Launching today

ChaseOS Studio

Launching today

Local-first AI workspace where agents run under approval.

0 followers

Local-first AI workspace where agents run under approval.

0 followers

Visit website

ChaseOS Studio is a local-first AI workspace for Windows. Project context compounds in a private typed graph instead of resetting every session. Agents run on your machine inside declared runtime profiles and stop at approval gates before consequential actions. Every run records what it read, produced, and was refused. Community is a free tier; ChaseOS Core is MIT, while Studio is commercial.

Free Options

Launch tags:Productivity•Developer Tools•Artificial Intelligence

Launch Team

Framer AI AgentsDesign and publish professional sites with AI

Promoted

Maker

📌

Windows-only first: ChaseOS Studio currently supports Windows 10 (1809+) and Windows 11, x64. It is not a hosted agent service. I built ChaseOS because project context kept resetting between AI sessions, while tools that could act often asked for too much trust. Studio keeps sources, decisions, approvals, runs, and outputs in a private typed graph on your machine. Agents work from scoped context inside declared runtime profiles, and sending, publishing, or spending stops at an approval gate. The Community tier is the complete local product, not a trial. ChaseOS Core is MIT; Studio itself is commercial. The Windows installer is signed and has a published SHA-256. I would especially value feedback on whether the approval and audit model makes unattended local agents easier to trust.

Report

4d ago

Forum Threads

p/chaseos-studio

•

1d ago

What must stay local for an AI agent to be genuinely local-first?

Disclosure: I m building ChaseOS Studio, a local-first workspace where agents operate under explicit approval and evidence boundaries.

I do not think local model and local-first product are the same thing. An app can call a cloud model and still keep the operator in control. It can also run a model locally while trapping durable state in an opaque store that is difficult to inspect, export or recover.

The boundary I m testing keeps five control surfaces on the operator s machine:

1. Durable project truth in inspectable, exportable representations

p/chaseos-studio

•

2d ago

Should captured information become agent memory automatically?

Disclosure: I m building ChaseOS Studio, and this is the memory boundary I m testing.

Most agent-memory stacks make capture and trust almost the same event: ingest a page or attachment, embed it, and let future agents retrieve it.

I m taking a different approach. New material enters Intake first. Its source remains visible, a person decides whether it belongs in the workspace graph, and rejection happens before it becomes durable agent context.

That separates three decisions that are often collapsed:

p/chaseos-studio

•

4d ago

Where should an AI agent stop and ask permission?

Disclosure: I m building ChaseOS Studio.

Most agent tools force a choice between supervising every step and granting broad autonomy. I m testing a third approach: let work continue locally, but require approval before publishing, external sends, protected writes or other consequential actions. The run history then records what the agent read, produced and was refused.

I m curious where other builders draw that boundary. Which actions would you allow unattended, and which should always pause for a human decision?

If you want to explore the current Windows workspace and try the free Community edition (the complete local product, not a trial): https://chaseos.ai/?utm_source=p...

View all

Forum Threads

p/chaseos-studio

•

1d ago

What must stay local for an AI agent to be genuinely local-first?

Disclosure: I m building ChaseOS Studio, a local-first workspace where agents operate under explicit approval and evidence boundaries.

The boundary I m testing keeps five control surfaces on the operator s machine:

1. Durable project truth in inspectable, exportable representations

p/chaseos-studio

•

2d ago

Should captured information become agent memory automatically?

Disclosure: I m building ChaseOS Studio, and this is the memory boundary I m testing.

Most agent-memory stacks make capture and trust almost the same event: ingest a page or attachment, embed it, and let future agents retrieve it.

That separates three decisions that are often collapsed:

p/chaseos-studio

•

4d ago

Where should an AI agent stop and ask permission?

Disclosure: I m building ChaseOS Studio.

I m curious where other builders draw that boundary. Which actions would you allow unattended, and which should always pause for a human decision?

If you want to explore the current Windows workspace and try the free Community edition (the complete local product, not a trial): https://chaseos.ai/?utm_source=p...

View all