8 Google Jules alternatives after the 2026 shutdown
Published
Summary
Google announced on October 29, 2026 that it is shutting down Jules, its asynchronous coding agent. Sessions stop on November 11, and the service closes on December 31, 2026. These eight alternatives are for teams that handed Jules tasks and want another agent to run that work in the cloud and return pull requests.
Why teams look
What happens to Google Jules
Google posted the schedule in the Jules changelog. It says it is winding Jules down to bring its agentic coding work together, and that what it learned from Jules is shaping other Google products, including Antigravity.
- October 29, 2026: Google announces that Jules will shut down.
- November 11, 2026: last day to continue sessions. After this date Jules is read-only.
- December 31, 2026: Jules shuts down.
- Your code, branches, and pull requests are already in GitHub and stay there.
- Jules-side data is not in GitHub: settings, environment variables, setup scripts, scheduled tasks, memories, and session history with plans and patches. Google's export uses the Jules Tools CLI, and the export can include environment variable values, so store it like a secret.
8 Google Jules alternatives
Google Jules alternatives at a glance
The table compares each tool by what it actually is, where the agent runs, and who it fits. Product surfaces change quickly in this category, so verify pricing and deployment details against each vendor before committing.
| Tool | Product model | Where work runs | Best for |
|---|---|---|---|
| Replicas | Cloud agent platform for delegated engineering work | One isolated Linux VM per task; dedicated or self-hosted for enterprise | Teams that want Jules-style async tasks with a choice of agents, scheduled runs, and GitHub or GitLab |
| OpenAI Codex | Provider-native coding agent from OpenAI | Local CLI and IDE, plus OpenAI-hosted cloud tasks | Teams that want the closest hosted task-to-PR flow, on OpenAI models |
| Claude Code | Provider-native coding agent from Anthropic | Local terminal and IDE, plus Anthropic-hosted web sessions | Teams that want Anthropic-hosted sessions on Claude models |
| GitHub Copilot coding agent | Agent built into GitHub | GitHub Actions runners | Teams that started Jules from GitHub issues and want that inside GitHub |
| Cursor | AI-native code editor with Cloud Agents | Local editor; Cloud Agents run in isolated VMs | Teams that want one editor and cloud agents from the same vendor |
| Devin | Autonomous software engineer | Managed Devin cloud sessions | Teams that want one packaged agent with its own workspace |
| OpenHands | Open-source coding agent platform | OpenHands Cloud or self-hosted | Teams that want an open-source agent they can host themselves |
| Antigravity CLI | Google's terminal coding agent, replacing Gemini CLI | Developer's own machine | Developers who want to stay with Google and Gemini and can work on their own machine |
Replicas: managed parallel engineering work with harness choice
Replicas is a cloud agent platform for delegated engineering work. Assign features, refactors, bug fixes, or tests; the agent plans the work, changes code, runs checks, and returns a pull request or investigation for your team to review. Independent tasks can run in parallel, and engineers can inspect and steer each session.
Work starts from wherever it already lives: a Linear issue, a Slack thread, a PR comment, a failed CI run, a schedule, a webhook, or the dashboard. Because Replicas is harness-agnostic, you can use existing Anthropic, OpenAI, Bedrock, or other inference credentials where supported instead of buying model usage through one vendor.
Developer is $50 a month and Team is $200+; each includes workspace usage equal to its price. Every organization starts with $100 of free usage and no credit card. Enterprise plans add SOC 2, SCIM, audit logs, static egress IPs, and single-tenant or self-hosted deployment.
OpenAI Codex
Codex gives ChatGPT subscribers a coding agent in the terminal, IDE, and browser, with cloud tasks that run in OpenAI-managed sandboxes and open pull requests.
Compare OpenAI-hosted tasks with running the Codex CLI through Replicas if your team wants to choose among several coding harnesses in the same platform.
Claude Code
Claude Code is the harness many engineering teams already trust for daily work. It runs in the terminal or IDE, supports plans, hooks, skills, and MCP servers, and is often the reference point in agent comparisons.
Anthropic also offers hosted Claude Code sessions that run independently in parallel and can return pull requests for GitHub repositories. Replicas is another way to run Claude Code in the cloud, with a choice of supported harnesses and shared environment configuration across them.
GitHub Copilot coding agent
Copilot's coding agent can be assigned a GitHub issue, work in a GitHub Actions environment, and open a pull request for review. For teams already paying for Copilot, it is the lowest-friction way to try delegated work.
Execution is bound to GitHub Actions and the GitHub surface. Teams on GitLab, teams that need browsers and long-running services in the agent's environment, or teams that want to choose the harness look elsewhere.
Cursor
Cursor is the most widely adopted AI-native editor. Its agent mode, Cloud Agents, Bugbot review, and CLI make it a full ecosystem for teams happy to standardize on Cursor for both interactive and background work.
The trade-off is ecosystem commitment. Model usage is metered through Cursor, and the cloud agent is Cursor's agent. Teams that already trust Claude Code or Codex, or that want to reuse existing inference contracts, tend to look for a workspace layer instead.
Devin
Devin from Cognition defined much of the autonomous software engineer category. It ships with its own workspace, Playbooks for repeatable tasks, Slack and Linear intake, and enterprise administration.
Devin is a single agent with a single working model. That is a feature for teams that want one vendor to own the whole experience, and a limitation for teams whose engineers already have strong preferences about which harness does the work.
OpenHands
OpenHands is the most established open-source cloud coding agent. It is model-agnostic, can be self-hosted, and has a managed cloud offering for teams that want the open foundation without running it themselves.
Self-hosting shifts environment management, scaling, and security onto your platform team. That is the right trade for some organizations and unnecessary overhead for others.
Antigravity CLI
Google names Antigravity as the product that carries forward what it learned from Jules. Antigravity includes a desktop app and Antigravity CLI (agy), which replaced Gemini CLI for Google AI plan users in June 2026.
Antigravity runs on your own machine. Google has not announced hosted, asynchronous tasks in Antigravity, so it does not yet replace the part of Jules that kept working after you closed your laptop.
Migration
How Jules features map to Replicas
Most Jules features have a direct counterpart in Replicas. The main differences are the model and the agent: Jules ran Google's own agent on Gemini, while Replicas runs Claude Code, Codex, Cursor, OpenCode, or Pi with your own subscriptions or API keys.
| Jules | Replicas |
|---|---|
| Task started from the Jules web app | Workspace started from the app, Slack, Linear, GitHub, GitLab, the CLI, or the API |
| Task VM on Ubuntu with Docker | Workspace: an isolated Linux VM with Docker, a desktop, and Chrome |
| Setup script with Run and Snapshot | warmHook in replicas.json, run in the repository ahead of time so workspaces start with dependencies installed, and a startHook |
| Environment variables | Environment variables, with sensitive values hidden after saving |
| AGENTS.md | AGENTS.md and CLAUDE.md, added to the agent's instructions |
| Scheduled tasks | Automations with schedule triggers |
| CI Fixer | CI failure response on pull requests linked to a workspace |
| Render integration and MCP servers | Plugins, including Render, Neon, and Supabase, plus the Linear integration |
| Jules Tools CLI and REST API | CLI, API, and MCP server |
| Gemini models | Claude, GPT, and other models; Gemini through Cursor, or through OpenCode and Pi with OpenRouter |
| GitHub repositories | GitHub and GitLab repositories |
Decision guide
How to pick a Google Jules alternative
Most teams are not choosing between good and bad tools. They are choosing between working models: an editor, a packaged autonomous engineer, a provider-native CLI, an open-source agent, or a shared cloud workspace. Decide which model fits how your team wants to delegate and review work, then compare products inside that model.
- You want the same flow on another vendor's models
- Codex cloud or Claude Code on the web, which also clone a repository into a hosted sandbox and return a pull request.
- You want work to start from GitHub issues
- GitHub Copilot coding agent if the team already lives in GitHub.
- You want to stay with Google
- Antigravity, keeping in mind that it runs on your own machine for now.
- You want a choice of agents, schedules, and team triggers
- Replicas, which runs several agents in managed cloud workspaces.
Replicas fit
When Replicas is the right Google Jules alternative
Replicas is strongest when the goal is delegated, reviewable engineering work in the cloud rather than a better local editing experience. Teams typically shortlist it when several of the following are true.
- You want to keep assigning tasks and coming back to a pull request, without the agent depending on your laptop.
- Your team wants to pick Claude Code, Codex, or another agent per task, with subscriptions or API keys it already pays for.
- You relied on scheduled tasks or CI fixes in Jules and want them to keep running.
- Work should start from Slack, Linear, GitHub, schedules, or webhooks as well as a web app.
- Some repositories are on GitLab.
Evaluation
Run the same five tasks through every finalist
Demos favor whichever product built the demo. Pick tasks from your own backlog and run them through each finalist with the same repository, the same review standard, and the same person judging the result.
- A code review follow-up: address reviewer comments on an open pull request and get CI green again.
- A CI failure: investigate a failing job, reproduce it, and ship a fix with the reasoning attached.
- A small feature from a ticket: implement it end to end, including tests, from a Linear or GitHub issue.
- A flaky end-to-end test: find the root cause instead of adding a retry.
- A backlog cleanup pass: remove dead code or stale feature flags across the repository without breaking anything.
FAQ