Agent skill that removes signs of AI-generated writing from text

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.

docx ↔ LLM translator. Projects .docx office files to Markdown for editing. Projects edits back to OOXML as tracked changes (redlines). Python and Node.js implementations.

Skills for Real Engineers. Straight from my .agents directory.

Self-hosted Error Tracking

A curated list for awesome discrete diffusion models resources.

Industrial design files for Keychron keyboards and mice. 100+ models with CAD assets in STEP, DXF, DWG, and PDF. Source-available, with commercial use allowed for original compatible accessories wi…

Late Interaction Models Training & Retrieval

Code for `LLM2VEC-GEN: Generative Embeddings from Large Language Models`

Efficient optimizers

Fast and memory-efficient exact kmeans

UNIX-like reverse engineering framework and command-line toolset.

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Build Real-Time Knowledge Graphs for AI Agents

A minimal, secure Python interpreter written in Rust for use by AI

Anthropic's original performance take-home, now open for you to try!

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

A Chrome DevTools Protocol driver for web automation and scraping.

A fast, standalone terminal music player in Rust: native Spotify streaming plus local, Subsonic, radio, Qobuz and Youtube sources

The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.

CADAM is the open source text-to-CAD web application

Open-source composable lakehouse platform with Spark 4 + Delta Lake 4. Complete local environment ready in minutes via Docker Compose.

LangChain for Go, the easiest way to write LLM-based programs in Go

Windows inside a Docker container.

Our library for RL environments + evals

The programming language for agents

A lightweight LMM-based Document Parsing Model