Atlas

API keys

Copy this key now. It is not shown again after you dismiss it or reload.

Atlas provides OpenAI-compatible chat completions under one model id: atlas-mesh. Point your client at this host and create a key in Settings.

Chat completion

curl http://HOST:8300/v1/chat/completions \
  -H 'content-type: application/json' \
  -H 'authorization: Bearer am_YOUR_KEY' \
  -d '{
    "model": "atlas-mesh",
    "messages": [{"role": "user", "content": "Summarize this log line"}],
    "stream": true
  }'

Python

from openai import OpenAI

client = OpenAI(base_url="http://HOST:8300/v1", api_key="am_YOUR_KEY")
reply = client.chat.completions.create(
    model="atlas-mesh",
    messages=[{"role": "user", "content": "What failed in this trace?"}],
)
print(reply.choices[0].message.content)

Endpoints

`POST /v1/chat/completions`	Chat completions; streaming supported.
`GET /v1/models`	Public model metadata.
`GET /healthz`	Service health.

Access

Atlas is invite only. Sign in with an invited Shinra ID to chat and to create API keys. Every API request needs a key.

Tracing

Send x-trace-id; Atlas echoes it in the response.

Built for offensive security.

A custom model

Web chat

API

Sign in to start.

New chat

Settings