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
docs: replace mock screenshots with real dashboard renders
JerrettDavis86efb596151a
diff --git a/docs/screenshots/subscription_window_active.png b/docs/screenshots/subscription_window_active.pngindex 6607db05d..7b8b9d0a2 100644Binary files a/docs/screenshots/subscription_window_active.png and b/docs/screenshots/subscription_window_active.png differdiff --git a/docs/screenshots/subscription_window_inactive.png b/docs/screenshots/subscription_window_inactive.pngindex 93f245b0d..b28f40026 100644Binary files a/docs/screenshots/subscription_window_inactive.png and b/docs/screenshots/subscription_window_inactive.png differ