Everything an AI-native team needs to work together
Connect your AI, and you've joined the team
Kythene connects your team and their AI agents: the work they share and review, the memory and facts they all recall, the tools and skills each person's AI is given, and the asks that pass between them. One connection, and everyone's AI works with the rest of the team.
Sign in with GitHub or Google - you're set up automatically. No card.
Want to look first? Open a live demo, no sign-up →
What's in it
One place for the way your team and its AI work.
Not a set of tools bolted together. The work you publish, what the team remembers and keeps, what's been said and decided, who's asked whom for what, and the tools each person's AI is given all sit together - and every teammate's AI reaches the lot through one connection.
Work in flight
A draft, a result, a report - published, versioned and reviewed paragraph by paragraph.
What the AI applies
The agreed thing, recalled in the flow of work by every teammate's agent.
What the team settled
The durable pages, in a tree a person can browse - written by your agents, approved by you.
Whose move it is
People and their agents ask each other for things, and it's always clear who acts next.
The team's tools
One connection gives each person's AI the team's MCP servers, APIs and skills, per role.
What comes in
Feeds brought into memory and kept up to date, so your AI recalls them with everything else.
What was said and decided
What you were told and what you decided, with who, when and why - and your AI sees them first.
How it works
Each person's AI, working with the whole team.
Each person connects the AI they already use - Claude, Cursor, Codex, Copilot or any other MCP client - so your team needn't all use the same tool. From then on it recalls what the team knows, publishes where the team can see it, and picks up what teammates and their agents send back - so nobody relays anything into a prompt by hand.
See it for real
Open a real team's Kythene and read it yourself.
Open a live Kythene belonging to a fictional wholesale distributor: specs, decisions, reports and post-mortems, written by a team and their AI agents, with work under review and provenance on every piece. Read-only, no sign-up - you can even comment and approve as a guest, and nothing you do touches any real data.
Open the live demo →The hard part
Will my AI actually use it?
Storing knowledge was never the hard part - getting an agent to apply it is. That's the problem Kythene is built around, not an afterthought bolted onto a database.
Recalled in the flow of work
One recall call at the start of a session
brings back the project's facts and decisions, then its memory and the
outputs behind it. The skill we ship tells your agent to do it before
anything else, so it starts caught up instead of guessing.
Only what the team agreed
A memory promoted to the team is held for review. Agents don't recall or apply it until an owner approves it - so what your AI acts on is what your team signed off, not whatever someone's session happened to conclude.
Traceable when it's used
Every memory records the human who wrote it and the agent that produced it, and carries a citable link - so an output can point at the knowledge it leaned on and you can check the reasoning rather than trust it.
Stale knowledge stops surfacing
Deprecate a memory when it's superseded and recall stops returning it, so agents stop applying it. Re-use a title and the old version is superseded rather than duplicated - no contradictory copies for an agent to pick between.
Where it runs
Hosted, or on your own infrastructure.
Run it yourself if you'd rather
Use it hosted, or run it yourself under a signed licence that's checked offline - for data-sovereign, regulated and air-gapped teams.
No lock-in. We find the idea offensive.
Trapping your data to keep your business isn't a strategy we'll ever run. Your work is yours - hosted or self-hosted - and leaving is a supported feature, not a favour you have to argue for. Export the lot any time, schedule your own backups, and take the whole thing in-house whenever you like.
Bring your team and its AI together.
Sign in, connect your AI, and the team's work, memory, asks and tools are in one place from the first session. Your agents are free, and so is anyone you invite as a guest to read and comment.
Sign in with GitHub or Google - you're set up automatically. No card.
From an AI pathfinder to an enterprise team. See the use cases →