Move your coding agents to the cloud

Run Claude Code and Codex in cloud sandboxes with your dependencies installed. Use for Development, Code Review, Background Agents, and more.

Install on GitHub

Free for individuals with a Claude Code or Codex subscription.

your-org
New sessionK

Dashboard

HomeActivitySessionsAutomationsReviews

Platform

EnvironmentsModelsIntegrationsAPIFiles

Account

BillingSettingsHelp

Reply to the agent...

Send

Development

Give every task its own workspace

Run Claude Code and Codex with your repositories, dependencies, and tools already configured. Build features, fix bugs, and run tests in isolated cloud sandboxes.

An Ellipsis development session showing the agent conversation and changed files.
environment.yaml
ellipsis:  kind: environment  name: developmentrepositories:  - name: web-repoimage:  setup: |    cd web-repo    pnpm install --frozen-lockfilecompute:  cpu: 4  memory: 8GB

Code Review

Find bugs before you merge

Ellipsis reviews pull requests against your codebase and flags bugs directly on GitHub. Set review scope and instructions to match the way your team ships.

Code Review

Graphic placeholder

A pull request diff with a review finding anchored to the affected lines.

code_review.yaml
ellipsis:  kind: code_reviewpull_requests:  draft: falsereview:  - name: correctness    harness:      type: claude_code    instructions: |      Find bugs and regressions.      Skip style and formatting.budget:  run: 10

Background Agents

Keep work moving in the background

Start agents on a schedule or in response to events. Let them handle fixes and recurring maintenance, then review the changes and session logs when the work is done.

Background Agents

Graphic placeholder

Scheduled and triggered sessions with their status, recent activity, and resulting pull requests.

automation.yaml
ellipsis:  name: dependency-updatestrigger:  type: cron  schedule: "0 9 * * 1"session:  harness:    type: claude_code  environment: development  instructions: |    Update dependencies in web-repo.    Run tests and open a pull request.  budget:    session: 5

Start agents from anywhere

Start, steer, and review sessions from the terminal, the web app, the API, Slack, or GitHub. Same agents, same logs, same budgets everywhere.

Governance built in
Every session logged, scoped, and capped

your-org / agents
standup-automator.yaml
ellipsis:
name: Standup automator
description: Posts a daily standup digest to Slack
trigger:
type: cron
schedule: "30 8 * * 1-5"
session:
harness:
type: claude_code
model: claude-opus-4-8
instructions: |
Each weekday, summarize yesterday's merged PRs, the
reviews still waiting, and any failing CI, then post
the digest to #engineering and @ the right owners.
budget:
session: 2

$

Agents are defined in YAML

One file declares the agent and the environment it runs in: repositories, dependencies, permissions, and budgets. Check it in, review it, and audit changes like any other code.

Tool callsmerge-referee
Bash
pytest -k auth · passed
Allowed
Edit
tests/test_auth.py
Allowed
gh pr merge
GH_TOKEN is read-only
Blocked
Grep
"flaky" · 3 matches
Allowed
Read
tests/test_auth.py
Allowed

Credentials set before the session starts

Every session runs on credentials minted just for it: the repositories it may touch, the tools it may call, nothing else. Revoked when the session ends.

agents/nightly-migration-checker.yamlUSD, enforced live
session:  budget:    session: 1.50    day: 5.00    week: 20.00    month: 60.00
session_9Kt4vR7m · stopped at its session capbudget_hit

Budgets that stop the session

Cap spend per session, per developer, or over time, in the same YAML. A session that hits its cap stops, and the ledger shows where every token went.

Steps (15)
15Commit pushed28 tok
14thinkingDouble-check the diff before pushing
13Bashgit commit -m 'Release connection on error path'20 tok
12thinkingWrite a clear commit message
11assistantGreen. Committing the fix.14 tok
10Bashpytest -k pool · 142 passed24 tok
9thinkingRe-run the pool suite to confirm the fix
Budget$0.40 / $1.00
Tokens30.8K

Every step is recorded

Every thinking token, tool call, and diff is recorded and attributed. Logs are searchable by the whole team, if you want.

Secure, Managed Infrastructure
that is very easy to use

Ellipsis is built with governance at scale in mind. Permissions are defined before a session starts. Every agent action is logged. You have full control over your data longevity.

More about security
SOC 2Type ICertified
SOC 2Type IIIn progress

Scoped credentials

Minted per session, scoped to the repos you allowed, revoked with the sandbox.

Zero source retention

Your code lives only in the session sandbox and is deleted with it.

Full audit trail

Every command, file change, and tool call an agent made, kept after the sandbox is gone.

Frequently asked questions