mksglu/context-mode
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
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 #1 among Web repositories tracked this week, and #1 over the last 30 days; #72 of 2,531 repositories GStars tracks this week (top 3%).
This week's +2,968 stars is ahead of its 30-day pace of about +1,847 per week.
No releases in the last 90 days; the most recent was 114 days ago, with 112 contributors on GitHub.
Peaked at #5 in the weekly ranking the week of Oct 11, its best in the past year.
Use Cases & Benefits
- Optimizes AI coding agents' context windows by sandboxing tool outputs and reducing context size by 98% across 12 platforms.
- Enables session continuity with SQLite tracking and BM25 search, allowing agents to resume exactly where they left off without losing context.
- Use for integrating context window optimization and session tracking in Claude Code plugin marketplace for seamless AI coding workflows.
- Use for enhancing VS Code Copilot Chat sessions with automatic routing and context compaction to maintain relevant coding context.
- Use for deploying as a native OpenClaw gateway plugin to manage Pi Agent sessions with automatic hook registration and zero manual configuration.
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
- Contributing guide: 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
The other half of the context problem.
Used across teams at
Every MCP tool call dumps raw data into your context window. A Playwright snapshot costs 56 KB. Twenty GitHub issues cost 59 KB. One access log — 45 KB. After 30 minutes, 40% of your context is gone. And when the agent compacts the conversation to free space, it forgets which files it was editing, what tasks are in progress, and what you last asked for.
Platforms are grouped by install complexity. Hook-capable platforms get automatic routing enforcement. Non-hook platforms need a one-time routing file copy.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+12,336 stars over 89 days across 52 snapshot days; best day +947 on Oct 14.
Forks
2.2K+818
Open issues
356+249
Compared with peers in Web
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| MadsLorentzen/ai-job-search | 60.6K | +12.8K | 60 | 1 day ago |
| anomalyco/opencode | 219.7K | +6.5K | 75 | 5 days ago |
| hmjz100/LinkSwift | 26.9K | +4.7K | 75 | 245 days ago |
| mksglu/context-mode | 31.7K | +3.0K | 75 | 114 days ago |
| YuJunZhiXue/dsh-purge | 8.9K | +2.9K | 55 | 8 days ago |
| withmarbleapp/os-taxonomy | 7.1K | +2.2K | 75 | — |
| Category median | 26.9K | +4.7K | 75 | — |
Discover Repositories
Search across tracked repositories by name or description