Ellipsis
Cloud platform for running Claude Code, Codex, and other AI coding agents at scale with spend controls, audit logs, and isolated sandboxes.
🔗 Visit Ellipsis
Description
Imagine a company wants dozens of AI coding assistants working at once — reviewing pull requests, fixing bugs, investigating issues — instead of each engineer running one assistant alone on their laptop. Ellipsis is the infrastructure that makes that possible: it hosts the sandboxes where the agents run, hands out temporary credentials so they can only touch what they need, tracks exactly how much each session costs, and keeps a full audit trail of what every agent did. It's a bit like managing a fleet of very capable interns — useful work gets done in parallel, but a manager is always watching the budget and the paper trail, so nothing runs unsupervised or out of control.
Technically, teams define agent behavior as config-as-code: a single YAML file per repository where a commit deploys the configuration, a pull request proposes a change, and a revert rolls it back. Agents can be triggered by cron schedules, GitHub events, Linear issues, Sentry alerts, Slack mentions, or direct REST/CLI calls, and dozens of sessions can run in parallel. Each session gets scoped credentials and runs in an isolated sandbox that is torn down afterward, with hierarchical spend caps enforced at the account, agent, session, and developer level over rolling windows. Every step is logged with its individual cost, transcript retention is configurable from 7 to 365 days, and no source code is retained once a session ends.
💬 Our review
The short version: Ellipsis doesn't make Claude Code or Codex smarter, it makes them safe and accountable to run at company scale — the pitch is governance and visibility, not raw agent capability.
Compared to running Claude Code or Codex directly on a laptop, Ellipsis is strictly more expensive and adds setup overhead, but it buys parallel sessions, scoped credentials, spend caps, and full audit logs that a solo local setup simply doesn't have — fine for one developer, but risky for a team running agents unsupervised against production repos. Compared to rolling your own runners on GitHub Actions, Ellipsis removes the burden of hosting and managing that infrastructure, which is real value at scale, but it's also more DIY-averse teams paying for convenience: self-hosted runners are cheaper per hour once you're set up. The honest catch is the pricing model — tokens billed at cost is fair, but the added 20% platform fee plus separate CPU and memory charges means costs can climb quickly with heavy parallel usage, and enterprise support tiers ($5,000-$15,000/mo) are a serious added expense on top. Worth it for organizations that need auditability and control over many concurrent agents; overkill for an individual developer or a small team just experimenting.
💰 Pricing
📊 Global score
🤖 AI-enriched data
Coût des tokens sans majoration + frais de plateforme de 20% + compute (CPU $0.142/vCPU-h, mémoire $0.024/GB-h), 100$ de crédit offert à l'inscription
Pros
Sandboxes isolés et détruits après chaque session
Contrôle des dépenses hiérarchique (compte, agent, session, développeur)
Journal d'audit complet avec coût détaillé par étape
Configuration as code en YAML, versionnable et réversible
Déclencheurs multiples (cron, GitHub, Linear, Sentry, Slack, API)
Cons
Frais de plateforme de 20% en plus du coût des tokens, qui s'ajoutent au compute
Support entreprise payant en supplément (5 000-15 000$/mois)
Coût qui peut grimper vite en usage parallèle intensif