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 |
|---|---|---|
| .. | ||
| auth_mode_layer.rs 7.7 KB | ||
| envelope.rs 9.2 KB | ||
| eventstream_to_sse.rs 18.2 KB | ||
| eventstream.rs 29.8 KB | ||
| invoke_streaming.rs 45.6 KB | ||
| invoke.rs 31.6 KB | ||
| mod.rs 3.1 KB | ||
| sigv4.rs 11.9 KB | ||
| vendor.rs 4.7 KB | ||