Developer Tools2 weeks 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
26 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
Real-time LLM-powered news aggregator surfacing trending stories with live updates.
tdubey · HN
DWS A LLM Generated, "Drudge Report" style news site
Run LLM inference on consumer GPUs with NVIDIA TensorRT-LLM optimization.
brianhabana123 · HN
TensorRT-LLM running natively on Windows (no WSL)
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
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
Compare and evaluate AI models across coding, reasoning, agents, and other benchmarks.
davidtsong · HN
Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities
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.
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 ⬇️
See the concepts a language model holds at each layer before it answers.
ada1981 · HN
I built a web tool to see and edit what an AI thinks before it answers
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
Analyzes news articles to verify whether conclusions are supported by evidence.
@BiaoBuilds · X
我做了一个帮助读者拆解新闻论证结构的工具：LedeLens。 它不做事实核查，也不判断政治倾向，只回答一个更小的问题：文章的结论，能否由它自己提供的证据支持？ 在线体验： 感兴趣可以看看~