Back to trending
How scoring works 
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.
Python72,109 stars5,521 forksApache-2.0
agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
Rankings
PeriodRankScore
Daily
#327050.0Weekly
#327050.0Monthly
#215458.7Engagement
Total stars
Daily new stars
Embeds
Best rank #1