Orkas
Open-source desktop AI workforce coordinated by Commander
What is Orkas?
Orkas is an open-source, local-first desktop AI workforce. Commander turns goals given through one chat into executable plans and coordinates specialist agents in parallel or in sequence to complete complex work together.
Developers, creators and small teams can use workflows for research, coding, data analysis, documents, presentations and video, and configure reusable agents, skills and MCP tools. VideoStudio is built into Orkas.
The core app is free; model calls and optional services may incur charges. Use supported model providers with your own API keys or compatible local model endpoints. Packaged installers are available for macOS and Windows; Linux runs from source.
Source code:
Ready to launch?
Submit your product and get discovered by builders and creators worldwide.
Launch Now
FounderPlaybooks.
What other founders did to grow.
2722 dispatches from hundreds of founders, pulled from the week's best podcasts.
Revisit your assumption every now and then — every 6 months or whatever — or at least control that gap between what we're sending and what is actually happening is not too big.
Revisit signal engineering assumptions every 6 months — they drift as your business changes
Signal engineering is not a set-and-forget system. Pricing changes, monetisation experiments, new channels, and macroeconomic shifts all alter which users are actually valuable — meaning the engineered values sent to ad platforms gradually diverge from reality. Thomas Petit monitors the gap between predicted and actual value; when it widens beyond acceptable tolerances (especially at the country level), he updates the model rather than letting the platform optimise against stale assumptions.
Tracking is broken even if performance is not right... if you look at the itunes dashboards you're like you think all right you know you didn't just go crashing down which is what i was afraid would happen right right that has not happened.
Tracking Is Broken — But Performance May Not Be. Check Blended Numbers Before Panicking
After ATT launched, reported CPAs from Facebook skyrocketed because the privacy threshold hid attribution — but many apps' iTunes dashboards showed stable or growing trial numbers. The lesson: platform-reported metrics became unreliable directional signals, not ground truth. Before cutting iOS spend, check blended acquisition cost (total spend / total trials) against the App Store revenue dashboard to see if real performance actually degraded.
There's a play for whatever you're stuck on.
Read all 2722 playbooks