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
Add dashboard screenshots for cache TTL metrics PR
JerrettDavis4226372b1561
diff --git a/docs/screenshots/cache-ttl-dashboard-history.png b/docs/screenshots/cache-ttl-dashboard-history.pngnew file mode 100644index 000000000..bd0cbc594Binary files /dev/null and b/docs/screenshots/cache-ttl-dashboard-history.png differdiff --git a/docs/screenshots/cache-ttl-dashboard-live.png b/docs/screenshots/cache-ttl-dashboard-live.pngnew file mode 100644index 000000000..1d9d60544Binary files /dev/null and b/docs/screenshots/cache-ttl-dashboard-live.png differ