GitHub · JavaScript
ooples/token-optimizer-mcp
91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
- Stars
- 586
- Forks
- 73
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: ai, ai-agents, caching, claude, claude-code, codex, compression, context-engineering, cost-optimization, developer-tools
Latest data point: Nov 21, 2026 · 586 stars · 73 forks