Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
mksglu/context-mode is drawing steady momentum at +122.1 stars/day (96th percentile in the tracked cohort), for a momentum score of 42.3/100. A recent release is helping fuel the run.
Reconstructed from 277 snapshots — the time-series GitHub’s API doesn’t expose.
Release count rose to 220.
Release count rose to 217.
Release count rose to 202.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/mksglu/context-mode)Low breakout odds over the next 14 days, led by star velocity (96th pctl) and push recency (100th pctl). Confidence is high given the available history.
Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
Release count rose to 200.
~18 forks/day, 5.6× the trailing baseline.
~18 forks/day, 3.1× the trailing baseline.
~41 forks/day, 5.6× the trailing baseline.
~14 forks/day, 4.8× the trailing baseline.
~13 forks/day, 4.7× the trailing baseline.
~16 forks/day, 7.6× the trailing baseline.