$vllm serve meta-llama/Llama-3.1-8B-Instruct --host 0.0.0.0 --port 8000

Port 8000 is one of NemoClaw’s bundled host-gateway ports.

The examples on this page listen on every IPv4 interface so both host-side onboarding and a containerized gateway can reach the server. When the server does not require authentication, use a host firewall with default-deny inbound rules. Allow TCP port 8000 only from the OpenShell Docker subnet to its gateway address, keep loopback access, and deny the port on every other interface. Do not expose the port to your LAN or the internet.

Run Onboarding

Start the onboard wizard.

$nemoclaw onboard

Select Other OpenAI-compatible endpoint. Enter the server base URL and the model ID reported by the server.

Use a host-routable URL such as http://localhost:8000/v1 when you want onboarding to verify the API, tool-calling, and streaming paths before gateway registration. To qualify for automatic rewriting, an HTTP endpoint URL must use the exact loopback host localhost, 127.0.0.1, or [::1]. Automatic rewriting is limited to NemoClaw’s bundled host-gateway ports: 8000, 11434, and 11435. NemoClaw validates the entered URL from the host and registers the OpenShell gateway route through host.openshell.internal:<port> for sandbox traffic. Sandbox inference requests continue to use the base inference.local policy, so the managed compatible-endpoint route does not require adding the local-inference preset. NemoClaw leaves URLs without an explicit port, URLs on :80 or another privileged port, and URLs on unsupported ports unchanged. Those URLs require a separately compatible runtime topology and network policy. This rewrite depends on an OpenShell topology that resolves host.openshell.internal inside the sandbox; if that bridge is unavailable, onboarding can still validate the host URL, but nemoclaw <name> status is the authoritative runtime check. Make sure the server listens on an address reachable from containers, such as 0.0.0.0; a server bound only to 127.0.0.1 can still be unreachable from the sandbox route.

If you manually enter a sandbox-internal alias such as http://host.openshell.internal:8000/v1, host-side endpoint probing is skipped during onboarding. Use a host-routable endpoint such as localhost when you need onboarding to verify the API, tool-calling, and streaming paths before gateway registration. Otherwise, verify the runtime route after onboarding with nemoclaw <name> status and a short agent request.

For an HTTP URL using the exact host localhost, 127.0.0.1, or [::1] and port 8000, 11434, or 11435, the API key prompt says that pressing Enter selects no authentication. Other URLs still require COMPATIBLE_API_KEY.

Refer to Choose a Compatible Inference API for the probe order and runtime API selection.

Serve a Raw Model File

Start a compatible server for a raw model file instead of passing the file path to NemoClaw. The Ollama provider accepts Ollama model tags and does not accept a raw .gguf path.

The following example starts llama-server with a GGUF model.

$llama-server \
>  -m /models/NVIDIA-Nemotron3-Nano-4B-Q4_K_M.gguf \
>  --host 0.0.0.0 \
>  --port 8000 \
>  -c 16384 \
>  -ngl 999 \
>  --parallel 1 \
>  --chat-template chatml

During onboarding, select Other OpenAI-compatible endpoint. Enter the server base URL and the model ID returned by /v1/models. Use the model ID, not the raw file path.

For the example above, the server commonly reports NVIDIA-Nemotron3-Nano-4B-Q4_K_M.gguf as its model ID.

Run Non-Interactive Onboarding

Start the endpoint before running the non-interactive command because onboarding validates the server. Set NEMOCLAW_REASONING=true when the endpoint serves a reasoning-only model.

Reasoning mode validates only /v1/chat/completions and does not verify tool calling or streaming. Enable it only when the endpoint supports the capabilities your agent requires.

$NEMOCLAW_PROVIDER=custom \
>  NEMOCLAW_ENDPOINT_URL=http://localhost:8000/v1 \
>  NEMOCLAW_MODEL=meta-llama/Llama-3.1-8B-Instruct \
>  NEMOCLAW_COMPATIBLE_AUTH_MODE=none \
>  nemoclaw onboard --non-interactive

For the raw model example, use the ID returned by /v1/models.

$NEMOCLAW_PROVIDER=custom \
>  NEMOCLAW_ENDPOINT_URL=http://localhost:8000/v1 \
>  NEMOCLAW_MODEL=NVIDIA-Nemotron3-Nano-4B-Q4_K_M.gguf \
>  NEMOCLAW_COMPATIBLE_AUTH_MODE=none \
>  nemoclaw onboard --non-interactive
VariablePurpose
NEMOCLAW_PROVIDERSet to custom.
NEMOCLAW_ENDPOINT_URLBase URL of the server.
NEMOCLAW_MODELModel ID reported by the server.
NEMOCLAW_COMPATIBLE_AUTH_MODESet to none to explicitly select no authentication for an HTTP endpoint using localhost, 127.0.0.1, or [::1] and port 8000, 11434, or 11435.
NEMOCLAW_REASONINGEnables reasoning-only validation with the case-insensitive true values true, 1, yes, and y.
NEMOCLAW_TRUSTED_PRIVATE_HOSTSOptional comma-separated exact hostnames or IP literals for operator-owned private endpoints. Wildcards are not supported.
NEMOCLAW_TRUSTED_PRIVATE_INFERENCE_HOSTSInference-only compatibility alias for NEMOCLAW_TRUSTED_PRIVATE_HOSTS. Inference onboarding combines entries from both variables.
COMPATIBLE_API_KEYEndpoint API key. Required unless loopback no-auth mode is selected.

For OpenClaw, NEMOCLAW_REASONING_EFFORT accepts low, medium, high, or default. A low, medium, or high value writes params.extra_body.reasoning_effort when the selected API is openai-completions. Another API family omits the field. An unset value or default leaves the endpoint’s own default in place. NemoClaw rejects an invalid value or a provider/API mismatch before changing provider, sandbox, policy, or registry state. After inference set changes the effort, an ordinary sandbox restart preserves the persisted value instead of restoring the image’s original onboarding value.

Private and reserved addresses are blocked by default. To use an inference gateway on a trusted corporate network, list only its exact host and keep the endpoint URL on that host:

$NEMOCLAW_TRUSTED_PRIVATE_HOSTS=llm.corp.example \
>  NEMOCLAW_PROVIDER=custom \
>  NEMOCLAW_ENDPOINT_URL=https://llm.corp.example/v1 \
>  NEMOCLAW_MODEL=your-model \
>  COMPATIBLE_API_KEY="$COMPATIBLE_API_KEY" \
>  nemoclaw onboard --non-interactive

NemoClaw still resolves the host before probing and pins the probe to the resolved address. Only RFC1918, carrier-grade network address translation (CGNAT), and IPv6 unique local address (ULA) destinations can be admitted; link-local metadata and other reserved ranges remain blocked. An unlisted private host, a hostname suffix match, or a DNS failure also remains blocked.