llmman

llmman pulls GGUF/safetensors models from OCI registries and serves them behind Ollama-, OpenAI-, and Anthropic-compatible APIs. It uses llama-server for GGUF models and vllm or mlx_lm.server for safetensors models. OpenClaw talks to it through the generic openai-completions adapter.

Property	Value
Provider id	`llmman` (custom; configure under `models.providers.llmman`)
Plugin	none — not a bundled OpenClaw provider plugin
Auth env var	none required; any value works, `llmman serve` has no auth
API	OpenAI-compatible (`openai-completions`)
Default base URL	`http://127.0.0.1:17434/v1`

llmman is a custom self-hosted OpenAI-compatible backend, not a dedicated OpenClaw provider plugin: you configure it under models.providers.llmman instead of picking an onboarding auth choice. For a bundled plugin with auto-discovery, see SGLang or vLLM.

Version scope: this page is verified against llmman b315, commit 0e7a3ed.

Getting started

Start llmman with a model

LLMMAN_CONTEXT_LENGTH=65536 llmman serve gemma4

llmman serve listens on 127.0.0.1:17434 by default. Set LLMMAN_HOST before startup to override the bind address; there are no --host/--port flags. GPU acceleration (CUDA, ROCm, Vulkan, or Metal) is auto-detected; set LLMMAN_LLM_LIBRARY to override it because there is no --device flag. The model argument is optional — omit it to start the server and load models on the first request that names them instead.The example fixes the server context at 65,536 tokens and uses the same value in OpenClaw below. If you change LLMMAN_CONTEXT_LENGTH, keep the OpenClaw model’s contextWindow at or below that value.

Verify the server is reachable

curl http://127.0.0.1:17434/v1/models
curl http://127.0.0.1:17434/api/version

llmman serve has no dedicated /health route at the top level; use /v1/models or /api/version for a readiness probe.

Add an OpenClaw provider entry

Add an explicit provider entry and point your default model at it. See the config example below.

Full config example

Gemma 4 on a local llmman server:

{
  agents: {
    defaults: {
      model: { primary: "llmman/gemma4" },
      models: {
        "llmman/gemma4": {
          alias: "Gemma 4 (llmman)",
        },
      },
    },
  },
  models: {
    mode: "merge",
    providers: {
      llmman: {
        baseUrl: "http://127.0.0.1:17434/v1",
        apiKey: "llmman-local",
        api: "openai-completions",
        models: [
          {
            id: "gemma4",
            name: "Gemma 4 (llmman)",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 65536,
            maxTokens: 4096,
          },
        ],
      },
    },
  },
}

On-demand startup

OpenClaw can start llmman itself only when an llmman/... model is selected. Add localService to the same provider entry:

{
  models: {
    providers: {
      llmman: {
        baseUrl: "http://127.0.0.1:17434/v1",
        apiKey: "llmman-local",
        api: "openai-completions",
        timeoutSeconds: 300,
        localService: {
          command: "/opt/homebrew/bin/llmman",
          args: ["serve", "gemma4"],
          env: { LLMMAN_CONTEXT_LENGTH: "65536" },
          healthUrl: "http://127.0.0.1:17434/v1/models",
          readyTimeoutMs: 180000,
          idleStopMs: 0,
        },
        models: [
          {
            id: "gemma4",
            name: "Gemma 4 (llmman)",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 65536,
            maxTokens: 4096,
          },
        ],
      },
    },
  },
}

command must be an absolute path. Run which llmman on the Gateway host and use that path. Full field reference: Local model services.

Advanced configuration

Why requiresStringContent might matter

llmman resolves and loads the requested model, rewrites its id for the selected backend, and adds generation defaults such as repeat_penalty. It forwards message content and tool schemas without normalizing them, so compatibility for those fields depends on the selected backend and model.

If OpenClaw runs fail with:

messages[1].content: invalid type: sequence, expected a string

set compat.requiresStringContent: true in the model entry. OpenClaw then flattens pure text content parts into plain strings before sending the request.

Tool-schema caveat

If a model accepts small direct /v1/chat/completions requests but fails on full OpenClaw agent-runtime turns, try disabling the tool schema surface first:

compat: {
  supportsTools: false
}

That reduces prompt pressure on stricter local backends. If tiny direct requests still work but normal OpenClaw agent turns keep crashing inside llama-server, treat it as an upstream model/server limitation rather than an OpenClaw transport issue.

Manual smoke test

Test both layers once configured:

curl http://127.0.0.1:17434/v1/chat/completions \
  -H 'content-type: application/json' \
  -d '{"model":"gemma4","messages":[{"role":"user","content":"What is 2 + 2?"}],"stream":false}'

openclaw infer model run \
  --model llmman/gemma4 \
  --prompt "What is 2 + 2? Reply with one short sentence." \
  --json

If the first command works but the second fails, see Troubleshooting below.

Proxy-style behavior

Because llmman uses the generic openai-completions adapter (not openai-responses), native-OpenAI-only request shaping never applies: no service_tier, no Responses store, no prompt-cache hints, and no OpenAI reasoning-compat payload shaping get sent.

Troubleshooting

curl /v1/models fails

llmman serve is not running or is not reachable at the configured address. The default is 127.0.0.1:17434; if you set LLMMAN_HOST, update the OpenClaw baseUrl and healthUrl to match.

messages[].content expected a string

Set compat.requiresStringContent: true in the model entry (see above).

Direct /v1/chat/completions calls pass but openclaw infer model run fails

Both probes are tool-free, so compat.supportsTools cannot change this failure. Check the configured base URL and model id, inspect the llmman/backend logs, and compare the two request payloads and responses.

Model run passes but a normal agent turn fails

The agent turn includes a larger prompt and may include tool schemas. Try compat.supportsTools: false to isolate tool-schema pressure (see the tool-schema caveat above).

llama-server still crashes on larger agent turns

If schema errors are gone but the spawned llama-server still crashes on larger agent turns, treat it as an upstream llama.cpp or model limitation. Reduce prompt pressure or switch backend/model.

For general help, see Troubleshooting and FAQ.

Local models

Running OpenClaw against local model servers.

Local model services

Starting local model servers on demand for configured providers.

Gateway troubleshooting

Debugging local OpenAI-compatible backends that pass probes but fail agent runs.

Model selection

Overview of all providers, model refs, and failover behavior.

Overview

Concepts and configuration

Providers

Getting started

Full config example

On-demand startup

Advanced configuration

Troubleshooting

Local models

Local model services

Gateway troubleshooting

Model selection

​Getting started

​Full config example

​On-demand startup

​Advanced configuration

​Troubleshooting

​Related

Local models

Local model services

Gateway troubleshooting

Model selection

Getting started

Full config example

On-demand startup

Advanced configuration

Troubleshooting

Related