EJClaw
c93691cc26
docs(readme): hold Brain at 350ms, trim STT 250->150 and TTS 250->170 (total ~0.85s)
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-08-11 20:35:30 +09:00
EJClaw
1eb6620eb3
docs(readme): tighten latency budget to <=1s, STT via Discord voice, Korean human-like TTS
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-08-11 17:52:00 +09:00
EJClaw
b0ab23909e
docs(readme): refocus on voice loop first, defer screen share
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-08-11 00:07:50 +09:00
EJClaw
b0780988a2
docs(readme): rewrite as implementation blueprint (latency budget, dual eye tracks, milestones)
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-08-09 22:00:44 +09:00
EJClaw
932e1b76b2
docs(readme): fix run commands to use workspace venv (python/pytest not on PATH)
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-08-09 21:53:09 +09:00
EJClaw
d756ea4cf5
docs(readme): rewrite as accurate project summary (selfbot receive + DAVE gate 1)
...
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-08-09 21:51:42 +09:00
claude-owner
4eeddc4b1f
feat: scaffold watch-screen AI pipeline (mock-runnable skeleton)
...
Modular async pipeline: FrameSource->Vision->context and STT/text->Brain->TTS.
All stages are Protocols; mock backends run end-to-end with no deps/keys.
Real backends included: mss screen capture, Claude vision+brain (guarded imports).
2026-08-09 02:16:14 +09:00
