Huzaifa785/context-compressor
AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while preserving semantic meaning with advanced compression strategies.
This tool helps AI application developers optimize how much text they send to large language models (LLMs) like ChatGPT or Claude. You feed it long documents or chat histories, and it intelligently shortens them, aiming to keep the most important information, especially what's relevant to a specific user question. The output is a significantly shorter version of the text, ready to be passed to an LLM, reducing processing costs and improving efficiency.
Used by 1 other package. No commits in the last 6 months. Available on PyPI.
Use this if you are building AI applications and need to reduce the length of your input text to large language models to save costs and stay within their context limits, without losing the essential meaning.
Not ideal if you need to compress text for human reading where perfect grammatical flow and every detail are critical, as the goal here is optimized input for AI systems, not a polished summary for people.
Stars
80
Forks
13
Language
Python
License
MIT
Category
Last pushed
Aug 16, 2025
Commits (30d)
0
Dependencies
26
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Huzaifa785/context-compressor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
chopratejas/headroom
The Context Optimization Layer for LLM Applications
Meirtz/Awesome-Context-Engineering
🔥 Comprehensive survey on Context Engineering: from prompt engineering to production-grade AI...
puppyone-ai/puppyone
The context file system for agents. Connect, govern, and share context across all agents.
redleaves/context-keeper
🧠 LLM-Driven Intelligent Memory & Context Management System （AI记忆管理与智能上下文感知平台） AI记忆管理平台 |...
ahmedsamy-244/ai-code-context-helper
🤖 A lightweight desktop tool for developers working with AI assistants. 📊 Visualize project...