The desktop and headless router judges every new user turn to pick an economy or primary model, keeps that choice through tool round-trips to reuse the KV cache, and works with Codex, Claude Code, Qoder, Pi, and DeepSeek Harness. Version 0.3.0 (Oct 11) fixes double-billed Messages cache usage, improves task continuation, and adds Linux packages that run on glibc 2.31.
The free, open source tool reads the session files Claude Code already writes, so the lead agent gives orders while sub agents join, share their screen with real commands and diffs, and report back, with a who asked whom tree, context gauges, and replays. It runs as a VS Code extension (VSIX for Cursor and Windsurf), via npx @double geste/agent standup open , or as an unsigned desktop app, and its author calls it "mostly for fun.…
Across 50 full stack app builds with GPT 6 Sol and Claude Opus 5.5, only Sol's medium effort team made a statistically significant gain (77.6% to 84.9%), while simply raising Sol's solo reasoning effort added 11.4 points. Opus showed no significant gain from either teams or higher effort, and its max effort team cost about $122 per app…
Ryan Dahl says the team will fold its self hostable celld into Workers and Durable Objects, pitching them as a home for agent harnesses, while the Deno runtime gets only bug and security fixes for one more year. Deno Deploy runs for six more months with migration help to Workers for paying customers, and JSR keeps running on Cloudflare infrastructure…
Maurice Heumann's agents stalled at a loose 80% until he added a pass/fail harness that compiles each function with the game's original compiler and compares bytes against the shipped EXE, then reached 99% of functions present and 83% byte exact in about two more months. He estimates 600 to 700 billion tokens spent, and the source stays private…
Describe a game and agents build it in a live preview, with Blender integration, generated 3D assets, and an optional loop that builds and judges candidate changes, while projects stay as ordinary local files. The MIT licensed app runs on macOS and Linux (Windows pending), works through your existing Claude Code or Codex CLI or Ollama, and v0.1.6 (Oct 10) runs OpenCode 1.18 and 2.x side by side…
Spotted something we missed? Start a thread.