Is this your project? Give it 30 days of featured visibility.
Promote your projectOrkas
Orkas is an open-source, local-first multi-agent AI desktop client for macOS and Windows. It enables users to direct a team of specialist AI agents coordinated by a Commander agent to complete complex multi-step workflows.
Official website(opens in new tab)OfficialChecked

Evidence-backed listing facts
Only known values with retained provenance are shown. Missing fields are omitted instead of being filled with guesses.
- Product form Verified
- Ready-to-use agent
Evidence: Orkas is an open-source, local-first multi-agent AI desktop client for macOS and Windows.
Official website(opens in new tab)OfficialChecked
- Primary job Verified
- Workflow automation
Evidence: Command an AI team across code, docs, research, data, operations, and more.
Official website(opens in new tab)OfficialChecked
- Deployment Verified
- Local / Self-hosted
Evidence: The open-source desktop edition is free to download and self-host, and it runs without an Orkas account
Official website(opens in new tab)OfficialChecked
- Interfaces Verified
- Desktop
Evidence: Orkas is an open-source, local-first multi-agent AI desktop client for macOS and Windows.
Official website(opens in new tab)OfficialChecked
- Source availability Verified
- Open source
Evidence: The Orkas desktop client is open source under the MIT license at github.com/Orkas-AI/Orkas.
Official website(opens in new tab)OfficialChecked
- MCP support Verified
- Native
Evidence: MCP and connectors Connect data sources, tools, and community capabilities through supported integrations.
Official website(opens in new tab)OfficialChecked
- API Verified
- Public API
Evidence: Membership credits can be used in external products with an API key .
Official website(opens in new tab)OfficialChecked
- Autonomy Verified
- Autonomous execution
Evidence: Agents are capable and run autonomously on your machine.
Official security information(opens in new tab)OfficialChecked
- Human approval Verified
- Optional
Evidence: Orkas provides three local-access modes: workspace approval, all-files approval (the default), and all-files auto. In approval modes, sensitive local file or shell operations ask for…
Official security information(opens in new tab)OfficialChecked
Reviewed sources
These sources were reachable when the listing evidence was checked.
Listing checked
About Orkas
Orkas is an open-source, local-first multi-agent AI desktop client for macOS and Windows. It enables users to direct a team of specialist AI agents coordinated by a Commander agent to complete complex multi-step workflows.
Evidence: Orkas is an open-source, local-first multi-agent AI desktop client for macOS and Windows. A super-powered Commander coordinates specialist agents to complete complex work together.
Official website(opens in new tab)OfficialChecked
By default, Orkas stores configuration, chat history, files, and credentials locally on the user's machine. Users can start free using managed official models or connect their own AI model providers directly.
Evidence: Local-first: your files, keys and outputs stay on your machine; use managed official models or connect your own provider.
Official website(opens in new tab)OfficialChecked
Capabilities
Commander multi-agent orchestration breaks complex goals into structured plans, routes work to specialized agents, and returns consolidated deliverables.
Evidence: Describe the outcome once. Commander breaks it into work, assigns the right Agents and skills, follows up on blockers, and brings the final delivery back for review.
Official pricing(opens in new tab)OfficialChecked
Local-first security architecture encrypts API keys at rest using authenticated AES-256-GCM without routing bring-your-own-key requests through proxy servers.
Evidence: With your own keys, your API keys and model traffic never go through Orkas — keys stay in an encrypted local config, and model calls go straight to your own provider, fully auditable.
Official security information(opens in new tab)OfficialChecked
External products can consume Orkas membership credits via an API key.
Evidence: Membership credits can be used in external products with an API key .
Official website(opens in new tab)OfficialChecked
Supports Model Context Protocol (MCP) integrations and connectors to link data sources, tools, and community skills.
Evidence: Connect data sources, tools, and community capabilities through supported integrations.
Official website(opens in new tab)OfficialChecked
Use cases
Conduct market research with an evidence trail to decide on market entry strategies.
Evidence: Bring customer interviews, usage data, competitor material, and current sources into one evidence trail. Contradictions and gaps stay visible in a recommendation your team can review.
Official website(opens in new tab)OfficialChecked
Turn a product brief into aligned launch assets including articles, social images, and reviewable product videos.
Evidence: Keep the same product facts, CTA, and creative direction across the launch article, social image, and reviewable 60-second video.
Official website(opens in new tab)OfficialChecked
Automate recurring weekly operational reviews by digesting tasks, messages, and meeting notes into team updates.
Evidence: On schedule, automatically read last week’s tasks, messages, and meeting notes, then produce the team update, refresh project notes, and list follow-up owners and due dates for your review.
Official website(opens in new tab)OfficialChecked
Perform repository-aware software development to implement features, fix bugs, or produce working app prototypes.
Evidence: ProductDeveloper reads the repository rules, plans the smallest safe change, implements it, runs the relevant checks, and returns a clear code handoff.
Official documentation(opens in new tab)OfficialChecked
Who Orkas fits — and what to check
Decision guidance below is tied to the cited evidence. Treat observed third-party claims as leads, not product guarantees.
Best for
Indie builders, one-person businesses, and small teams looking to direct a team of AI specialist agents.
Evidence: For indie builders, one-person businesses, and small teams: direct a team of AI specialists to deliver the work.
Official website(opens in new tab)OfficialChecked
Users who want to turn complex multi-domain work into reusable team workflows with full control over data and keys.
Evidence: Orkas is stronger when work needs a team, local context, reusable workflows, and control over model keys.
Official website(opens in new tab)OfficialChecked
Limitations to check
Orkas operates as a local desktop client, not a multi-user server deployment.
Evidence: One thing worth being clear about: Orkas is a desktop client, not a server, so self-hosting means running the app on your own machine rather than deploying a server for a team.
Official website(opens in new tab)OfficialChecked
Local encryption of API credentials protects against casual local disclosure, but not against a forensic attacker who holds both disk access and the app binary.
Evidence: It is not hardware- or keychain-bound, and it does not defend against an attacker who holds both your disk and the app binary.
Official security information(opens in new tab)OfficialChecked
Method: ClawSites keeps discovery copy separate from publishable claims, retains a source excerpt, and displays the date each cited source was checked. Pricing and availability can still change after that date.
Related to Orkas
Similar directory context, not an editorial claim that these products are interchangeable.

AI by Zapier is a built-in tool that lets you add AI action steps to your Zap workflows.

AutoGen is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans.

AutoGPT lets users build, deploy, and run AI agents that carry out complete workflows on demand, on schedules, or from triggers.

Automation Anywhere provides AI Agent Studio with built-in safety and governance guardrails.

AI personal assistants (Claude/ChatGPT) buying and configuring travel eSIMs in chat.

Fay is an AI agent platform for building, deploying, and managing autonomous workers and deterministic workflows.
