Plugins

#model-routing
ZeroGPU Router@zerogpu
#mcp#zerogpu

ZeroGPU Router plugin for OpenClaw: route your AI tasks (summarize, classify, redact PII, extract JSON, chat) to open-weight and small language models via the zerogpu CLI. OpenAI-compatible and pay-as-you-go — cuts agent inference costs without changing your reasoning model.

1.3k
Amazon Bedrock Mantle@openclaw
#amazon-bedrock-mantle#model-routing

OpenClaw Amazon Bedrock Mantle provider plugin for OpenAI-compatible model routing.

1.2k
ZeroAPI Router@dorukardahan
#model-routing

ZeroAPI - transparent subscription-aware model and account routing for OpenClaw

1k
ToggleLogic@togglelogic
#model-routing#togglelogic

Generic model routing, approval, audit, and cost-visibility primitives for OpenClaw. ToggleLogic Free includes no assistant, memory, skills, or business workflow policy.

201
ZeroGPU@allenaj
#mcp#zerogpu

OpenClaw plugin: offload cheap AI tasks to the ZeroGPU MCP server.

186
Claw Cost Router@anthony1232123-create
#model-routing#claw

Auto-route Claude models (Opus/Sonnet/Haiku) per message in OpenClaw — cut API costs without sacrificing skill quality.

174
ZeroGPU Router@allenaj
#mcp#zerogpu

ZeroGPU Router plugin for OpenClaw: route trivial AI tasks (summarize, classify, redact PII, extract JSON, follow-ups) to small/nano models via MCP. Cuts agent inference costs without changing your reasoning model.

174
Genor's Orchestrator@genortg
#model-routing#orchestrator-auto-populate

Genor's Orchestrator — OpenClaw Plugin

138
UniGateway@unigateway
#unigateway#gemini

UniGateway LLM provider plugin for OpenClaw — Multi-provider LLM aggregator

125
Jev Claw@trietphan
#typesafe#llm-routing

Typed model-routing for OpenClaw agents, powered by TypeSafe Jev

74
Openclaw Router@3222535290
#model-router#model-routing

Router — OpenClaw pre-call model routing with budget and token policy

221
OrgX for OpenClaw@useorgx
#mcp#orgx

Persistent organizational memory and coordination for OpenClaw agents

208
OpenMark AI Model Router@openmarkai
#model-routing#model-router

Benchmark-driven model routing for OpenClaw. Uses your own benchmark data to route tasks to better-fit models and reduce overuse of expensive flagship models.

201
tierflow@eucal-ai
#model-router#model-routing

@eucal-ai/tierflow

173
Openclaw Mode Switcher@roman-yakobnyuk
#anthropic#model-routing

Self-escalating model routing — upgrades to a smarter model when it's needed, reverts automatically when it's done.

164
Jev Router@gowtham980
#model-routing#cost-optimization

Provider-neutral, quality-aware model routing for OpenClaw with cost-conscious profiles and native Control UI.

36
Odoo@da22le123
#odoo-chatter#xml-rpc

OpenClaw channel plugin for Odoo — receive webhooks and reply via configurable XML-RPC methods

150
AIsa Provider@aisadocs
#aisa#deepseek

Requires AISA_API_KEY. Uses the supplied AISA_API_KEY to send requests to https://api.aisa.one. Native-first ClawHub plugin for aisa-provider. Ships the packaged AIsa skill with an openclaw.plugin.json manifest and a Claude-compatible bundle fallback. Configure AIsa as an OpenAI-compatible provider endpoint for OpenClaw and related runtimes. Use this skill when the user wants to set AISA_API_KEY, point a client at https://api.aisa.one/v1, inspect AIsa model IDs, compare routed model options such as Qwen, DeepSeek, Kimi, and Doubao, or troubleshoot provider configuration. Use when: the user needs model routing, provider setup, or Chinese LLM access guidance.

136
LLM Router@baofeng-tech
#router#aisa

Native-first ClawHub plugin for llm-router. Ships the packaged AIsa skill with an openclaw.plugin.json manifest and a Claude-compatible bundle fallback. Use AIsa for model routing, provider setup, and Chinese LLM access. Use when: the user needs model configuration, provider guidance, or routing workflows. Supports setup and model operations.

129
Cn LLM@bibaofeng
#aisa#model-routing

Native-first ClawHub plugin for cn-llm. Ships the packaged AIsa skill with an openclaw.plugin.json manifest and a Claude-compatible bundle fallback. Use AIsa for model routing, provider setup, and Chinese LLM access. Use when: the user needs model configuration, provider guidance, or routing workflows. Supports setup and model operations.

112
Louter — Lite Router@liseman
#local-llm#model-routing

Keep simple replies local. Choose a model explicitly. Ask your configured models in parallel and retain their full answers.

11