usetig/sage
An LLM council that reviews your coding agent's every move
This project acts like a senior engineering colleague, reviewing the thought process and plans of your AI coding assistant. It takes the ongoing conversation and proposed solutions from your coding AI as input and provides a critique card, suggesting alternative approaches or ready-to-paste messages for your AI. This is for software developers who use AI tools like Claude Code to help them plan and write code.
Use this if you want to catch fundamental flaws in your AI coding assistant's approach or plan before it writes any code, helping you avoid optimizing a suboptimal solution.
Not ideal if you are only looking for a tool to catch syntax errors or security issues in already written code, as existing code review tools are better suited for that.
Stars
86
Forks
7
Language
TypeScript
License
—
Category
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.
Featured in
Higher-rated alternatives
code-yeongyu/oh-my-openagent
omo; the best agent harness - previously oh-my-opencode
nrslib/takt
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and...
beclab/Olares
Olares: An Open-Source Personal Cloud to Reclaim Your Data
neomjs/neo
The Application Engine for the AI Era. A multi-threaded, AI-native runtime with a persistent...
rush86999/atom
Atom Agent, automate your workflows by talking to an AI — and let it remember, search, and...