Deploy coding agents in the cloud

Deploy, manage, and observe your coding agents in the cloud. Each agent gets their own sandbox, so your code is secure and the agent trace is visible to the whole team.

Install on GitHub Documentation Talk to a human

Claude

Codex

Gemini

Works with the agents your team already uses

Attach Screenshot Agent

attach-screenshot.yaml@ main

10github:create_comment3.1K tok

9thinkingPush is blocked. Upload it through a PR comment instead.420 tok

8Bashgit push origin pr-7612 · branch is protectedBlocked

7thinkingAttach the screenshot to the PR and tag the author.360 tok

6browser:screenshotlanding-hero.png · 1440×9002.6K tok

5browser:openpreview-7612.ellipsis.dev900 tok

1m06sDuration$0.27Cost10.0KTokens/ $0.50 budget

Agents as Code

Define in YAML, deploy with git push

Prompt, model, trigger, tools, and spend cap live in one YAML file. Commit it to deploy, open a pull request to change it, revert to roll it back. Every agent is reviewed and versioned like the rest of your code.

beaconhq / agents

standup-automator.yaml

ellipsis:

name: Standup automator

description: Posts a daily standup digest to Slack

triggers:

- type: cron

schedule: "30 8 * * 1-5"

limits:

run: 2

claude:

model: claude-opus-4-8

system: |

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.

Organization-wide visibility

Define, govern, and observe every agent

Choose the model, the tools (and MCP servers), set permission boundaries, and enforce spend limits on every run.

agent — zshlive

Permissions

Decide what agents can do before they run

Set per-agent allow-lists for tools and MCP servers, and scope each agent to specific repos and branches. Then cap what it can spend per run, per day, and per month, so an agent never runs up a surprise bill.

Learn more →

Runslive

Flagged 1 risk on beacon-api #1841

Dropped column without backfill

$0.21

12.0K tok

just now1m30s

Posted daily standup to beaconhq #engineering

4 merged, 2 awaiting review

$0.05

3.3K tok

just now22s

Opened beacon-web #314

Implement CSV export

$0.42

31.2K tok

22s ago4m02s

Approved beacon-api #1839

Add rate limiting to /v1

$0.18

9.1K tok

1m ago48s

Reviewed beacon-web #1842

Fix connection leak on error path

$0.31

18.4K tok

3m ago1m12s

Observability

Observe and monitor fleetwide

One pane of glass for every agent your team runs: which are active, what they shipped, what they cost, and how much they have spent today, across every repo.

Learn more →

Steps · 152Show thinking

152Commit pushed28 tok

151Bashgit commit -m 'Release connection on error path'20 tok

150thinkingWrite a clear commit message

149assistantGreen. Committing the fix.14 tok

148Bashpytest -k pool · 142 passed24 tok

147Editapi/pool.ts · +12 −426 tok

146thinkingPatch the finally block and add a test

Tracing

See every step, from Thinking to Diff

See the reasoning behind every change, not just the change. Each run records the agent's thinking, the tools it called, the tests it ran, and the diff it shipped. No black boxes.

Learn more →

Agents

Explore the agent templates

Start from a working agent instead of a blank file. Copy the YAML into your repo, adjust the triggers and tools, and deploy it with a git push.

agents/ci-failure-triager.yaml

ellipsis:  version: v1  name: CI Failure Triager  description: Find the cause of failed CI runs and open a fix planenabled: truetriggers:  - type: react    events:      - event: pull_request_pushsandbox:  repositories:    - name: beacon-webtools:  - type: githublimits:  run: 0.75  day: 6.00  week: 30.00claude:  model: claude-haiku-4-5-20251001  system: |    You triage failing CI on pull requests.    Inspect the changed files, recent commits, and available check output.    Identify the most likely root cause and write a short fix plan with the    files that need attention. If the failure is flaky or infrastructure    related, say so and include the evidence.

Deploy coding agents in the cloud

Define in YAML, deploy with git push

Close your laptop!

Define, govern, and observe every agent

Decide what agents can do before they run

Observe and monitor fleetwide

See every step, from Thinking to Diff

Explore the agent templates

From the blog

The Future of Software Is the Agent

How CTOs Should Think About Agentic Workflows

Maintaining Documentation Without a Human

Deploy your first agent in minutes