CINCO ID: Cinco Identity Generator 2.5. A talking Win95-style computer that loads dancing sequences, opens far too many windows and can do real work. Unofficial fan tribute.

Audio-visual live performance monorepo : SuperCollider sound engine + openFrameworks Hantek oscilloscope visualizer + macOS SwiftUI launcher

A native Rust engine for the Strudel pattern language

ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.

Procedurally generated Delft-blue floral page margins for LuaLaTeX, with plants and visitors sampled from genomes and a TikZ library that also draws them under pdfLaTeX

The open source AI video agent: turns any coding agent into a video agent, with an editor to change anything it makes.

Open-source virtual microscope lab: real microorganisms, cell cultures and plant tissues whose life emerges from physics (soft bodies, low-Reynolds fluid, chemistry). Reproducible and measurable, f…

Bi-hemispheric synthesis of ultrametric p-RoPE sparse attention (Gemma 4 31B, Llama 3.1) & neuromorphic test-time reasoning. Solves 38/400 ARC-AGI-1 & 25/25 ARC-AGI-3 games (63/183 levels, 4 full w…

rust tool to choose the best read alignment between haploids to a diploid reference genome

Complete Lean formalization of deterministic O(n^1.962) integer 3SUM.

An open-source, cross-platform, node-based realtime visual programming environment in the spirit of TouchDesigner. Rust + wgpu.

PhotoCraft: An open-source photo editor written from scratch in pure Rust

Cross-vendor 3D Gaussian Splatting trainer - video to splat to mesh, Vulkan or CUDA.

One-click photogrammetry. Turn photos into 3D models using the latest COLMAP + OpenMVS — no command line needed.

State-of-the-art bio cell models for inference and training. Minimal, readable, and produciton-ready.

Cherimoya is a lightweight sequence-to-function (S2F) model that is small, fast, and easy to use. Now usable by agents.

Open, Jev-compatible System One decision server on DiffusionGemma

A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness

Diarization scoring on 15 frozen PriMock consultations: explicit speaker policies, reproducible baseline scores of Open Source and API-based models.

Topic-tree memory for the Pi coding agent: topic-projected context with on-demand recall

Pangenome simulator

Controller-optimized fork of Whisper To Input for hands-free AR terminal workflows

Unitig Resolution and Assembly

Implementation of the Suffixient-Array index

Lightweight headless WebKit browser designed for agents first

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.