local-llm-routerLocal LLM model router for Llama, Qwen, DeepSeek, Phi, Mistral, and Gemma across multiple devices. Self-hosted local LLM inference routing on macOS, Linux, a...
Install via ClawdBot CLI:
clawdbot install twinsgeeks/local-llm-routerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:11435/dashboard/api/settingsCalls external URL not in known-safe list
https://github.com/geeks-accelerator/ollama-herdAI Analysis
The skill's external calls are to its own local dashboard API and its public GitHub repository, which are consistent with its stated purpose of managing local LLM routing. There is no evidence of unauthorized data exfiltration, credential harvesting, hidden instructions, or obfuscation.
Audited Apr 16, 2026 · audit v1.0
Generated Oct 8, 2026
A software team runs Ollama on a mix of Mac Studios, Mac Minis, and Linux GPU servers. They route all coding assistant requests through the local LLM router to avoid manual model switching and to keep latency low during peak development hours.
A mid-size SaaS company hosts local Llama and Qwen models on bare-metal GPUs to power an internal support assistant. The router balances requests across nodes so no single machine is overwhelmed, and context protection prevents expensive model reloads during long chats.
A clinic network uses local DeepSeek and Mistral models to summarize patient notes without sending data to the cloud. The router scores nodes based on memory fit and historical latency to ensure sensitive inference stays on-premises and responds predictably.
A university AI lab shares GPU workstations across graduate students running varied local LLM benchmarks. The router load-balances jobs, tracks model performance via SQLite, and provides routing traces so researchers can compare latency across hardware.
A factory deploys local Phi and Gemma models on rugged edge devices to inspect products in real time. The router routes inference requests to the least busy node with the right model already hot in memory, keeping production lines responsive without internet dependency.
Offer businesses a fully managed local LLM router deployment, including installation, node configuration, monitoring, and updates. Customers pay a monthly subscription per node or per seat, avoiding cloud LLM API costs and data privacy risks.
Provide expert consulting to help enterprises optimize their existing Ollama fleets using the router's 7-signal scoring engine. Services include latency audits, hardware recommendations, custom scoring weight tuning, and integration with internal tools.
Distribute the core router as open-source (ollama-herd) to build adoption, then sell premium features like advanced dashboards, multi-tenant management, SSO, audit logging, and priority support to larger organizations.
💬 Integration Tip
Start by installing ollama-herd on the router machine and herd-node on each device, then point your OpenAI-compatible client to http://localhost:11435/v1 before tuning scoring weights or context protection settings.
Scored Oct 8, 2026
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
使用豆包(火山引擎)语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色(S_ 开头的音色ID)和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时,务必使用此 skill。即使用户只是说"帮我把...
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...
自动生成科技新闻摘要。从多个来源(RSS、Twitter、GitHub、Web Search)抓取科技新闻,整合后生成摘要。
让 AI 代理根据对话内容自动选择最合适的模型。四层识别(系统过滤→关键词→指示词→语义相似度),四池架构(高速/智能/人文/代理),五分支路由,全自动 Fallback 回路。支持 trigger_groups_all 非连续词组命中。
OpenAI API integration — chat completions, embeddings, image generation, audio transcription, file management, fine-tuning, and assistants via the OpenAI RES...