Source code for the Claude Opus 5.5 music video for I'm Upping My P(doom)

A painted music video for "Functional Emotions", made by Claude Opus 5.5: custom GPU brushstroke renderer, storyboard, and 7 parallel chapter agents.

Ask an open vision-language model typed questions about an image and get probabilities back, on your own machine.

JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.

Jev powered call coach

Auto-detect AMD GPUs on Windows/Linux and instantly get the correct HSA_OVERRIDE_GFX_VERSION for local AI (ROCm/HIP).

Guardrails for Pi that steer instead of interrupt: enforces your project rules on every write, holds only hard-to-undo actions (3 per 1,000 calls, measured on real sessions), catches unverified "do…

A local inference engine for Apple silicon, built around the model.

Measures which LLM serving settings pay off on your GPU and your traffic, then serves the winner. Benchmarks vLLM, SGLang and llama.cpp configurations; one OpenAI-compatible AP

Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

Electron GUI app for the pi coding agent runtime

Fastest and cheapest web agent

Lean formalizations related to the Riemann hypothesis

Net Worth and Tax Tracker

C++ ggml runtime hub for multilingual ASR and TTS models: Cohere Transcribe, Parakeet TDT, Voxtral, Canary 1B v2, etc, plus universal forced alignment, and more

PyTorch implementations of modern open-source LLM architectures (Llama, Qwen, DeepSeek, Gemma, GPT-OSS, Kimi, and more) — written from scratch for readability and learning, based on Sebastian Rasch…

Open source, clear, transparent, real world llm benchmarks

Cross-platform local MCP capabilities for ChatGPT with Chrome integration, Goal, Compact & Resume, and durable multi-agent workflows.

A drop-in CLAUDE.md style section that changes how Claude writes prose.

The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; benchmarks vs llama.cpp in the README.

Compile agent conversations!

My own personal evaluation harness

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and supp…

AiO webtools for Pi: Search, Fetch, Pull | no API keys

Perplexity open source garden for inference technology

GLM-5.3 Flash EXL3 for 2-4x DGX Sparks

Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards