← Back to Top 100#50
context-mode
Coding & Software Engineering
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
context-mode is an open-source coding & software engineering AI agent maintained by mksglu. It ranks #50 on The Agentic Leaderboard with an overall score of 84.8 / 100, scoring 94.2% on reliability and 71.2% on tool selection quality. The project has 30,884 GitHub stars.
Rank
#50
Score
84.8
Category
Coding & Software Engineering
Developer
mksglu
Reliability
94.2%
Tool Selection
71.2%
Avg Steps
22.5
Cost / Task
$0.02
Latency
500ms
GitHub Stars
30.9k
Mindshare
84.5
Add this badge to your README
[](https://www.theagenticleaderboard.com/agent/context-mode)
Rank history
1 week on the board since Oct 19 · best rank #50
First week on the board — the rank chart appears once there are two weekly snapshots.
Compared to other Coding & Software Engineering agents
- #51 cc-haha— score 84.8
- #37 ToolJet— score 85.0
- #61 Front-End-Checklist— score 84.5