Spaces:

HOLOGRAMTECH
/

bonsai-kappa-stream

Running

App Files Files Community

bonsai-kappa-stream

8.2 MB

Ctrl+K

Ctrl+K

4 contributors

History: 41 commits

humuhumu33

Claude Opus 4.8

Voice on by default for every new visitor (mute persists)

e40897c 22 days ago

hbao
The speaking mind, one kappa: Bonsai 8B and its voice now stream as ONE BLAKE3-rooted object (root ceb22e28...) carved into the cache by verified range windows; the voice arrives first and narrates the mind's arrival; sentences batch into single generates for natural prosody; synthesis is seeded-deterministic so spoken clauses are content-addressed and replay in O(1). 23 days ago
q
Self-heal poisoned weight cache: purge + re-fetch on κ MISMATCH 22 days ago
vendor
Re-mint the κ-runtime manifest over the 27B build (26 members) + vendor; seal is now part of build-space 24 days ago
.gitattributes

1.7 kB
Boot inside the κ-addressable holospace runtime from byte zero 24 days ago
README.md

1.79 kB
card: short_description under 60 chars 25 days ago
bao-carve.mjs

9.49 kB
Protect decode throughput: the background carve now yields the CPU while the mind is generating (the 8B does one GPU readback per token on the main thread, so any concurrent verify+gunzip steals exactly that). Background top-up waits for idle. No effect once weights are resident; matters on a slow first-load. 23 days ago
bonsai-ear.mjs

13.1 kB
The conversing mind: tap the mic and talk to it. Moonshine hears you on-device (Silero VAD segments, ~300ms transcribe), Bonsai answers, alba speaks it back while it writes, and the mic reopens when the voice finishes - a full voice-to-voice loop, 100% in the browser, audio never leaving the device. The ear, its runtime, the voice and the mind now ship as ONE BLAKE3 object (root 4eed444d...) with per-device slices: phones stream moonshine-tiny, desktops moonshine-base, one hash pins both. 23 days ago
bonsai27-bridge.mjs

5.73 kB
The conversing mind: tap the mic and talk to it. Moonshine hears you on-device (Silero VAD segments, ~300ms transcribe), Bonsai answers, alba speaks it back while it writes, and the mic reopens when the voice finishes - a full voice-to-voice loop, 100% in the browser, audio never leaving the device. The ear, its runtime, the voice and the mind now ship as ONE BLAKE3 object (root 4eed444d...) with per-device slices: phones stream moonshine-tiny, desktops moonshine-base, one hash pins both. 23 days ago
index.html

84.1 kB
Voice on by default for every new visitor (mute persists) 22 days ago
kappa-swarm.mjs

10.5 kB
No more dead 0%: the loading line now counts real bytes, starts where the welcome head-start left off, and everything the load needs (manifest, GPU adapter) begins at first paint instead of at the click. 23 days ago
manifest.holo.json

5.52 kB
Self-heal poisoned weight cache: purge + re-fetch on κ MISMATCH 22 days ago
pocket-voice.mjs

12 kB
Karaoke: the clause being spoken lights up in the transcript, bound to the audio clock itself (segment timeline recorded at schedule time) - text and voice cannot drift. Quiet wash, no motion, zero residue when playback ends or a new question barges in. 23 days ago
pocket-worker.js

20.6 kB
The speaking mind, one kappa: Bonsai 8B and its voice now stream as ONE BLAKE3-rooted object (root ceb22e28...) carved into the cache by verified range windows; the voice arrives first and narrates the mind's arrival; sentences batch into single generates for natural prosody; synthesis is seeded-deterministic so spoken clauses are content-addressed and replay in O(1). 23 days ago
portal-sw.js

13.9 kB
Fix ERR_FAILED on model switch: the SW served the HF directory-root 302 as the navigation response, and Chrome rejects a redirected Response for a navigation (then it was cached redirected, so it failed on every reload). shell() now rebuilds a clean 200 from the body before caching or returning it, and never serves a redirected cache entry. 23 days ago