Publish your app to managed hosting with one command; compare LLM cost/latency with real metered billing; PDF translate, cited research, PPTX — one MCP server.
This diagram is itself rendered by the service — a stateless image URL, no request needed to build it.
npm/PyPI READMEs don't render mermaid; this does.
Hosted open-source AI apps, callable by your agent over MCP — and from your terminal.
npx ai-netcafe compare "dedupe a JS array preserving order"
MODEL COST LATENCY
deepseek-v4-flash $0.00012 7.6s
gemini-3.5-flash $0.000341 10.0s
GLM5.2 $0.001828 9.0s
cheapest: deepseek-v4-flash fastest: deepseek-v4-flash
15.2× between cheapest and priciest
Every number above is read from the upstream usage response, not derived from a
published price list. That distinction matters more than it sounds — while building
this we found the obvious conversion formula was wrong for several models
(one was off by ~9×, another by ~3×), and only billing-delta measurement matched
reality. Full method and data.
npx ai-netcafe install # prints config for Claude Code / Desktop / Cursor
Or directly:
claude mcp add --transport http ai-netcafe https://ainetcafe.com/mcp
| Skill | What it does |
|---|---|
compare_models | One prompt across many LLMs, with real metered cost + latency |
translate_pdf | Translate a PDF keeping formulas, figures and two-column layout intact |
deep_research | Plans sub-questions, searches, reads sources, writes a cited report |
make_slides | Generates a real downloadable .pptx |
list_apps / get_app | Catalogue of the hosted open-source apps, with source repos |
ask_model / list_models | Single model call; model list with prices |
Backed by open-source projects — PDFMathTranslate, GPT Academic, GPT Researcher, NextChat, LobeChat — hosted pre-configured so you can try them without installing Docker, Python, or supplying an API key.
npx ai-netcafe compare "<prompt>" # multi-model comparison with real costs
npx ai-netcafe ask "<prompt>" # single model
npx ai-netcafe apps # hosted apps + source repos
npx ai-netcafe models # models with per-million prices
npx ai-netcafe install # MCP config for your agent
Anonymous calls get a small free quota — enough to try. Heavy skills (whole-PDF translation, deep research, slide generation) need an account or your own key, because one of those runs costs dozens to hundreds of model calls.
export ALLROUTER_API_KEY=sk-... # unlimited, billed to you
MIT
FAQs
Zero-dependency client + framework-neutral tools for AI agents: Excel/xlsx read-write, bank reconciliation without shared keys, entity dedupe with tax-ID checksums, US HS/HTS codes, diagrams, web search reachable from mainland China. Anonymous free quota,
We found that ai-netcafe demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Security News
GitHub Actions now supports cache-mode, a least-privilege control on the Actions cache aimed at the cache poisoning technique behind recent compromises.
Company News
Allow myself to introduce... myself.
Research
/Security News
A Twitch browser extension on Chrome and Firefox forwards users’ live OAuth session tokens through proxies controlled by a Russian bot service.