Tenjin
Tenjin is a knowledge layer for AI agents so they stop duplicating work. It rides Claude Code/Codex hooks to capture useful information and injects it when needed (such as when an error occurs) for other agents. Knowledge is shared across a team and a global marketplace layer with incentives for contributions. It is currently being benchmarked with an aim of 10% token reduction, and preliminary design partners are being accepted.
What it addresses
AI agents duplicate work because there is no shared knowledge layer between them.
Shared over time
Each entry reflects what was shared on that date. Details may have changed since then.
Tenjin
Tenjin is a knowledge layer for AI agents so they stop duplicating work. It rides Claude Code/Codex hooks to capture useful information and injects it when needed (such as when an error occurs) for other agents. Knowledge is shared across a team and a global marketplace layer with incentives for contributions. It is currently being benchmarked with an aim of 10% token reduction, and preliminary design partners are being accepted.
Problem: AI agents duplicate work because there is no shared knowledge layer between them.
Audience: Teams of developers using AI coding agents
Posted by @AliAbdoli · Original comment ↗
“Working on https://tenjin.sh/ . It's a knowledge layer for agents so agents stop duplicating work. Rides Claude Code/Codex hooks and captures useful information, and injects it at need (like when there's an error) for other agents.”