Search

Name reserved for the tokenspeed-trtllm-attn project.

Compress your local LLM KV cache with 5.3× memory reduction

Name reserved for the tokenspeed-trtllm-common project.

Name reserved for the tokenspeed-trtllm-gemm project.

AlchemyLab - agentic coding IDEm

Metadata quality bot for software repositories, leveraging metacheck for analysis and GitHub/GitLab APIs for issue management.

Natural language to SQL query engine powered by LangChain and DuckDB

The LEGO set for custom vLLM model plugins — build, test, and deploy custom encoders, poolers, and kernels

Local inference server for Apple Silicon that hot-swaps MLX models (LLM, vision, embeddings, TTS, STT) via OpenAI-compatible API

This is LLM interface library.

Python package for LLM compression

A comprehensive Python library and CLI tool to perform LLM Red Teaming with Avenlis SandStrike.

AI service client for the Frontal Python SDK — text, embeddings, images, speech, video, and more

Blob storage client for the Frontal Python SDK

Graph-based project memory for Claude Code — semantic density over transcript volume

RAG pipeline library — chunking, embeddings, vector search, and retrieval for the Willian SaaS platform

Immutable audit log library with PostgreSQL storage for the Willian SaaS platform

Stateless GitHub activity summary — compact, LLM-friendly output

Search across Claude Code session history

A modern, configuration-driven X12 EDI parser and validator for healthcare transactions with optional LLM-powered explanations