Player profile
Orkas
An MIT-licensed, local-first multi-agent desktop application where a Commander coordinates specialist agents across research, coding, data, documents, and media.
Profile
Where it fits
Orkas is an open-source, local-first AI workforce for macOS, Windows, and Linux. A Commander decomposes goals and coordinates specialist agents for research, coding, data analysis, documents, video, and slides from one desktop conversation.
It belongs in Open Orchestrators because multi-agent coordination is the product surface: structured dispatch, shared plans, parallel or sequential execution, visibility-scoped context, local files and model keys, and per-agent private memory and skills.
The repository is MIT-licensed and supports bring-your-own model keys, local model endpoints, and external CLI coding agents including Claude Code, Codex, OpenCode, and Cline.
Builder web analytics
Measure projects built with Orkas
Orkas coordinates specialist agents across research, coding, data, documents, and media. Agent Analytics gives those agents user-facing outcome data after an Orkas-built change ships.
Install Agent Analytics on the user-facing surface Orkas agents change. Agent Analytics measures outcomes after deployment; it does not replace Orkas conversations, plans, local files, private agent memory, or execution logs.
First loop to measure
- a user asks Orkas to research, plan, build, or revise a website, docs path, onboarding flow, app surface, or growth experiment
- the Commander dispatches specialist agents and the finished change ships
- the changed surface reports visits, sources, CTA clicks, signup, activation, retention, funnels, and experiment events to Agent Analytics
- a later Orkas task reads those outcomes and chooses the next improvement from measured user behavior
Copyable prompt
Use Agent Analytics for this project. If event reporting is missing, add the tracker and report events for this project surface, including Orkas-built page, traffic source, CTA click, signup, activation event, funnel step, retention signal, or shipped experiment. Verify events are arriving. Then fetch the last 7 days and compare them with the prior 7 days. Tell me which Orkas-built page, traffic source, CTA click, signup, activation event, funnel step, retention signal, or shipped experiment moved users toward value, where users dropped off, which sources mattered, and what my agent workflow should improve next.