Deploy the Full Open-Source AI Stack Locally With Docker Compose in 5 Minutes

git clone https://github.com/future-agi/future-agi.git
cd future-agi

The OSS build uses futureagi/Dockerfile.oss (Python 3.11 base) and builds locally, so there’s nothing to pre-pull. First-build downloads about 6 GB of layers; subsequent boots reuse the cache.

Copy the template and rotate the four CHANGEME placeholders.

cp .env.example .env

Replace these four values in .env with generated secrets:

• SECRET_KEY (Django)
• PG_PASSWORD (Postgres)
• MINIO_ROOT_PASSWORD (object storage)
• AGENTCC_INTERNAL_API_KEY (gateway shared secret)

A one-liner to generate each:

python3 -c "import secrets; print(secrets.token_urlsafe(32))"

Drop your provider keys in the same file so the gateway can route requests:

OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...

If you want signup confirmations and password-reset emails to actually deliver, add Mailgun credentials too:

MAILGUN_API_KEY=key-...
MAILGUN_DOMAIN=mg.your-domain.com

If you don’t have Mailgun, skip this. You can still create a user and set a password via the Django shell in Step 4.

See Environment Variables for the full list of knobs.

docker compose up -d
docker compose ps --format "{{.Names}} {{.Status}}"

-d runs detached. The --format flag prints one line per service so you can scan health quickly without horizontal-scrolling the default table. The stack is ready when the backend logs Application startup complete:

docker compose logs -f backend

What you just started:

Three URLs are now live on your machine:

Open the frontend, sign up with any email (the local stack doesn’t enforce verification by default), and grab an API key from Settings -> API Keys. Set the keys in your shell so the next step can use them:

export FI_API_KEY="your-fi-api-key"
export FI_SECRET_KEY="your-fi-secret-key"

docker compose exec backend python manage.py shell -c "
from django.contrib.auth import get_user_model
u = get_user_model().objects.get(email='you@example.com')
u.set_password('your-new-password')
u.save()
"

Point the FutureAGI instrumentation SDK at your local backend with the FI_BASE_URL env var. Anything else is identical to the cloud setup.

pip install fi-instrumentation-otel traceai-openai openai

import os
from fi_instrumentation import register, FITracer
from fi_instrumentation.fi_types import ProjectType
from traceai_openai import OpenAIInstrumentor

os.environ["FI_BASE_URL"] = "http://localhost:8000"  # SDK sends spans to /tracer/v1/traces on this host

trace_provider = register(
    project_type=ProjectType.OBSERVE,
    project_name="local-stack-smoke-test",
)
OpenAIInstrumentor().instrument(tracer_provider=trace_provider)
tracer = FITracer(trace_provider.get_tracer("local-stack-smoke-test"))

from openai import OpenAI
client = OpenAI()

@tracer.agent(name="hello_agent")
def hello_agent(q: str) -> str:
    r = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": q}],
    )
    return r.choices[0].message.content

print(hello_agent("Say hi to my self-hosted Future AGI stack."))
trace_provider.force_flush()

Open Tracing -> local-stack-smoke-test in the dashboard. You should see one parent span (hello_agent) with the OpenAI call nested underneath. If the trace shows up, every layer of the stack is wired correctly: backend ingestion, ClickHouse via PeerDB, frontend rendering, gateway routing.