The work behind the words.
Plans, research, and decisions, with saved revisions you can return to.
About documentsKeep your notes, ideas, and preferences in one place. Bring them to the AI tools you use, so every new conversation starts with a little more you.
Space is in development. Public access isn’t open yet.
Start with the tools you already love.
Your notes, preferences, and plans, in one place.
Use what you’ve saved in your next conversation.
Useful context shouldn’t disappear with the chat window. An agent you authorize saves it to Space, then finds it when the next piece of work begins.
Ask your agent to keep a useful preference, decision, or next step.
See what was saved. Follow a source, make a correction, or remove it.
Your agent finds what’s relevant the next time you work together.
Connects over the Model Context Protocol (MCP).
A quiet workspace for the things that matter. Read a plan, find the next step, and follow the context back to its source.
Plans, research, and decisions, with saved revisions you can return to.
About documentsKeep the next step close to the context behind it, on a board or a list.
About tasksPreferences and decisions, saved with their sources and organized your way.
About memoryCreate categories such as Dev or Accounting and describe what belongs in each. Space files new memories into the right category and project, and you can correct any assignment.
Learn about categoriesAtlas releases need an automated regression test before deployment.
Choose which agents have access. See what was saved, correct what has changed, and revoke a connection whenever you need to.
Privacy & dataYour chosen agentOnly the access you approve
Space and the providers you authorize process the content used to serve your requests.
An agent can work across a business without carrying every project's assumptions into every task. Here is where workspaces, skills, and Space each help.
Two saved memories can belong together without saying the same thing. Here is how I use Jev to judge those connections in Space, without comparing every memory with every other memory.
An agent can revise its instructions without retraining its model. Hermes and Prime Agent show how the software around a model can retain useful lessons, organize work, and make improvement measurable.
Give your work a place to continue.