Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

Exclusively Dark (ExDARK) dataset which to the best of our knowledge, is the largest collection of low-light images taken in very low-light environments to twilight (i.e 10 different conditions) to…

Automated data broker opt-out runner — removes your personal info from 30+ people-search sites on a monthly schedule

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.

Bringing BERT into modernity via both architecture changes and scaling

Get your reservations when others cancel... for OpenTable

One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.

Docker configuration for running VLLM on dual DGX Sparks

Open-source, local-first Granola/Otter alternative that Claude Code, Codex, Cursor, and any MCP client can query. Meetings, calls, and voice memos transcribed on-device into markdown you own.

Autonomous AI pipeline that turns prompts into shipped PRs. CEO agent proposes, plans, implements, reviews, and delivers — all without human intervention.

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

Cactus Kotlin Multiplatform library: Run AI locally in your Kotlin apps

CLI tool to generate terraform files from existing infrastructure (reverse Terraform). Infrastructure to Code

Ready-to-use Media-over-QUIC / SRT / WebRTC / RTSP / RTMP / LL-HLS / MPEG-TS / RTP live media server and media proxy that allows to read, publish, proxy, record and playback real-time video and aud…

An agentic skills framework & software development methodology that works.

End-to-end realtime stack for connecting humans and AI

Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.

Repository for "Introducing CAD: the Contextual Abuse Dataset", Vidgen et al., NAACL 2021

Catalog of abusive language data (PLoS 2020)

Analysis of the evolution of advanced transformer-based language models: experiments on opinion mining

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unita…

A large scale video database for violence detection, which has 2,000 video clips containing violent or non-violent behaviours.

A nearly-live implementation of OpenAI's Whisper.

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

Whisper realtime streaming for long speech-to-text transcription and translation