开发者工具1 month ago
WatchMachineGo
实时可视化硬件在运行LLM推理时的性能指标
dev_dan_2 · HN
WatchMachineGo – A visualizer to show hardware performing LLM inference
完整作品展
技术栈
60 projects
实时可视化硬件在运行LLM推理时的性能指标
dev_dan_2 · HN
WatchMachineGo – A visualizer to show hardware performing LLM inference
检查LLM权重张量的交互式工具，支持量化误差和分布分析。
alesha-pro · GitHub
atlas Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels for every weight tensor
多智能体LLM系统的可视化编辑器，支持本地推理。
sascha10000 · HN
Multi-agent LLM editor with local inference via WebSockets
The end-to-end platform for small language models. Tuned to your task, a small open model matches frontier accuracy at a fraction of the cost. Own your intelligence: private, compa
@dayoffdev · X
追踪100+来源的AI和LLM新闻和模型发布。
jonam21 · HN
KBlip – turns AI/LLM news across 100 sources into daily digest threads
为中国财经网站新闻添加 AI 解读按钮，支持多个 AI 模型。
EliteOtaku · V2EX
搞了个解读财经数据的油猴脚本，适配金十，财联社，汇通，华尔街见闻 比较简单，但挺好用的，在快讯旁边加了一个 AI 按钮，点击后由 AI 解读该新闻/数据的影响，需自己准备 API key，支持 DeepSeek 和 OpenAI、Anthropic 格式 https://greasyfork.org/zh-CN/scripts/590009-%E9%87%91%E5%8D%81%E6%95%B0%E6%8D%AE%E5%87%80%E5%8C%96-ai-%E8%A7%A3%E8%AF%BB-deepseek
开源LLM和视频模型的OpenAI兼容API
bingus-bongo · HN
Use GLM-5.3 in Cursor today via tokengo API
为LLM输出提供token级引文API，通过注意力分析验证。
apoorvumang · HN
TokenPath – token-level citations for LLM output, read from attention
对比语言模型在 Redactle 谜题上的表现排名。
pampas · HN
Redactle LLM Leaderboard
通过OrcaRouter为200+个LLM提供自适应路由和负载均衡
Continuum-AI-Corp · GitHub
OrcaReplay OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.
通过调整限流规则看AI提供商如何在需求激增时分配强模型。
eliotho · HN
I built a tool showing how AI providers (should) throttle their models
