Compression: open-source projects on GitHub
12 repositories on Compression, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
LLM Input Compression
Compresses tool outputs, logs, files, and RAG chunks before sending to the LLM, cutting token usage by 60‑95% without loss of quality.
★ 79,744 · PythonDeepSpeed: optimization library for training
DeepSpeed is an optimization deep learning library ensuring efficient distributed training and inference. Supports ZeRO, MoE and parallelism for training models with hund
★ 43,332 · PythonMEMORY FOR AI AGENTS
SimpleMem — efficient long-term memory for LLM agents with support for text and multimodal data.
★ 3,878 · PythonVORTEX — MOST STRUCTURED DATA FORMAT
Vortex is an extensible framework for columnar data compression and the fastest open columnar format. It is the primary tool for next‑generation analytics from LFAI&Data.
★ 2,966 · Rustheadroom — compression for LLM
Compresses tool outputs, logs, files, and RAG chunks before sending to the LLM, cutting tokens by 60–95% while preserving answer quality. Library, proxy, and MCP server.
★ 1,828 · PythonNNCFF - ACCELERATING MODEL INFERENCE
NNCFF is a neural network compression framework for accelerated inference in OpenVINO™. It reduces model size while preserving accuracy.
★ 1,221 · PythonTOKEN OPTIMIZER: -95% TOKENS
Reduces token usage in Claude Code by 95%+ through caching, compression, and smart tool selection.
★ 582 · TypeScriptCONTEXT-ENGINE CONTEXT COMPRESSION
Context-Engine MCP compresses agent prompts, boosting LLM efficiency without losing meaning. It supports Python and is ready for integration.
★ 402 · PythonYAMS — MEMORY FOR LLM
Persistent storage for LLM and applications: a content‑addressable DB with deduplication, compression, full‑text and vector search.
★ 372 · C++PICOLLM - OFFLINE LLM ON DEVICE
picollm enables running LLM on-device through extreme k‑bit quantization, delivering fast and private inference without the cloud.
★ 320 · PythonSMART-TREE AI REVOLUTION
Context-aware code tree with MEM8 quantum compression, semantic search, and AST-smart editing — replaces 20+ tools.
★ 274 · RustGLYD: LOSSLESS AI COMPRESSION
Glyd reduces GPU memory by 33% without losing data, ensuring bit‑for‑bit identity. The project is written in Rust and supports CUDA, C‑ABI, and CLI for convenient benchma
★ 200 · RustNew projects on this topic in Telegram
Telegram →