AI/ML●●●Banger
N0x – LLM inference, agents, RAG, Python exec in browser, no back end
Full ReAct agent loop running locally with WebGPU and Pyodide—no server required.
WizardryZero to OneSlick
redhanuman
903mo ago
Back to browse
I wrote a 1-bit WebGPU runtime to run a 1.7B LLM in the browser
by stfurkan·Jul 7, 2026·3 points·1 comment
AI Analysis
●●●BangerWizardryZero to OneBold Bet
1.7B LLM running entirely in-browser with WebGPU—no servers, no API keys, no per-message costs.
Strengths
- •Inverts cloud-AI deployment assumption by running model on visitor's device.
- •One script tag integration with zero backend or billing setup required.
- •Local RAG keeps user data in-browser with no privacy trade-offs.
Weaknesses
- •290MB one-time download may impact page load on slower connections.
- •WebGPU browser support limits compatibility to modern devices only.
Category
Target Audience
Website owners wanting on-device AI chat widgets
Similar To
WebLLM · Transformers.js · Off Grid AI
Similar Projects
AI/ML●●Solid
Nexa-gauge – Cache/cost-aware graph-based eval for LLM and RAG
Cache-aware execution cuts eval costs while tracking grounding and relevance metrics.
Solve My ProblemSlick
Sardhendu
301mo ago
Developer Tools●●Solid
Argmin AI, system level LLM cost optimization for agents and RAG
LLM cost optimizer, but Anthropic's batch API and local quantization solve this cheaper.
Solve My ProblemBig Brain
konyrevdmitriy
204mo ago
AI/ML●Mid
A calculator to expose the hidden infrastructural costs behind RAG
Breaks down hidden RAG costs like vector storage overhead and HNSW indexing fees.
Solve My Problem
abarth23
202mo ago
AI/ML●●Solid
Doppler.js – WebGPU inference, faster/simpler than transformer.js
Explicit kernel control over TVM-style black boxes, but benchmarks show mixed wins vs Transformers.js.
Big BrainWizardry
clocksmith
304mo ago
AI/ML●●Solid
AI support chatbot with RAG and citations – one back end file, no infra
One-file RAG chatbot backend when Chatbase and CustomGPT already dominate this space.
Big BrainShip It
anupsing_ai
902mo ago