* [Headroom v0.36.0](https://github.com/headroomlabs-ai/headroom) – Headroom compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach an LLM to reduce tokens while preserving answers.

* [CyberChef v11.4.0](https://github.com/gchq/CyberChef) – Simple, intuitive web app for performing encryption, encoding, compression, parsing, and other data transformations in the browser.

* [Token Optimizer MCP v5.7.1](https://github.com/ooples/token-optimizer-mcp) – Model Context Protocol server that optimizes Claude Code context usage using caching, Brotli compression, and smart tool replacements for large text and file operations.

* [8mb.local v142](https://github.com/JMS1717/8mb.local) – Selfhosted GPU-accelerated video compressor with multi-vendor support and realtime progress tracking.