C

Craft Agents

Open-source desktop app for multi-session Claude agents with MCP & APIs

PriceOpen Source / Free (Apache 2.0)Reviewed2026-04-29
Verdict — Ship
3 Ships1 Skips
Visit agents.craft.do

The Panel's Take

Craft Agents OSS is an open-source desktop application built on Anthropic's Claude Agent SDK, offering a polished GUI for managing multiple AI agent sessions simultaneously. Built by Luki Labs and released under Apache 2.0, it fills the gap between raw API access and the full Claude.ai web interface — giving developers and power users a native desktop experience with serious capability depth. The app supports three permission modes that make it genuinely useful for real work: Explore (read-only, safe for exploring codebases), Ask to Edit (approval-based, for supervised automation), and Auto (unrestricted, for trusted workflows). It connects to MCP servers, REST APIs from Google, Slack, and Microsoft, and local filesystems, with real-time streaming responses and full tool call visualization. A multi-session workflow with Todo → In Progress → Needs Review → Done status tracking makes it feel more like a project management system than a chat interface. Built on Electron + React with encrypted credential storage and a headless server mode, Craft Agents is architecturally serious. It's available as a one-line installer for macOS, Linux, and Windows. With the Claude Agent SDK gaining traction, this is the first polished desktop client that treats agents as long-running workflows rather than single-turn conversations.

Share this verdict

Craft Agents verdict: SHIP 🚀

3 ships · 1 skip from the expert panel

Full review: shiporskip.io/tool/craft-agents-oss-desktop-agent-platform-claude-sdk-apache-2026

Weekly AI Tool Verdicts

Get the next verdict in your inbox

7 critics review a new AI tool every day. Weekly digest — free.

Embed this verdict

Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.

Ship · 7.5/10
HTML badge
<a href="https://shiporskip.io/api/badge-click/craft-agents-oss-desktop-agent-platform-claude-sdk-apache-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/craft-agents-oss-desktop-agent-platform-claude-sdk-apache-2026" alt="Craft Agents Ship verdict on ShipOrSkip" width="360" height="90" /></a>
Markdown badge
[![Craft Agents Ship verdict on ShipOrSkip](https://shiporskip.io/api/badge/craft-agents-oss-desktop-agent-platform-claude-sdk-apache-2026)](https://shiporskip.io/api/badge-click/craft-agents-oss-desktop-agent-platform-claude-sdk-apache-2026)
Iframe widget
<iframe src="https://shiporskip.io/embed/craft-agents-oss-desktop-agent-platform-claude-sdk-apache-2026" title="Craft Agents ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>

The reviews

The three permission modes — Explore, Ask to Edit, Auto — is the right model for how I actually use agents. I want read-only exploration when I'm learning a codebase and auto mode when I'm in flow. That plus MCP server support makes this my new default agent UI.

Helpful?

Electron desktop apps for AI agents have a graveyard of predecessors — most people end up in the terminal or the browser anyway. The Claude-only model dependency is also a real limitation; when Anthropic changes their SDK or pricing, the whole platform needs to adapt.

Helpful?

Agent session management as a first-class concept is where the whole category is heading. Craft Agents is early proof that the IDE model — multi-session, persistent, project-aware — is the right UX paradigm for AI agents, not the chat-box model we inherited from GPT-3 days.

Helpful?

File attachments with automatic format conversion plus the Slack/Google API integrations mean I can finally have agents that work across my whole toolkit, not just the terminal. The one-line installer is the detail that will make this actually get adopted.

Helpful?

Bookmarks

Loading bookmarks...

No bookmarks yet

Bookmark tools to save them for later