llm gpu fit
by Postlethwaite Labs
Stop OOM crashes with architecture-aware VRAM estimation and 3-way agent compatibility checks for local LLMs.
Practical AI agent skills for people who build and run things. Postlethwaite Labs ships tools that route models across cloud and local GPUs, watch the vulnerability landscape, aggregate threat intelligence, and automate daily briefings. Built from real-world use: self-hosted AI in production, cybersecurity operations, and single-operator automation.
by Postlethwaite Labs
Stop OOM crashes with architecture-aware VRAM estimation and 3-way agent compatibility checks for local LLMs.
by Postlethwaite Labs
Automated pipeline to scrape sources, generate branded PDFs, and deliver daily reports via email and cron.
by Postlethwaite Labs
Route AI tasks across providers with automatic fallback.
by Postlethwaite Labs
Automated OpenRouter price monitoring and alerts with zero recurring token costs.
by Postlethwaite Labs
End-to-end guide for publishing, securing, and updating AI agent skills on the Agensi marketplace.
by Postlethwaite Labs
Generate production code with a local LLM on the GPU you already own. Spec-driven codegen via LM Studio/Ollama/vLLM, with auto model-loading, a 13-bug review checklist, and a working genfile script — all model-agnostic.
by Postlethwaite Labs
A zero-API-key security toolkit for CISA KEV monitoring, threat news aggregation, and update decision-making.
by Postlethwaite Labs
Turn your AI agent into a game master for text adventures, trivia, riddles, and classic word games.
by Postlethwaite Labs
Aggregates and deduplicates live cybersecurity threat intelligence from five major news sources into a single feed.