Open-source toolsWorks with Hugging Face

3 match your filters — 3 of them answered our check today.

Watching this group for 20 days · how we check

This weekno new arrivals

Narrow it down

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 14 days · last checked 2d ago

Details →

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 17 days · last checked 11d ago

Details →