Structured YAML catalog of 4,587 AI models across 95 providers — pricing, context windows, modalities, capabilities. First-party data with TypeScript types and Zod validation.

Local-first desktop app for running uncensored, refusal-ablated language models. Tauri + Rust + Ollama. 12MB installer, zero telemetry.

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA, full SFT, distillation, and DPO/RLHF alignment.

Curated list of open-source LLM-serving runtimes, routers, evaluators, and standards. Run LLMs without locking into one vendor.

tiny tool, big videos. topic in, video out. no film degree required. webapp, windows app and mcp server for agent use

Pre-registered adversarial robustness study testing whether model-initiated session termination provides defensive coverage beyond refusal training against multi-turn attacks. Minimal Python harness with scorer and analysis pipeline. Pilot on Gemma 4 26b. Preliminary findings in FINDINGS.md.

GLM-5.2 Released: 1 Million Usable Context Window, MIT Open-Source Licensing, & Claude Code Integration Guide.

Collect and refine high-quality prompts for Ideogram 4.0 to improve your image generation results.

AI tool licenses and data terms — know what you're signing.

Data-driven exploration of open weight AI models and providers, based on performance x cost x energy use.

Production-ready multi-facet conversation evaluation benchmark - 399 facets, 5-level ordinal scoring, scales to 5000+ without redesign. Open-weights LLM (Qwen 3 8B) via Ollama/vLLM/HF.

Ideogram 4 本地 CUDA 图像生成器：内置 NF4 权重、官方 Magic Prompt 提示词优化、Windows/Linux 便携包 / Local open-weight text-to-image generator

Physical Intelligence — foundation models for robotics

Open-weight Brazilian Portuguese LLMs trained from scratch — Apache 2.0

Open-weights image generation models — Flux family.

API Evangelist profile of Mixedbread - embeddings and reranking API

VoxReach POC — full-duplex AI receptionist demo built on Kyutai MoshiRAG (open weights). Persona: Hearth & Pass Korean restaurant. 2-pane investor demo UI + POS-write moat story.

Python client for Pareta — deploy open-weights endpoints, run metered inference, and evaluate models on your own data.

A general-purpose agent fleet you run yourself — any model, in a sandbox, on a budget, connected to your data.

An open-source agentic coding harness that learns from its own failures. Observability-driven self-evolution, open-weight-first. Pre-alpha.