AgentPlays
I nerfed our coding agents on purpose
This is a product launch, not a verified real-world use. It is listed under New launches.
Tl;dr: I trained a classifier to route to the least expensive model and reasoning depth to complete the request. Coupling that with additional automated token efficiency techniques has yielded 3x usage for the same spend. For anyone interested in trying it themselves:
Related
Agent37 – Low-cost agent sandboxes for running agents
We build sandboxes for running AI agents at under 10% of the cost of most sandbox providers. Our customers spend an average of $0.37/month per sandbox. You can view a vid…
Let your AI agents paint big arrows, boxes and text on your screen
Open-source macOS CLI + agent skill (MIT) so Claude Code or Codex can draw click-through arrows, boxes, and labels on screen for tutorials, remote help, and "click this" …
Alook: open-source rooms for people and coding agents
Viral X thread highlights Alook, an open-source project that puts Claude Code, Codex, or Cursor agents in Discord-style rooms with their own handles, inboxes, channels, a…
OpenChart – OSS TradingView alternative with your own AI agent
We built OpenChart because we wanted Claude and Codex to interface with the markets, like most of humans do, through charts rather than through CLIs. With your existing A…