AI/ML●●Solid
Sentinel – LLM browser automation using 10x fewer tokens
Token efficiency beats Stagehand — 2-5k vs 29-51k per action with cached selectors.
Solve My ProblemSlick
isoldex
102mo ago
Back to browse
GitHub Repository
A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler
179 starsGo
I Made TS Compiler Graph MCP: 10x Fewer Tokens in Claude Code and Codex
by autobe·Jul 1, 2026·2 points·0 comments
Similar Projects
Developer Tools●●●Banger
Tappi Browser – Fastest AI browser, 3-10x fewer tokens, zero telemetry
Referenced element indexing cuts token spend 3-10x versus DOM-dumping AI browsers.
WizardryBig BrainShip It
shaihazher
104mo ago
AI/ML●●Solid
Cowork/Codex DOCX plugin. Uses 2x fewer tokens than the docx skill
Bidirectional docx-html conversion cuts token usage 2-5x versus Anthropic's built-in skill.
Big BrainNiche Gem
tanin
5613d ago
Developer Tools●●●Banger
MCP Codebase Index – 87% fewer tokens when AI navigates your codebase
MCP query server cuts codebase context by 87% with zero dependencies, measured.
Solve My ProblemBig BrainShip It
localforthewin
104mo ago
AI/ML●●●Banger
Cost-Xray – per-token cost attribution, by tool, skill, prompt and more
Mitmproxy capture shows why each turn costs without touching agent config.
Big BrainSolve My Problem
ruihanli
2013d ago
AI/ML●●Solid
A Bridge Between Claude Code and Codex Using Channels and MCP
Clever use of Claude Channels to push messages—nobody else bridged these two agents yet.
WizardryNiche Gem
darkbatman
203mo ago