Search

Utilities to handle BP/RP (XP) Gaia low-resolution spectra as delivered via the Archive.

A type of potential-based recurrent neural networks implemented with PyTorch

Mjolnir: a paged decode-attention kernel for NVIDIA Jetson AGX Thor (sm_110) on tcgen05 / TMEM / TMA (CuTe DSL), with fp8 and 6-bit (e2m3) KV caches — packaged as the vLLM MJOLNIR attention backend.

n8n chat model node for Nebius Token Factory: open models for AI agents and chains

Decisões estruturadas para o código (TypeSafe Jev) e texto livre para pessoas (LLM), com custo zero por padrão.

Small, token-aligned activation hooks for Nemotron in PyTorch and vLLM

Eleven free Claude skills that run an X account, with a virality engine behind every idea: posts off 21 hook formulas, threads, replies, profile score, weekly plan, analytics audit and a humanizer. Free, MIT.

Boruna: a deterministic, capability-safe programming language and framework for LLM-native applications