ranxianglei/billion-context
A context-compression plugin for month-long single sessions (billions of tokens) ,small context windows (a 100K context is enough) and token savings (5x fewer tokens) .上下文压缩插件，月级长会话会话， 兼顾小窗口(100k上下文足矣)省token(省5倍token) . billion-context is all you need
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #15 among Web repositories ranked this week, and #12 over the last 30 days; #83 of 182 repositories with measured growth this week (top 46%).
This week's +773 stars is in line with its 30-day pace of about +817 per week.
5 releases in the last 90 days, the latest 3 days ago, with 84 contributors on GitHub.
Peaked at #4 in the weekly ranking the week of Oct 18, its best in the past year.
Use Cases & Benefits
- Provides a context-compression plugin that enables long-lived AI sessions by compressing conversation context into layered summaries.
- Reduces token usage by 5x and supports month-long single sessions with billions of tokens using small context windows around 100K tokens.
- Use for extending AI coding agents' session length without context window overflow or degradation in multi-day coding workflows.
- Use for integrating with various AI clients like pi, opencode, dsh, and claude to transparently compress and manage conversation context.
- Use for optimizing token costs and maintaining high-fidelity context in applications requiring incremental, reversible, and prefix-cache friendly compression.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
General guidance from repository metadata, not legal advice. How we score
From the README
Context-compression plugin — billion-context is all you need.
small context windows (100K is enough) · 5× fewer tokens · month-long single sessions (billions of tokens) · high compression quality
npm install -g billion-context --prefix=~/.local
Cache health at a glance: a healthy session keeps a 95–97% prefix-cache hit rate — compression itself costs ≤2%. Sustained lower? Check attribution with
/acpor/acp-cache(see FAQ); usual causes, in order: upstream cache TTL expiry · model switch · a bili bug (please report) · other/unknown.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+3,540 stars over 31 days across 30 snapshot days; best day +200 on Oct 26.
Forks
335+276
Open issues
841+737
Compared with peers in Web
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| pingdotgg/t3code | 48.4K | +16.6K | 40 | today |
| pbakaus/impeccable | 104.0K | +8.7K | 54 | 10 days ago |
| HunYiSage/dsh-purge | 19.2K | +6.2K | 13 | today |
| Renhuai123/ziwei-doushu | 16.2K | +6.1K | 44 | 21 days ago |
| paperclipai/paperclip | 111.5K | +2.8K | 59 | 13 days ago |
| ranxianglei/billion-context | 4.1K | +773 | 55 | 3 days ago |
| Category median | 48.4K | +6.2K | 44 | — |
Discover Repositories
Search across tracked repositories by name or description