perfup
01Command Claude Code
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR.
79 tagged apple silicon, measured the same way as everything else here.
Browse within: inference 60benchmark 59lm-studio 59mlx 12speech-to-text 11text-to-speech 11asr 7bun 7chatterbox 7coreml 7openclaw 7experimental 5workflow 5
Command Claude Code
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR.
Command Claude Code
Archive a completed change in the experimental workflow.
Command Claude Code
Run the full pre-push verification gate (bun + rust) per CLAUDE.md's VERIFY BEFORE PUSHING rules.
Command Claude Code
Create a gitignored worktree off fresh origin/main per CLAUDE.md's "MAIN STAYS IN ROOT" rule.
Command
Search, save, inspect, and maintain memo persistent memory.
Command
Comment configurer asiai : gérer les URL des moteurs, les ports et les paramètres persistants pour votre configuration de benchmark LLM sur Mac.
Command
A saved settings manager for the local programs that run language models, including their addresses, ports, versions and labels.
Command
Hintergrunddienste über macOS launchd LaunchAgents verwalten.
Command
Summarize and speak the last response.
Command
Install MLX dependencies and download model (4GB).
Command
Temporarily mute TTS notifications.
Command
Jump In and add spoken guidance.
Command
Start talking with Cadence Code.
Command
Choose Cadence Code speech models.