#mistral

Ask your repo what breaks before an AI coding agent edits it.

Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated.

⚛️ AgentKthx - minimal, modular, python stdlib, agentic framework for tool calling AI agents. Runs locally with Ollama, BitNet, TurboQuant, in the cloud with OpenRouter, ZAI, HuggingFace, and Google Gemini. Extensible via a manifest-based plugin system for additional backends and features.

Instant, controllable, local pre-trained AI models in Rust

Pure-Go LLM tokenizer and tiktoken-compatible token counter for OpenAI BPE, WordPiece, SentencePiece, Gemini, Llama, Mistral, and Hugging Face adapters.

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Go reimplementation of pi.ai core with multi-provider LLM streaming, a CLI, and a single-agent runtime.

Create conversational AI solutions with custom data and abilities using ChatBotKit for Go applications.

Rust implementation of the Mistral Tekken tokenizer

Run AI at CLI