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 |
|---|---|---|
| .. | ||
| ccr | ||
| relevance | ||
| signals | ||
| tokenizer | ||
| transforms | ||
| auth_mode.rs 11.8 KB | ||
| cache_control.rs 15.0 KB | ||
| compression_policy.rs 26.2 KB | ||
| hf_cache.rs 28.2 KB | ||
| lib.rs 1.9 KB | ||
| offline.rs 7.3 KB | ||
| onnx_cpu.rs 1.3 KB | ||
| rollout.rs 13.9 KB | ||