Repository Index

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

• agent
• ai
• anthropic
• compression

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

• deep-learning
• pytorch
• gpu
• machine-learning

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

• esrgan
• pytorch
• real-esrgan
• super-resolution

Contexts Optical Compression

Deduplicating archiver with compression and authenticated encryption.

• python
• compression
• ssh
• deduplication

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

• nlp
• embedding
• bert
• ernie

SSH server & client security auditing (banner, key exchange, encryption, mac, compression, compatibility, security, etc)

• auditing
• security
• ssh

Insane(ly slow but wicked good) PNG image optimization

• png
• png-compression
• compression
• image-quality

SSH server auditing (banner, key exchange, encryption, mac, compression, compatibility, security, etc)

Self hosted file converter and compression tool for images, video, audio, json, excel and more. Supports over 3,000 conversions!

• convert
• docker
• python
• file-converter

:camera_flash: Fast batch image resizer and rotator

• image-processing
• image-compression
• image-manipulation
• image-optimization

Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.

• python
• pytorch
• machine-learning
• deep-learning

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

• ai-agents
• claude-code
• mcp
• token-optimization

One zero-dependency MCP gateway CLI for every server and agent skill. Token optimization, tool discovery and context compression: 71,929 -> 581 tokens (-99.2%, measured), schemas stay out of context. One config for Claude Code, Codex, Cursor, every agent. 561KB, pure Python. | 零依赖 CLI：管所有 MCP 工具与技能，工具发现省 99.2% token。

• mcp
• claude
• claude-code
• cursor

TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.

• agent-memory
• claude-code
• codex
• context-compression

Micropython wrapper for FastLZ, a lightning-fast lossless compression library