usetig/sage

An LLM council that reviews your coding agent's every move

30
/ 100
Emerging

Embeds itself into Claude Code workflows to automatically critique agent reasoning and plans before implementation, not just final code diffs. Uses tool-calling capabilities to inspect codebases and search during review, generating structured verdict cards with alternatives and ready-to-paste feedback. Designed to scale to multi-model ensembles (Claude, Gemini, Grok) for cross-checking agent decisions, automating the manual pattern of running parallel agents for second opinions.

No License No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 5 / 25
Community 10 / 25

How are scores calculated?

Stars

86

Forks

7

Language

TypeScript

License

Last pushed

Dec 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/usetig/sage"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.