# timerring/bilive

极快的B站直播录制、自动切片、自动渲染弹幕以及字幕并投稿至B站，综合多种模态模型，兼容超低配置机器。Extremely fast live recording, automatic slicing, rendering, uploading and Integrating MLLMs. Compatible with low configurations machines.

Repository: https://github.com/timerring/bilive
Canonical: https://ross.abutalabs.com/products/bilive
Homepage: https://bilive.timerring.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: bilibili, bilive, live-recording, ass, bili, danmaku, stream, xml
Last push: 2026-04-24T04:06:22+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 79, release rhythm 40, longevity 55
- inputs: {"age_days": 773, "days_push": 131, "days_rel": 493, "gap_med": 4.5, "n_releases_24m": 21}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3275, forks 264 (observed 2026-08-28T04:07:53.311703+00:00)

## What it is
BILIVE is a Python application that records Bilibili live streams and danmaku 24/7, then automatically renders danmaku and AI-generated subtitles, slices highlight moments, generates covers and titles with multimodal LLMs, and uploads everything back to Bilibili. It runs on very low-spec hardware, including GPU-less single-core machines and both x64 and arm64 architectures.

## Use cases
- record bilibili live streams automatically
- render danmaku into recorded videos
- auto-generate subtitles for live recordings
- automatically slice highlight clips from streams
- auto-upload recordings to bilibili
- run a 24/7 unattended recording bot on a low-end server
- generate video titles and covers with multimodal models

## When to choose
- you need hands-off 24/7 bilibili live recording and re-upload
- you want automatic danmaku rendering, subtitles, and highlight slicing in one pipeline
- you have only a weak CPU-only server or old machine
- you want to record multiple rooms simultaneously with low disk usage

## When to avoid
- you need to record platforms other than Bilibili
- you cannot comply with its learning-only, non-commercial usage restrictions
- you need large-scale recording, which risks account bans
- you want a GUI-driven recorder rather than a configured pipeline

## Facets
- artifact type: application
- maturity: active
- function: video-processing, speech-recognition, machine-learning, workflow-automation, image-processing, nlp
- domain: media, artificial-intelligence, self-hosted
- platform: python, cross-platform, cli
- tags: bilibili, live-recording, danmaku, auto-slicing, auto-upload, subtitle-rendering, multimodal-llm, low-resource, video, automation, linux, docker

## Member repositories
- timerring/bilive (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:53.311703+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:43:23.439341+00:00, confidence not recorded.
  - readme: https://github.com/timerring/bilive (fetched 2026-08-28T04:07:53.311703+00:00, sha bc152a676739)
  - homepage: https://bilive.timerring.com (fetched 2026-08-29T09:36:21.675265+00:00, sha 137e92ea7123)
  - site_page: https://bilive.timerring.com/getting-started.html (fetched 2026-08-29T09:36:21.685013+00:00, sha 9ae0bf69e6b1)
- Data as of 2026-08-30T08:39:29.467469+00:00.