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.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| __init__.py 50 B | ||
| test_code_handler.py 15.1 KB | ||
| test_deprecation.py 3.7 KB | ||
| test_evals.py 42.0 KB | ||
| test_json_handler.py 15.8 KB | ||
| test_llm_eval.py 21.4 KB | ||
| test_masks.py 10.6 KB | ||
| test_universal.py 12.9 KB | ||