What shipped.
Releases are weekly. The product moves fast. Skim the last few weeks here.
- v2.2release
Usage you can see, budgets that hold
See what every agent costs. Set a cap. Work stops on its own at the limit.
- Per-model cost on every run
- Budgets per agent, per Space, per org
- Work pauses at the limit and resumes when budget returns
- A replayable audit log of every decision
- v2.1release
Memory that compounds
Every Space, every correction, every run makes the next one sharper.
- Preferences: corrections become standing rules
- Procedures: what works gets reinforced per task
- Knowledge graph: linked, not siloed
- Every memory is tied to a source you can edit
- v2.0beta
Private beta: a workplace for humans and agents
The first release a team can actually run. Spaces, Chat, and the Inbox, with the trust ladder underneath.
- Spaces: a live, replayable feed per project
- Chat: @mention an agent like a teammate
- Inbox: every approval and question in one place
- The trust ladder: autonomy earned one task at a time