A gateway-level plugin that automatically switches to fallback LLM models when primary APIs hit rate limits or encounter quota errors.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-model-failover
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openclaw-model-failover using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenClaw Model Failover Plugin?
The OpenClaw Model Failover plugin is a critical infrastructure component designed to enhance the reliability of AI agents. Rather than being a standalone agent skill, it functions as an OpenClaw Gateway plugin that monitors session health in real-time. It specifically targets common points of failure such as HTTP 429 rate limits, quota exhaustion, and authentication scope errors, ensuring that your Openclaw Skills never get stuck in failure loops.
By dynamically patching pinned session models, this plugin allows for seamless transitions between providers like Anthropic, OpenAI, and Google. This ensures that even if one provider faces an outage or a specific API key hits its limit, the underlying workflow continues without manual intervention, making it a cornerstone for production-grade Openclaw Skills deployment.
OpenClaw Model Failover Plugin Use Cases
- Preventing 'API rate limit reached' loops during high-concurrency agent tasks.
- Maintaining service continuity when a specific LLM provider experiences regional outages.
- Automatically bypassing quota exhaustion by shifting traffic to secondary providers.
- Handling specific authentication or scope failures (e.g., missing specific write permissions) by falling back to a more permissive model environment.
How OpenClaw Model Failover Plugin Works
- The plugin sits at the gateway layer, intercepting responses from LLM providers during active sessions.
- It monitors for specific error triggers such as HTTP 429 (Rate Limit) or RESOURCE_EXHAUSTED codes.
- Upon detecting a failure, the plugin identifies the next available model based on a user-defined fallback priority list.
- It automatically patches the pinned model metadata for that specific session.
- The gateway retries the request using the fallback model, ensuring the user or agent receives a successful response without restarting the workflow.
OpenClaw Model Failover Plugin Setup
Integrating this plugin into your Openclaw Skills environment is straightforward. You can install it via the central hub or manually from a local repository.
Option A: ClawHub Installation
clawhub install openclaw-model-failover
Option B: Local Development Installation
openclaw plugins install -l ~/.openclaw/workspace/openclaw-model-failover
openclaw gateway restart
OpenClaw Model Failover Plugin Data Schema & Taxonomy
The plugin manages failover logic through a structured configuration block that defines the hierarchy of LLM providers.
| Attribute | Type | Description |
|---|---|---|
| fallback_order | Array | A prioritized list of providers (e.g., ["anthropic", "openai", "google"]). |
| trigger_codes | Array | List of HTTP or gRPC error codes that initiate a switch. |
| session_id | String | The unique identifier of the session being patched with a new model. |
| model_patch | Object | The updated model metadata applied to the session context. |
OpenClaw Model Failover Plugin Advanced Features
- Multi-provider chaining: Configure complex fallback sequences across different LLM families.
- Real-time session patching: Update model assignments on-the-fly without losing conversation context.
- Auth error detection: Identify specific scope failures (like missing write permissions) to trigger switches.
- Seamless gateway integration: Works silently in the background to improve the resilience of all your Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
OpenClaw Memory Docs
A local-first, audit-friendly memory store plugin for OpenClaw that provides explicit control over documentation capture and semantic search.
Openclaw Memory Core
A high-performance utility library providing privacy-first redaction, local JSONL storage, and offline text embeddings for AI memory management.
Openclaw INWX
A comprehensive automation plugin for managing the INWX domain registrar lifecycle, including DNS, registration, and DNSSEC within the Openclaw Skills ecosystem.
openclaw-help
A security-first plugin that adds a customizable /help command to your agent while keeping private workflows and shortcuts safe from public repositories.
OpenClaw Ops (Elvatis)
A comprehensive operational toolkit for managing, monitoring, and validating OpenClaw deployments and configurations.
OpenClaw RSS Feeds
An automated security digest tool for Openclaw that fetches RSS feeds, enriches items with CVE data, and publishes drafts to Ghost CMS.
METADATA
Featured*
