The Platform for Your Software Factory

Build your own coding agents for feature generation, background tasks, and code review. We'll handle the infrastructure, permissions, logging, and budgets.

Any agent, any model

Change one line to switch harness or model.

Move from Claude Code to Codex, or from Anthropic to OpenAI, without rebuilding your agent.

1
ellipsis:
2
kind: agent
3
name: triage-issues
4
session:
−
claude_code:
5
codex:
−
model: claude-opus-5-5
6
model: gpt-6-sol
7
prompt: Label new issues and find duplicates.
8
environment:
9
repositories:
10
- name: web-repo

An agent.yaml diff replacing Claude Code and an Anthropic model with Codex and an OpenAI model.

Build your own coding agent

Every part is yours to configure.

Set the repositories, setup hooks, compute, triggers, and budget for each agent in YAML.

1
ellipsis:
2
kind: agent
3
name: check-api-changes
4
trigger:
5
type: react
6
pull_request:
7
on: [pushed]
8
repositories: [api-repo]
9
session:
10
claude_code:
11
model: claude-opus-5-5
12
prompt: |
13
Check the changed API routes for
14
missing test coverage.
15
environment:
16
repositories:
17
- name: api-repo
18
hooks:
19
after_checkout: |
20
cd api-repo
21
pnpm install --frozen-lockfile
22
compute:
23
cpu: 4
24
memory: 8GB
25
budget:
26
session: 5
27
day: 50

An agent.yaml with its trigger, environment, hooks, compute, and budget highlighted.

Own every log

Download the raw output of every agent process.

Choose how long session data is kept, from zero hours to one year.

1
{
2
"kind": "claude_code",
3
"source": "claude_code",
4
"record_format": "claude_jsonl@1",
5
"record_type": "assistant",
6
"session_id": "session_2f8c1d",
7
"turn_id": "turn_9a41",
8
"feed_seq": 42,
9
"payload": {
10
"type": "assistant",
11
"message": {
12
"role": "assistant",
13
"model": "claude-fable-5-1",
14
"content": [
15
{ "type": "text", "text": "Running the pool test suite." },
16
{
17
"type": "tool_use",
18
"name": "Bash",
19
"input": { "command": "pytest -k pool" }
20
}
21
],
22
"stop_reason": "tool_use"
23
},
24
"uuid": "22222222-2222-4222-8222-222222222222"
25
},
26
"tools": ["Bash"],
27
"cost": 0.0142,
28
"created_at": "2026-09-10T14:00:00Z"
29
}

A raw Claude Code JSON record with a Download logs button.

Use Cases

Use the Ellipsis platform as a foundation for your own tools, workflows, and agent-powered applications.

From YAML to API

Define agents in YAML, deploy with a merge, and run them through API calls, schedules, or events.

Learn more about Agents
1
ellipsis:
2
name: dependency-updates
3
trigger:
4
type: cron
5
schedule: "0 9 * * 1"
6
session:
7
claude_code:
8
prompt: |
9
Update dependencies in web-repo.
10
Run tests and open a pull request.
11
environment:
12
repositories:
13
- name: web-repo
14
hooks:
15
after_checkout: |
16
cd web-repo
17
pnpm install --frozen-lockfile
18
compute:
19
cpu: 4
20
memory: 8GB
21
budget:
22
session: 5
FREE FOR INDIVIDUALS

Interactive Sessions

Cloud sessions feel like local but they give you an isolated cloud environment with your repositories, dependencies, and tools ready. No more git worktree conflicts.

Learn more about Interactive Sessions
your-org
New sessionK
Dashboard

Today

Yesterday

PS

Outbound webhook deliveries fail permanently on any non-2xx. Add retries with exponential backoff, max 5 attempts, and record each attempt.

Starting sandbox…
0s

Reply to the agent...

Send

Secure, Managed Infrastructure
that is very easy to use

Ellipsis is built with governance at scale in mind. Permissions are defined before a session starts. Every agent action is logged. You have full control over your data longevity.

More about security
SOC 2Type ICertified
SOC 2Type IIIn progress

Scoped credentials

Minted per session, scoped to the repos you allowed, revoked with the sandbox.

Zero source retention

Your code lives only in the session sandbox and is deleted with it.

Full audit trail

Every command, file change, and tool call an agent made, kept after the sandbox is gone.

Frequently asked questions