 Louistiti
|
13a29160d3
|
feat: create settings standard for skills with required settings for better onboarding for tools usage
|
2026-02-21 13:38:15 +08:00 |
|
|
Louistiti
|
ca247033a8
|
feat(skill/skill_writer): allow skill changes
|
2026-02-20 13:54:40 +08:00 |
|
|
Louistiti
|
fa3dfccb83
|
feat(skill/video_summarizer): implemented by Leon
|
2026-02-20 12:36:41 +08:00 |
|
|
Louistiti
|
bd40ccc5f1
|
feat(tool/ytdlp): isolate default config into config file
|
2026-02-19 23:32:17 +08:00 |
|
|
Louistiti
|
b2d5dc7a59
|
feat(skill/voice_designer_skill): implemented by Leon
|
2026-02-19 20:53:54 +08:00 |
|
|
Louistiti
|
0d272b5bcc
|
build: bump core deps to latest
|
2026-02-19 14:58:33 +08:00 |
|
|
Louistiti
|
ae587ba327
|
feat: improve skill writer skill; report command execution output; and more
|
2026-02-19 01:02:11 +08:00 |
|
|
Louistiti
|
404d7fbec7
|
feat: embed OpenCode in the Skill Writer skill; restructure tools; create simple forecast skill and more
|
2026-02-18 21:23:27 +08:00 |
|
|
Louistiti
|
ada9c25b3e
|
feat(skill/video_translator): use Qwen3-TTS tool by default
|
2026-02-18 11:13:21 +08:00 |
|
|
Louistiti
|
3bdabaf943
|
feat(tool/qwen3_tts): implement Qwen3-TTS tool
|
2026-02-18 00:40:36 +08:00 |
|
|
Louistiti
|
7e573c2b7d
|
feat(tool/qwen3_asr): implement Qwen3-ASR tool
|
2026-02-07 23:14:26 +08:00 |
|
|
Louistiti
|
cd782b2095
|
feat(scripts): auto download pre-built PyTorch libs on install
|
2026-02-07 14:28:49 +08:00 |
|
|
Louistiti
|
66dd2fe2c0
|
refactor: rename CUDA runtime with NVIDIA libs
|
2026-02-06 15:54:02 +08:00 |
|
|
Louistiti
|
d831833d49
|
feat: add settings at toolkits/tools level where skills settings has higher priority than tool settings
|
2026-02-01 14:25:30 +08:00 |
|
|
Louistiti
|
32b60f1298
|
feat(tool/openrouter): remove models mapping
|
2026-01-30 00:04:57 +08:00 |
|
|
Louistiti
|
4ddb12246d
|
feat(tool/chatterbox): built-in text segmentation
|
2026-01-27 18:36:13 +08:00 |
|
|
Louistiti
|
50b21532fc
|
fix(tool/grok): search output parsing
|
2026-01-26 23:40:26 +08:00 |
|
|
Louistiti
|
35bd421b84
|
feat(tool/grok): implement deep research (WIP)
|
2026-01-26 21:16:40 +08:00 |
|
|
Louistiti
|
3045985952
|
feat(tool/opencode): add deep guidelines following Leon's granular architecture
|
2026-01-25 23:40:06 +08:00 |
|
|
Louistiti
|
6ab6cfd9ba
|
feat(tool/opencode): Leon writes his own skills (WIP)
|
2026-01-24 13:33:36 +08:00 |
|
|
Louistiti
|
b0fdd38532
|
feat(tool/cerebras): add Cerebras tool for faster inference
|
2026-01-20 19:30:31 +08:00 |
|
|
Louistiti
|
8b5b810f88
|
feat(tool/ytdlp): fallback web_safari when 403
|
2026-01-18 16:58:27 +08:00 |
|
|
Louistiti
|
80e636df5c
|
fix(tool/ffmpeg): remove stderr output non-necessary logs
|
2026-01-12 00:19:22 +08:00 |
|
|
Louistiti
|
4b477ccd76
|
fix(tool/ytdlp): update on progress download regex
|
2026-01-11 22:19:11 +08:00 |
|
|
louistiti
|
0273099ea6
|
feat(skill/video_translator): split vocals/instrumental and merge back audio
|
2026-01-11 15:22:50 +08:00 |
|
|
Louistiti
|
183ba56c32
|
feat(skill/video_translator): audio segmentation and merge
|
2026-01-06 19:25:23 +08:00 |
|
|
Louistiti
|
c85b849206
|
feat: Video Translator skill nearly completed; delete previous versions of tool binaries on download; and more
|
2026-01-06 02:01:33 +08:00 |
|
|
Louistiti
|
7d798b13f9
|
feat(tool/chatterbox_onnx): auto set CUDA runtime path for Windows and Linux x86_64
|
2026-01-04 22:22:16 +08:00 |
|
|
Louistiti
|
26728b283a
|
feat(tool/chatterbox_onnx): new text-to-speech and voice cloning tool
|
2026-01-04 21:15:33 +08:00 |
|
|
Louistiti
|
6ca96e3deb
|
feat(skill/video_translator): find longest segment to get speaker ref as 10-secs fallback
|
2025-12-31 11:13:37 +08:00 |
|
|
Louistiti
|
9d1d66a07d
|
feat(tool/ytdlp): reduce time intervals for faster download
|
2025-12-30 22:27:47 +08:00 |
|
|
louistiti
|
7b5860410b
|
feat(skill/video_translator): ECAPA gender voice recognition; AssemblyAI tool for transcription; and more
|
2025-12-30 20:35:45 +08:00 |
|
|
Louistiti
|
6c7e8d8af4
|
feat(tool/ffmpeg): merge audio to video
|
2025-11-05 22:10:30 +08:00 |
|
|
louistiti
|
b4f4fffa5e
|
feat(tool/elevanlabs_audio): dubbing function implementation
|
2025-11-05 20:47:28 +08:00 |
|
|
louistiti
|
118ed10817
|
feat(tool/elevenlabs_audio): transcription function implementation
|
2025-11-05 08:32:12 +08:00 |
|
|
Louistiti
|
3aa45fcc64
|
feat(tool/openai_audio): add chunking_strategy param for diarization
|
2025-11-04 22:30:06 +08:00 |
|
|
louistiti
|
8063cc6074
|
feat: support speaker diarization when transcribing from third-party providers
|
2025-11-04 21:56:20 +08:00 |
|
|
louistiti
|
0013ffc888
|
feat: execute actions from other skills; push/get data from context across flow; OpenAI audio tool and more
|
2025-11-01 17:38:32 +08:00 |
|
|
louistiti
|
f075d7c922
|
feat: format path when resource already exists
|
2025-09-14 17:41:20 +08:00 |
|
|
Louistiti
|
884d027610
|
feat: clean up dev runtime
|
2025-09-14 09:48:42 +08:00 |
|
|
louistiti
|
612d773fe8
|
feat(tool/yt-dlp): add common args
|
2025-09-13 23:41:38 +08:00 |
|
|
louistiti
|
8715e71903
|
feat: tool logger and tool download progress report
|
2025-09-13 11:39:25 +08:00 |
|
|
louistiti
|
17ec4ed348
|
fix: auto download binary and resources from bridges
|
2025-09-13 10:23:06 +08:00 |
|
|
louistiti
|
2ad3fe7d91
|
feat: faster_whisper download model resources and end-to-end flow
|
2025-09-11 00:12:12 +08:00 |
|
|
louistiti
|
a9e22de8ca
|
feat: auto download tool resources (models, etc.); Faster Whisper tool
|
2025-09-09 23:45:49 +08:00 |
|
|
Louistiti
|
f513713959
|
feat: more robust audio extraction across bridges
|
2025-09-07 22:11:04 +08:00 |
|
|
louistiti
|
1fed246ca9
|
feat: OpenRouter tool; bash tool
|
2025-09-07 14:52:27 +08:00 |
|
|
louistiti
|
4e0d0cf91d
|
feat: tool output UI
|
2025-09-07 11:58:11 +08:00 |
|
|
louistiti
|
1aea646c6c
|
feat: unify binary tool calls for both bridges
|
2025-09-07 10:52:13 +08:00 |
|
|
louistiti
|
58fe7691ec
|
feat: describe taken actions in binary tools
|
2025-09-07 01:23:41 +08:00 |
|