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.
About the project
An MCP server for AI coding agents that sandboxes tool output (up to 98% context reduction), persists session memory in SQLite with FTS5 search, and enforces routing across 17 platforms.
Useful for
- Connect to Claude Code so Playwright snapshots and logs stop flooding the context window
- Index project files into FTS5 and search them after session compaction
- Run ctx_execute with a script instead of dozens of Read calls to get only the final result
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 181 stars today. The usual pace is 30 per day, so that's 6.2× as much.
- The spike has held for 3 days in a row — not a one-off blip.
- GitHub Trending this week: #5, +1,936 stars.
- About 28 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 22,614
- Stars in a day
- 183
- Forks
- 1,631
- Issues and pull requests
- 1,101
- Watchers
- 95
- Language
- TypeScript
- Latest release
- v1.0.169 · June 29, 2026
- Created
- February 23, 2026
- Last push
- September 13, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 13, 2026GitHub Trending this week: #5, +1,936 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/mksglu/context-mode)Similar projects
-
6.8
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.2
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
6.2
ayghri/i-have-adhd
A skill for a coding agent (Claude Code) that makes it lead with the answer and numbered steps, without preamble or filler. Helps you get concrete actions instead of long-winded reasoning.
-
6.1
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.1
jordan-gibbs/hyperresearch
A deep research harness for Claude Code: turns one prompt into a report with verified citations and a persistent source vault. Every source lands in a searchable store reused by later sessions.
-
6.0
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.