Developer Tools1 week ago
Solheim — your own EU-hosted LLM instance, no reset timer
Host a dedicated LLM instance in the EU with flat-rate pricing and no usage limits.
CodingPanda42 · HN
Virtual Private LLM, fixed fee with no usage or token limits
The full gallery
Tech stack
60 projects
Host a dedicated LLM instance in the EU with flat-rate pricing and no usage limits.
CodingPanda42 · HN
Virtual Private LLM, fixed fee with no usage or token limits
Write, organize, and run prompts across multiple AI platforms in one interface.
@promptboxxx · X
Have all your AIs in one place and never repeat a prompt
Ready-made AI prompts you can save and use anywhere through a Chrome extension.
@thehitechnomad · X
Stop typing! Discover a cloud-based prompt repository built with Lovable, featuring all the tools you need. Get access now at #AIprompts #TechTools
Turn your app idea into a detailed prompt for AI coding agents and builders.
@AjonyePaul · X
Your AI coding agent isn't lazy. Your prompts are just too vague. I just launched IdeaPrompt to interview you like a product engineer and catch the edge cases you missed. Try it: What are you building today? 🛠️ #AI #buildinpublic #coding
Real-time LLM-powered news aggregator surfacing trending stories with live updates.
tdubey · HN
DWS A LLM Generated, "Drudge Report" style news site
Deploy serverless AI models with a single line of code at competitive rates.
Synexa AI — 一行代码部署 AI 模型 (Replicate 50% 低价平替)，Synexa 是运行无服务器 AI API 最具性价比的解决方案，提供业界最具竞争力的 A100 GPU 价格，相比其他服务商可节省高达 62% 的 AI 算力成本 - [更多介绍](https://github.com/1c7/chinese-independent-developer/issues/47
Organize prompts, character settings, and visual descriptions for AIGC projects locally.
innerpeace03 · V2EX
做了个管 AIGC 提示词的本地工作台 —— Prompt Studio 先放地址（纯静态、无后端，打开即用）： https://prompt-studio-7gh.pages.dev ## 为什么做这个 起因是身边一个做漫剧 / AI 短视频的朋友，她的 prompt 和素材全靠飞书文档 + 手动复制粘贴管理。 同一段角色设定、画风描述，在几十条 prompt 里被物理复制了几十遍 —— 真实样本里同一段片段重复出现了 16 次。 改一个设定就得全文档翻着改，漏一处就出错。 市面上要么是「以图为中心」的图库（ MJ / Civitai 那种），要么是通用文档（ Notion / 飞书）， 都没解决「同一段提示词在很多地方被重复、想改一处就同步所有引用」这件事。所以自己动手做了一个。 ## 它是什么 一句话：浏览器里运行、数据全在本地、单人用的「提示词 + 素材」工作台。 核心就一件事 —— 消灭 prompt 片段的物理重复： - 片段层 + 规则层两级可复用资源，prompt 里用「引用」而不是复制粘贴 - 改一次片段，所有引用它的
Route your LLM API requests across multiple providers to cut costs and meet latency targets.
Aperswal · HN
Made a Free LLM Router
Manage and run LLM models in your browser via WebAssembly.
userfrom1995 · HN
Goku – WASM (wllama)-powered LLM inference and model manager
Jira plugin for managing test cases, requirements, and execution with traceability.
@pakosteve · X
Improve your SaaS quality when scaling (by register requirements and test via MCP)
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)
Visual editor for configuring multi-agent LLM systems with local inference.
sascha10000 · HN
Multi-agent LLM editor with local inference via WebSockets