Tools that work with Hugging Face — how many are there?

Tablif is tracking 8 of them. 8 answered our check today.

Which ones are still maintained?

Tablif knocks on every door once a day and records the answer. 8 of these 8 responded on the latest run, so that number is what "still here" means on this page — not a review score.

Are any of them free?

2 of the live ones say so in their own words, and 1 let you start without making an account. Tablif records the claim the product makes; we don't verify pricing.

Any open-source options?

2 of the live ones on Tablif mention being open source.

What's the newest one?

Was It Built? — Tablif first saw it 3 days ago.

Did a person actually look at these?

8 of them Tablif opened and read, then wrote a one-line summary in our own words instead of reusing the founder's tagline. The rest carry keyword labels we haven't confirmed by reading yet — and we say so rather than hiding it.

Tools that work with Hugging Face

We're tracking 8 of these, and 8 are still live today.

Watching this group for 17 days · how we check

This week2 new arrivals

Narrow it down

Doesn't mention AI1 Free2 No sign-up1 Works offline1 Open source2 No subscription2

Super arXiv

Live

A Chrome extension that turns arXiv into a research workspace by auto-renaming PDFs and linking papers to GitHub, Hugging Face, and Scholar.

What to know▼

How it works: organizes papers, auto-renames PDFs, surfaces related GitHub/Hugging Face/Scholar links and citation info
Best for: researchers managing a personal paper library

Watched for 3 days · last checked 2d ago

Details →

Umbra

Live

An OpenAI/Anthropic-compatible API where Apple Silicon Mac owners host open-weight Hugging Face models for pay-per-token access. Built for developers who want hosted access to niche open models without renting a GPU.

Domain registered 1 month ago

What to know▼

How it works: An OpenAI- and Anthropic-compatible API endpoint where Apple Silicon Mac owners host approved open-weight Hugging Face GGUF models; you swap your base_url, keep your existing client, and pay per token.
What's different: Gives hosted API access to open-weight models that otherwise have no hosted API, without renting a GPU yourself.
Pricing: Pay per token.
Best for: Developers who want hosted access to niche open-weight models without running their own GPU or leaving a Mac on overnight.
Watch out: Described by its maker as 'my experiment' — inference runs on community-hosted Apple Silicon Macs rather than dedicated infrastructure.

Watched for 13 days · last checked 7d ago

Details →

AIVory Smart Inference

Live

A hosted LLM inference router that's a drop-in replacement for the OpenAI API, automatically sending each request to the cheapest healthy provider. Aimed at developers who want lower inference bills without code changes.

No subscription

What to know▼

How it works: An LLM inference router and GPU marketplace that acts as a drop-in replacement for the OpenAI API, automatically routing each request in real time to the cheapest healthy provider serving the requested model.
What's different: Continuous automated price discovery across providers, rather than a fixed rate you sign up for once.
Pricing: No subscription.
Best for: Developers who want lower LLM inference bills without changing their SDK or code.

Watched for 9 days · last checked 3d ago

Details →

Tilino Chat

Live

An Android app that runs LLMs entirely on your phone with no data leaving the device, plus a built-in tool to search and download models from Hugging Face.

Works offline

What to know▼

How it works: An Android app, built with Rust and Tauri, that runs large language models fully on-device, supporting text and vision models, with a built-in tool to search and download models from Hugging Face.
What's different: Runs models entirely locally with no user data collected, rather than calling a cloud API.
Best for: Android users who want to run LLMs on their phone without their data leaving the device.

Watched for 16 days · last checked 2d ago

Details →

Stickblade Arena

Live

Two LLMs control stick-figure fighters with swords in a real physics simulator and you vote on who fought better — a playful but genuine benchmark for comparing model tactical reasoning.

FreeNo sign-upOpen source

What to know▼

How it works: Two LLMs control 2D stick-figure fighters in a real physics simulator, each receiving a JSON snapshot of the world every 3 seconds and choosing an action within 15 seconds; users pick the weapon and vote blind on who fought better, with per-weapon, per-zone Elo rankings.
What's different: Server-side randomization of which ragdoll is which color keeps voting unbiased, turning a joke concept into a tactical-reasoning benchmark.
Pricing: Free, no account required, open source.
Best for: People interested in comparing how different LLMs plan multi-turn tactics, in a more entertaining format than typical chatbot arenas.

Watched for 16 days · last checked 10d ago

Details →

Was It Built?

Live

Checks whether a software idea already exists by scanning app stores, GitHub and Hugging Face, then gives a launch blueprint if there's a gap.

Free

What to know▼

How it works: Scans the Apple Store, GitHub, Hugging Face, and package registries to score whether a typed idea already exists as Done, Partial, or Novel, then gives a market read, launch blueprint, and a paste-ready prompt for your AI builder.
Pricing: Search is free; the first 250 users get 30 credits with code LAUNCH30.

Watched for 2 days · last checked 2d ago

Details →

Forrrge

Live

A native Mac and iPad app for quickly generating AI app-icon and thumbnail ideas — you supply your own AI key and pay the provider directly, for a one-time $2.99.

Pay onceNo subscription

What to know▼

How it works: A native Mac and iPad app where you type an idea, pick a style, and get generated app-icon or thumbnail directions back, using your own AI key from Google, OpenAI or Hugging Face.
What's different: You bring your own AI key and pay the provider's real cost directly instead of a subscription, credits, or per-image fee; keys stay in your Keychain.
Pricing: $2.99 one-time purchase, covers both Mac and iPad.
Best for: Designers and developers generating app icons and thumbnails who want to avoid recurring generation fees.

Watched for 17 days · last checked 2d ago

Details →

MDMA - GenUI for apps

Live

An open-source Markdown extension that lets LLMs output interactive UI — forms, tables, approval gates — instead of plain text, shipped with a CLI and MCP server for developers.

Domain registered 1 month ago

Open source

What to know▼

How it works: An open-source Markdown extension (fenced ```mdma``` blocks) that lets LLM output render as interactive UI — forms, tables, approval gates, charts, callouts, webhooks — instead of plain text. Ships component renderers for React and React Native, a validator, prompt packs for OpenAI/Anthropic/Google/xAI, a CLI, and an MCP server.
What's different: Deterministic parsing with a headless runtime that includes an audit log and PII redaction.
Pricing: Open source, MIT license.
Best for: Developers building chat interfaces who want LLMs to output structured, renderable UI components rather than plain text.

Watched for 13 days · last checked 2d ago

Details →

Tools that work with Hugging Face — the short answers

Every number here comes from our own daily check — not from a vendor list.

Tools that work with Hugging Face — how many are there?: Tablif is tracking 8 of them. 8 answered our check today.
Which ones are still maintained?: Tablif knocks on every door once a day and records the answer. 8 of these 8 responded on the latest run, so that number is what "still here" means on this page — not a review score.
Are any of them free?: 2 of the live ones say so in their own words, and 1 let you start without making an account. Tablif records the claim the product makes; we don't verify pricing.
Any open-source options?: 2 of the live ones on Tablif mention being open source.
What's the newest one?: Was It Built? — Tablif first saw it 3 days ago.
Did a person actually look at these?: 8 of them Tablif opened and read, then wrote a one-line summary in our own words instead of reusing the founder's tagline. The rest carry keyword labels we haven't confirmed by reading yet — and we say so rather than hiding it.