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 |
|---|---|---|
| .. | ||
| anthropic.rs 16.8 KB | ||
| framing.rs 15.5 KB | ||
| mod.rs 1.5 KB | ||
| openai_chat.rs 8.2 KB | ||
| openai_responses.rs 17.8 KB | ||