メニュー
Changes the active inference model without restarting the sandbox. Use when change inference runtime, inference routing, openclaw, openshell, switch memantoclaw inference models.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Provisions a remote GPU VM with MemantoClaw using Brev deployment. Also covers forwards messages between Telegram and the sandboxed OpenClaw agent. Use when deploy memantoclaw remote gpu, deployment, gpu, memantoclaw, memantoclaw brev cloud deployment, memantoclaw telegram bridge, openclaw, openshell.
Installs MemantoClaw, launch a sandbox, and run your first agent prompt. Use when inference routing, install memantoclaw openclaw sandbox, memantoclaw, memantoclaw quickstart, memantoclaw quickstart install launch, openclaw, openshell, sandboxing.
Reviews and approve blocked agent network requests in the TUI. Also covers adds, remove, or modify allowed endpoints in the sandbox policy. Use when approve deny memantoclaw agent, customize memantoclaw network policy, customize memantoclaw sandbox network, memantoclaw, memantoclaw approve network requests, network policy, openclaw, openshell.
Inspects sandbox health, trace agent behavior, and diagnose problems. Use when debug memantoclaw agent issues, monitor memantoclaw sandbox, monitor memantoclaw sandbox activity, monitoring, memantoclaw, openclaw, openshell, troubleshooting.
Learns how MemantoClaw combines a lightweight CLI plugin with a versioned blueprint to move OpenClaw into a controlled sandbox. Also covers MemantoClaw is an open source reference stack that simplifies running OpenClaw always-on assistants safely; changelogs and feature history for MemantoClaw releases. Use when blueprints, how memantoclaw works, inference routing, memantoclaw, memantoclaw changelog, memantoclaw overview, memantoclaw overview does fits, memantoclaw release notes.
Learns how MemantoClaw combines a lightweight CLI plugin with a versioned blueprint to move OpenClaw into a controlled sandbox. Also covers fulls CLI reference for plugin and standalone MemantoClaw commands; configurations reference for MemantoClaw routed inference providers. Use when blueprints, cli, inference routing, llms, memantoclaw, memantoclaw architecture, memantoclaw architecture plugin blueprint, memantoclaw cli commands.
| name | memantoclaw-configure-inference |
| description | Changes the active inference model without restarting the sandbox. Use when change inference runtime, inference routing, openclaw, openshell, switch memantoclaw inference models. |
Change the active inference model without restarting the sandbox.
PATH.Change the active inference model while the sandbox is running. No restart is required.
Switching happens through the OpenShell inference route. Use the provider and model that match the upstream you want to use.
$ openshell inference set --provider nvidia-prod --model nvidia/nemotron-3-super-120b-a12b
$ openshell inference set --provider openai-api --model gpt-5.4
$ openshell inference set --provider anthropic-prod --model claude-sonnet-4-6
$ openshell inference set --provider gemini-api --model gemini-2.5-flash
If you onboarded a custom compatible endpoint, switch models with the provider created for that endpoint:
$ openshell inference set --provider compatible-endpoint --model <model-name>
$ openshell inference set --provider compatible-anthropic-endpoint --model <model-name>
If the provider itself needs to change, rerun memantoclaw onboard.
Run the status command to confirm the change:
$ memantoclaw <name> status
Add the --json flag for machine-readable output:
$ memantoclaw <name> status --json
The output includes the active provider, model, and endpoint.
inference.local.memantoclaw-reference — Inference Profiles for full profile configuration details