Developer Tools1 week ago
WatchMachineGo
Visualize hardware performance metrics while running LLM inference on your system.
dev_dan_2 · HN
WatchMachineGo – A visualizer to show hardware performing LLM inference
The full gallery
Tech stack
21 projects
Visualize hardware performance metrics while running LLM inference on your system.
dev_dan_2 · HN
WatchMachineGo – A visualizer to show hardware performing LLM inference
Run LLM inference on consumer GPUs with NVIDIA TensorRT-LLM optimization.
brianhabana123 · HN
TensorRT-LLM running natively on Windows (no WSL)
Compare and evaluate AI models across coding, reasoning, agents, and other benchmarks.
davidtsong · HN
Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities
Fine-tune LLMs with your data, teach and erase custom facts, get cryptographic deletion proofs.
@MBrew26730 · X
Dataset cleaning + fine tuning + continual learning at
Find AI models optimized for your hardware with performance and pricing estimates.
cdnsteve · HN
Tokenstead, find AI models for your hardware
Compress prompts and reduce LLM token costs by detecting duplicate tool calls.
@DeveloperL92487 · X
I built my first app in 60min And now I got $500 MRR in one month Check here if you are interested It’s a tool to reduce agent token consumption, speed up agent response, and clean up memory cache
Monitor AI model calls, agent steps, and retrieval with token tracking, cost analysis, and latency metrics.
ephraimduncan · HN
Observability for Coding Agents and LLM Applications
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 ⬇️
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～
Compare AI coding models on real tasks with live previews, cost tracking, and ELO rankings.
@intheworldofai · X
On the World of AI Bench (vibe-coding composite): Claude Fable 5 → 85.2 GPT-5.6-sol → 82.4 kimi-k3 → 81.5 Moonshot’s K3 just walked in and claimed bronze on one of the toughest coding-focused leaderboards out there.
Interactive LLM chat interface running on Enclave's confidential compute platform.
SteveDeFacto · HN
Hi HN, I built Enclave, self-serve confidential compute on GPUs. Technical documentation is on the site, but I'd rather show than tell. Here are a couple apps hosted live on the platform: LLM Chat bot: https://cc1f4f3f.app.enclave.host AI Image Generation: https://da09d0f2.app.enclave.host If you have any questions, I would be more than happy to discuss.
Daily digest of AI/LLM news and model launches from 100+ sources.
jonam21 · HN
KBlip – turns AI/LLM news across 100 sources into daily digest threads