Search

Text chunking / splitting utilities for the GATRAG RAG framework

Know what your rig can run. Hardware-aware local LLM discovery, recommendation, setup, and benchmarking.

Fully on-device vector search engine with built-in embeddings - no cloud, no server, no account

Simple Python API for local Qwen LLM with tools

You use AI to help with your writing, and now everything you create reads AI-written. There is a name for that machine "tell": AI slop. Zero Slop finds that slop in your draft and strips it out without changing what you said, then scores your writing before and after so you can see it drop. Free, runs locally, works in any AI assistant.

Purge multi-vendor AI watermarks: clean Unicode text, apply statistical rewrite hooks, and clear C2PA plus metadata from PNG, JPEG, SVG, PDF, DOCX, HTML, and MD.

Chat with any LLM + offline olympiad task helper. Zero dependencies.

TLLM runs 70B large language models on a single 4GB GPU without quantization, distillation or pruning. 405B Llama 3.1 on 8GB, DeepSeek-V3 671B on ~12GB, Kimi K3 2.8T on under 4GB, Qwen3.8-27B on 3.3GB.

Transcribe meetings locally with faster-whisper/whisper.cpp, then extract structured info via Claude/Cursor skills.

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