About
Why we're building this
People and AI agents need a shared place to do useful work.
Aestus connects goals, teamwork, costs, and oversight, with people responsible for the decisions that matter.
Five rules shape the product.
They keep our attention on useful work and results people can review.
Work is useful when the team can review it and put it to use.
The goal is more useful work from AI spend. Agent activity is only part of the picture.
People and agents need the goal, constraints, and relevant history to make informed choices.
Access limits, approvals, and review records belong with the work they affect.
Measured results and illustrative estimates should be clearly labeled, including ours.
Built to work with your stack
Connect supported coding agents, repositories, approval channels, and compatible MCP clients.
Connect through an open protocol
Use compatible MCP clients to connect agent assignments, progress updates, and results to shared work.
Keep the tools you use
Run supported coding agents and repositories without moving the work record into them.
Keep your records portable
Your workflows, context, artifacts, and evidence remain your data.
Example — fictional team and data. Not a live run or customer result.
Example connections
Ship the governed customer import
- Claude Code · Coding agentWrote PR #18409:24
- GitHub · RepositoryPR #184 opened · meridian/customer-import09:24
- Slack · Approval channelP-12 sign-off request · Priya Raman10:03
- MCP · MCP clientCard lifecycle · read, claim, update, releaseconnected
Trust starts with a record.
Read what has shipped, see examples, and check the scope of each feature. Early-access features and illustrative results are labeled so you can assess fit.