Local AI Advisor
wllama local inference with explicit dictionary fallback.
Read Guide →AI & Compute
Local inference, model management, and AI guidance.
Active Models
Llama-3-8B (Local)
readywllama
Phi-3-Mini (Local)
idlewllama
Bonsai (Cloud)
generatingopenai
Mistral-7B (Local)
loadingwllama
AI & Compute Guides
Compute Donation Page
Consent-first Web Worker compute for BOINC/Cocoon-style workloads.
Read Guide →Compute Resources
Cocoon
Distributed edge compute for decentralized AI fine-tuning.
PrismML Bonsai
Ultra-efficient ternary quantized LLM for edge inference.
Nous Hermes
Advanced function-calling & agent orchestration models.
llama.cpp
LLM inference in pure C/C++ for CPU-only deployment.
Internet Archive
Digital library of millions of free books & media.
arXiv
Open-access preprints for scientific papers.
Kiwix
Offline content reader for ZIM file archives.
Khan Academy
Free world-class education for anyone, anywhere.
Wikipedia
Free, multilingual encyclopedia (offline via Kiwix).
OpenStax
Peer-reviewed, openly licensed university textbooks.