Automated pull-request review
Review each new push, keep pull-request descriptions current, and post line-level findings without rereading the full change every time.
Independent tool overview
Ellipsis is a cloud platform for running AI coding agents and incremental pull-request reviews with budgets, scoped permissions, and searchable session logs.
Visit the official Ellipsis.dev site ↗
Overview
Ellipsis began as an AI code-review bot and has expanded into infrastructure for running Claude Code and Codex agents in the cloud. Teams connect GitHub, define agents as YAML in their repositories, and trigger them from pull requests, schedules, GitHub, Linear, Slack, Sentry, the dashboard, CLI, or API.
Its built-in code-review pipeline checks only the commits added since the previous pass, posts confirmed findings as inline GitHub comments, and can be customized with specialist reviewers and a gatekeeper. Ellipsis can run the same feature set in its managed service or inside a customer's AWS VPC.
Use cases
The strongest fit depends on the job you need the product to complete, not the size of its feature list.
Review each new push, keep pull-request descriptions current, and post line-level findings without rereading the full change every time.
Build agents for issue handling, incident diagnosis, maintenance, reporting, and other workflows that need codebase context.
Manage permissions, models, spend limits, shared skills, deployment, and observability across many repositories and developers.
Capabilities
Reviews only new commits, deduplicates findings, and attaches comments to the relevant lines and commit.
Stores versioned YAML agent definitions in the repository and deploys changes through pull requests.
Starts agents from cron schedules and events in GitHub, Linear, Slack, and Sentry, plus direct mentions.
Runs each session in a separate environment with scoped repository access and configurable compute.
Keeps transcripts, costs, outcomes, recaps, and pull-request references searchable in one place.
Exposes agent and review operations for scripted workflows outside the dashboard.
Process
Step 1
Install the Ellipsis GitHub app and grant access only to the repositories agents should use.
Step 2
Turn on the built-in organization-wide review or commit a YAML configuration for a specialized agent or review pipeline.
Step 3
Choose repositories, triggers, models, sandbox requirements, and per-session or rolling spend caps.
Step 4
Trigger work from connected services or the dashboard, then follow live activity and review the persistent session record.
Cost
Ellipsis has no per-seat charge or feature tiers. Managed SaaS passes through model-token costs, charges sandbox compute, and adds a 10% platform fee. Organizations receive $100 in one-time signup credit and personal accounts receive $10. Optional enterprise support starts at $5,000 per month.
Usage based
Agents run in isolated Ellipsis cloud sandboxes.
Usage based + AWS costs
Runs agent sandboxes and model calls inside your AWS VPC while Ellipsis provides the platform.
From $5,000/month
Optional support packages for onboarding, configuration, procurement, and deployment help.
Pricing checked . Check current pricing at the source ↗
Assessment
Compare
The right alternative depends on the specific output, workflow, controls and budget your project requires.
Coding
Choose Claude Code Review for Anthropic's dedicated multi-agent pull-request review workflow.
Explore Claude Code Review →Coding
Choose Cursor when the primary need is an AI-first desktop editor with interactive coding agents.
Explore Cursor →Coding
Choose Devin Desktop for a workspace centered on coordinating coding agents from Cognition.
Explore Devin Desktop →Questions
Ellipsis runs AI coding agents in cloud sandboxes and provides built-in, incremental pull-request review, triggers, budgets, permissions, APIs, and searchable session records.
No. Ellipsis lists zero per-seat fees and bills for model tokens, sandbox compute, and a 10% platform fee.
Yes. The customer-hosted option runs credentials, code, model calls, and sandboxes inside the customer's AWS VPC while retaining the full platform feature set.
No. Code review is a core workflow, but teams can define general cloud agents for scheduled work and events from GitHub, Linear, Slack, Sentry, the CLI, or the API.
New organizations receive $100 in one-time usage credit and personal accounts receive $10. Usage pauses when credit runs out unless billing is configured.
Bottom line
Ellipsis is a strong fit for engineering organizations that want code review and broader coding-agent automations under one governed, observable platform. Teams seeking only an editor assistant may prefer a simpler IDE product, while teams adopting Ellipsis should still require tests and human approval for consequential changes.
Visit Ellipsis.dev website ↗
With Postgres Sandbox, instantly spin up Postgres databases in your browser for easy data management and analysis.

Streamline AI workflows for data teams efficiently.

Appy Pie: Automate workflows & create applications.

Mimrr automates codebase documentation and analysis.

Get access to all our AI courses, hundreds of real-world AI use cases, live expert-led workshops, an exclusive network of AI early adopters, and more.
Get unlimited access to all of our current & upcoming industry-specific AI courses for the duration of your subscription.
To keep up with the rapid pace of AI, our team publishes AI implementation guides daily. Our library contains 300+ practical use cases to automate real-world work.
Join weekly, live, interactive sessions with industry leaders who are at the forefront of AI for hands-on implementation guidance and exclusive insights.
Network with an exclusive community of AI-first professionals who are working smarter with AI. Learn how early adopters are using AI in their work and businesses.