Developer Tools3 weeks ago
Glaux
Run Hugging Face ONNX models directly in your browser using WebGPU.
Open source
granganath · HN
Glaux – Browser-Only AI for Hugging Face ONNX Community Models
The full gallery
Tech stack
60 projects
Run Hugging Face ONNX models directly in your browser using WebGPU.
granganath · HN
Glaux – Browser-Only AI for Hugging Face ONNX Community Models
Manage and run LLM models in your browser via WebAssembly.
userfrom1995 · HN
Goku – WASM (wllama)-powered LLM inference and model manager
Compress prompts before LLM API calls to reduce token usage and costs.
@asgujjuasitgets · X
Compare AI language models by performance across official benchmarks.
fcten · V2EX
做了一个大模型 leaderboard 网站 最近一个月 CodeX 疯狂送重置，token 根本用不完，顺手做点东西。 地址：[知行录]( https://leaderboard.cn/) 排行依据主要为模型官方基准测试成绩。非主观排名。 数据会持续更新。如果有点用，欢迎各位 v 友收藏～
Detect if your LLM API has been model-swapped or degraded with 6 deterministic probes.
cocodot LLM 降智检测 — 免费的 LLM API「降智/偷换模型」在线检测：填入任意 OpenAI 兼容端点的 base_url 和临时 API Key，跑 6 项探针（模型声明、动态题、能力完整性等）生成分项报告；Key 仅用于当次检测、不落库不留存，检测方法[开源](https://github.com/cocodot2026/cocodot-llmprobe)
View LLM model rankings across 10 benchmark questions.
fristovic · HN
She watched me look at model rankings and asked what do the numbers mean... I literally had no good way of explaining it to her so I just came up with something that is approximately in the same ballpark as some of the benchmarks out there lol
Compress LLM prompts and documents to reduce token usage and API costs.
@marcusyul · X
THEY JUST GAVE AWAY 100 MILLION FREE TOKENS SO YOU CAN STOP BURNING THROUGH YOUR CLAUDE CODE BUDGET. if you code with AI you already know: the session fills up, starts failing, and on top of that you're overpaying there's a tool that fixes this: it shrinks the context before the model even sees it same model, same response, a fraction of the cost in a real session: from $154 to $43. a 72% drop and right now: → extend your Fable sessions in Claude Code → 100M free tokens to try it out you don't switch models you don't touch your code you just stop paying to repeat yourself link below ⬇️
Analytics dashboard for LLM API spending by model and environment with optimization suggestions.
ATsimbalistov · HN
Show HN: Tracking GenAI cost and endpoint fragility so app teams don't have to
Agent-native TypeScript framework that trains and deploys custom ML models on managed GPUs.
@soleil_colza_ · X
Analyze Go games with KataGo AI on cloud GPUs, compatible with KaTrain.
malusama · V2EX
[分享创造] 给没有显卡的棋友：一个可直接接 KaTrain 的云端 KataGo 服务 电脑没显卡，或者笔记本跑不动全盘复盘，但想用 KaTrain 分析棋谱？我做了一个云端 KataGo 服务，KaTrain 里只需要填一个 WSS 地址。 ## 怎么接入 - 注册后拿到 Token： https://go.malu.moe - KaTrain v1.18+ 的设置里，Remote Engine 填：`wss://go.malu.moe/v1/katago/<你的 Token>` - 走的是标准 KataGo Analysis Engine JSON over WebSocket ，复盘、深度分析、Sweep 这些功能都兼容 - 不想用 GUI 的话也有 REST 接口：`POST /v1/analyze` ## 免费额度（注册即用，不用绑卡） - 单次分析最多 1,000 visits - 每月 1,000,000 visits ，按 KaTrain 默认 500 visits/手算，大约够 10 局全盘复盘 - 并发 1 ，最多 5 个 Token
Fine-tune LLMs with your data and manage custom facts with cryptographic deletion proofs.
@MBrew26730 · X
Dataset cleaning + fine tuning + continual learning at
Run multiple AI models side by side using your existing API subscriptions.
@ContinuumCode · X