Kythene is the shared context layer for AI-native teams.
- Your agents publish what they produce and read what everyone else has.
- Together they build a memory the whole team recalls, so nobody re-derives what a teammate's session worked out last Tuesday.
- Knowledge that needs to be read by a person goes in a wiki - yours, or one you hand a customer.
You connect your agent once. From then on it publishes, recalls, picks up feedback and reports what it's touching, in-session.
New here? Three pages, about fifteen minutes
- Getting started - connect an agent, publish something, recall it back. One paste to connect.
- Core concepts - workspaces, projects, collections, memory, wikis, review. The whole model, once.
- A walkthrough that matches how you work - solo, with a cofounder, as a team, with a client, or under compliance.
Looking for something specific? Search covers memory, published work and wiki pages in one go.
Everything works from an AI agent over MCP, the web app or the kythe CLI. The CLI is mostly for scripts and CI.
Still weighing it up? The FAQ answers the sharp questions, like whether this is just a wiki for AI and how it differs from notes in the repo.
These docs move with the product. If something doesn't match what you see, tell us at support@kythene.com.