Enterprise platform forCloud Coding Agents

Run your team's Claude and Codex sessions in the cloud with isolated sandboxes, scoped permissions, hard budget caps, spend attribution, audit logs, and full observability.

Get started with $100 credit
Schedule a demo
Claude logoClaudeCodex logoCodexGemini logoGemini
Works with the agents your team already uses
0+
engineering teams
0.0M
agent sessions
Ellipsis, #4 Product of the Day on Product Hunt
Mosaic logoTrack logoRoo logoTribe AI logoRingier logoAdaptive Security logoUpsales logoLorikeetConcord logoCentral logoCurbside SOS logoSymphonyAIMotion logoWego logoSuperscript logo
01The CLI

A fleet of cloud agents, managed like infrastructure

Each agent runs in its own sandbox with scoped credentials and a hard budget. Developers get parallelism, the platform team gets the audit trail.

Learn more
Graphic: Terminal streaming a fleet of parallel agent sessions

Run parallel sessions from your terminal

02Harnesses

You choose the harness, we handle the infrastructure

Ellipsis is the infrastructure under whichever agent wins: sandboxes, credentials, budgets, and logs stay the same while the harness and model are config fields.

Learn more
Graphic: Side-by-side claude/codex YAML files: same agent, one field changed

Swap the harness with one config field

03Agents as code

Agents are defined as code

An agent is a YAML file in your repo: the prompt, the model, the sandbox, the permissions, the budget. Like infrastructure-as-code, for your agents.

Learn more
Graphic: Agent YAML file revealing field by field, live on merge

Define the agent in YAML, live on merge

04Code review

Code review with your prompts and your models

Choose the models and prompts, add multiple reviewers, and gate what lands with a filter you write. Too noisy? Write a stricter prompt.

Learn more
Graphic: code_review.yaml with multiple reviewers and a gatekeeper filter

Add reviewers and gate what lands

05Sandboxes

Agents spawn in seconds, with your toolchain installed

Each agent spawns the full stack and runs the tests in its own sandbox, so ten agents on one repo never clobber each other.

Learn more
Graphic: Sandbox provisioning timeline: warm image, repos cloned, tests running

Warm images make repeat sessions instant

06Governance

Scoped credentials, hard budgets, full audit trail

Agents stop running on developers’ own credentials. Permissions are minted per session, spend is capped and attributed, and the transcript outlives the sandbox.

Learn more
Graphic: Governance panel: per-session token scopes, budget bar, audit trail

Permissions minted per session, spend attributed

07The API

Spawning agents is as simple as POST /v1/sessions

Put an LLM decision-maker anywhere in your SDLC with no infra to manage. Spawn a session from any workflow and get typed, structured output back.

Learn more
Graphic: POST /v1/sessions curl request and the 201 response body

One POST starts a session, typed output back

08Self-hosted

No data ever leaves your VPC

Self-host in your AWS account and nothing leaves your VPC. Model calls can route through your own gateway for compliance and logging.

Learn more
Graphic: Your-VPC diagram: platform, sandboxes, and model calls inside the customer account

The whole platform inside your AWS account