Jackalope
A desktop workspace for running coding agents in parallel and reviewing their changes.
- Tool type
- Desktop workspace for AI coding agents
- Made for
- Developers
- Runs on
- Windows, macOS and Linux desktop
- Advertised Windows, macOS and Linux builds; current installer availability requires confirmation.
What it does
Jackalope is a local desktop workspace for developers who want to coordinate AI coding agents on repository tasks. Give it a plain-language brief and select supported installed agents, including Codex, Claude Code, Gemini CLI, Grok, OpenCode, Kimi Code and Antigravity. Jackalope can run tasks concurrently, each in a separate Git worktree, collect agent questions and show the resulting diffs and checks for review. Changes do not merge until you approve them.
The app keeps project guidance and saved lessons available to tasks and supports agent-account profiles, browser automation, terminal access and scheduled tasks while the app is open. The website advertises Windows, macOS and Linux downloads and free email-confirmed accounts, while the repository retains prerelease and approved-account requirements, including source builds. Confirm installer and native-task access before adopting it. Bring supported agent tools and provider accounts; separate charges and data policies apply. Git worktrees isolate changes, not operating-system privileges.
What it can do
- Run coding-agent tasks in parallel Git worktrees
- Collect task questions and present diffs and checks for human approval
- Share project guidance and saved lessons across tasks
- Maintain named account profiles and project defaults for agents
- Automate browser interactions, screenshots and accessibility audits
- Run scheduled tasks while the app remains open and invoke agents from a repository terminal
Works with
- Codex
- Claude Code
- Gemini CLI
- Grok
- OpenCode
- Kimi Code
- Antigravity
- MCP tools
- DeepSeek
- OpenRouter
Before you choose
- Jackalope does not include model access; provider subscriptions, usage limits and charges depend on the agent and provider.
- Agents may send repository code and context to their providers; connected tools have separate data policies.
- Git worktrees isolate changes, not agents’ or tools’ operating-system privileges.
Listed under
Get started
Website advertises free email-confirmed access; repository retains approved-account requirements. Confirm current native-task eligibility.
- Check the official download page for the build matching your system.
- Confirm account activation and native-task eligibility; the repository retains approved-account requirements.
- Install supported agent tools, authenticate your model accounts and review permissions before connecting a repository.
Plans and prices
No recurring Jackalope charge is stated. Agent and model access are not included and may incur provider charges.
- Free account advertised; confirm native-task eligibility
- Bring supported agents and provider accounts
Source: jackalope.dev, checked 2 Nov 2026. Prices can change; check before you buy.
Sources for this overview
Product pages, documentation, and pricing checked 2 Nov 2026. Each source supports part of the overview; availability and prices can change.
- Jackalope: Run AI coding agents in parallel ↗jackalope.dev
- Download the Jackalope app for Windows, macOS & Linux ↗jackalope.dev
- Jackalope: Run AI coding agents in parallel ↗jackalope.dev
- GitHub - Jackalope-Dev/jackalope: A desktop workspace for coding agents, parallel Git worktrees, and code review. · GitHub ↗github.com
Ratings and reviews
No ratings for Jackalope yet.
What’s changed
Free accountSignals
Free accountData and security
Free accountCompare with similar tools
Free accountWhere this comes from
How we research- Company website
- jackalope.dev: product, pricing and policy pages
- YC directory mirror
- Batch and company name
- Social accounts
- Accounts the company links, and its posts on X
- Human review
- Checked by a person
- knowledge_base
- manual_review
Last checked 2 Nov 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.