AI & ML interests

AI assistants, AI agents, coding agents, voice AI, multimodal AI, AI research, evaluation and benchmarks

Recent Activity

torkehub-team  updated a Space 2 days ago
TorkeHub/README
torkehub-team  published a Space 2 days ago
TorkeHub/torki-2-benchmarks
torkehub-team  published a dataset 2 days ago
TorkeHub/torki-2-evals
View all activity

Organization Card

TorkeHub — we build AI that does the work

Try Torki TorkeHub App Store Google Play Torki on X TorkeHub on LinkedIn

We build AI that does the work.

TorkeHub makes Torki, one AI assistant that answers, researches, makes images, builds prototypes and decks, runs code and takes on work you hand it — and Torki Code, a coding agent for real software work.

Torki runs on our own models, on machines we own and operate, and it works on the web, iPhone, iPad, Android and Mac, all on one account.


Torki — ask the hard ones. Torki works it out.

Torki reading a 38-page contract and flagging the one clause that matters
What it does
💬 Chat Ask anything, with web search and four modes — from Pulse (fast) to Cosmos (maximum capability).
🔎 Research Searches first, then answers with its sources.
🎙️ Voice Talk to Torki in real time, with seven companions to choose from.
🖼️ Vision Reads photos, screenshots and charts, and makes images.
🧩 Forge Turns a description into a landing page, dashboard, prototype or pitch deck — no code needed.
🧑‍💻 Canvas Writes and runs code and documents side by side.
🤖 Agents Hand off multi-step work and let it run.
🗂️ Projects Keep files, chats and instructions together.

Try Torki free → torkiai.com


Torki Code — tell it what's broken. It fixes it.

Torki Code tracing a crash, patching one line and running the tests

Ask in plain language and Torki Code plans the change, edits the files, runs the commands and tests, and reports back. On Mac today, with Windows and Linux coming.


On Hugging Face

Torki 2's benchmark results are here: 22 public benchmarks, measured on the same model and settings Torki users get, with exactly how each one was run and the per-question result behind every score.

  • 📊 Torki 2 evaluations (dataset): every score, per-question results, and each comparison number with its source
  • 🏁 Torki 2 benchmarks (Space): Torki 2 beside 29 models from Anthropic, OpenAI, Google, Meta, xAI and labs in China and India, all 22 results, and six projects Torki 2 built from a single prompt

Follow TorkeHub to see them first.

models 0

None public yet