You can close your laptop now

On the Ellipsis cloud, agents run in isolated sandboxes, so your code is secure and the whole team can see what they did. There is nothing to host and nothing to babysit.

01

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.

Cloud data flow

Events enter Ellipsis cloud, run in managed sandboxes, and return as GitHub code changes.

Developer Laptop

Spawn remote agent with @ellipsis

Slack

tagged in #engineering

GitHub

CI pipeline

Linear

Assigned to @ellipsis

Sentry

New error reported

Ellipsis cloud

Control plane

spawns runs, checks permissions, records status

Agent Sandboxes

ephemeral, scoped to single agent

SECURE

Agent Watchtower

streams every step, tracks budgets

GitHub

pushed

branch: ellipsis/fix-auth

commit: 8f3a1c9

pull request opened

Ellipsis backend writes the change back to GitHub.

Events enter the cloud, run in sandboxes, return as code changes

02

Agents that remember the whole thread

Every PR, issue, Slack thread, and Sentry alert is one durable conversation. Pushed commits get incremental review instead of amnesiac re-reviews, a reply wakes it in seconds with its working tree intact, and merge closes it. Idle time costs near zero.

api-repo #512 · Fix shift-trade raceIdle

pull_request_open · priya-shah opened #512

Reviewed the diff, flagged a double-booking window in trade_engine.py

2m 14s · $0.41

pull_request_push · priya-shah pushed 2 commits

Incremental review: the lock fix holds, one nit on the retry test

58s · $0.12

@ellipsis make the retry test cover shift boundaries · marcus-lee

Extended test_trade_retry with boundary cases, pushed 1 commit

1m 41s · $0.28

3 turns · one conversation per PRwakes on the next event

One durable conversation across the life of a PR

03

Agents start themselves

Run on a schedule, react to 15 event types across GitHub, Linear, Slack, and Sentry, or start on demand from the dashboard, API, or CLI. Work starts the moment the event fires, while context is fresh.

agents/on-call-helper.yamldeployed on git push
triggers:  - type: cron    schedule: "0 14 * * 1-5"  - type: react    events:      - event: pull_request_open      - event: push        branches: [main, release/*]      - event: sentry_issue_alert

Triggers declared in the agent's YAML

04

Mention it and it answers in the thread

Tag @ellipsis on GitHub, Slack, or Linear. It picks up the conversation it was mentioned in, takes the action you asked for, and answers in the same thread. It remembers the conversation, so 'now fix it' works.

api-repo #512 · comments

marcus-lee

@ellipsis use the staging database, not prod

👀 · conversation woken, same working tree

ellipsis[bot]

Switched the fixtures to the staging database and re-ran the suite: 12 passed. Pushed the change to this branch.

one message to steer, no kill-and-restart

A mention answered in the same thread

05

The reviewer is just another agent

A review agent is the same YAML as any other: it reacts on every head advance of a pull request, holds one conversation per PR, and reviews only the commits it has not seen. Any coding agent can write slop; yours is the one that catches it before merge.

agents/review-agent.yamllive on merge
ellipsis:  version: v1  name: Review agent  description: Review every PR, incrementally on pushtrigger:  type: react  pull_request:    on: [opened, pushed]session:  claude:    system:      file: .agents/prompts/review.md  environment:    repositories:      - name: api-repo  budget:    session: 2.00

A review agent defined in YAML

Every way an agent runs

Every trigger, steering surface, and lifecycle rule the runtime enforces, so nothing here is your team’s job to build.

Cron schedules

Standard five-field cron expressions, all in UTC. AWS EventBridge rate() and at() expressions pass through verbatim.

Pull request events

React to opened, pushed, merged, closed, review_submitted, and commented, filtered by repository, branch, labels, paths, drafts, and author.

Push and issue events

Fire on commits pushed to a branch or on GitHub issues opened, closed, or commented, with the same filter semantics.

Linear and Sentry

A new Linear issue or a Sentry issue or metric alert starts a session. A re-firing Sentry issue reaches agents at most once every 6 hours.

Slack

Mention agents answer app mentions, direct messages, and thread replies, and a react trigger can fire when a channel is created.

@ellipsis mentions

A built-in responder answers every mention with no config. A mention trigger replaces it with your own agent and scopes its platforms.

API and CLI starts

Any agent starts directly, with an appended prompt and a per-session config override, recorded as source api or cli in history.

One conversation per thing

A pull request, GitHub issue, Linear issue, or Slack thread is one durable conversation. Every follow-up on that surface continues it.

Context carries

Across turns the agent keeps the whole exchange and the working tree, so a follow-up continues the work instead of redoing it.

Warm for 10 minutes

After a turn the sandbox stays warm, then state is snapshotted and the sandbox destroyed. The next message resumes it intact in a fresh sandbox.

One budget per conversation

budget.session caps cumulative spend across every turn. A conversation at its cap records budget_hit; raise the budget to continue it.

Deploy by merging

The YAML on your default branch is the live agent. Pull requests preview config changes, and an invalid edit keeps the last good version running.

Frequently asked questions

Explore the platform