# Modal Reference (/deploy/templates/modal/reference)
The Modal app is `agentos`, served as one always-warm container. Configuration lives in the `agentos-secrets` Modal secret, and the default provisioned database is a Neon Postgres project named `agentos`. To supply your own database, configure host, user, password, database name, and optional port as described on the [deploy page](/deploy/templates/modal/deploy).
## Manage [#manage]
| Task | Command |
| -------------------- | ----------------------------------------------------------------------------------------------- |
| Deploy code changes | `./scripts/modal/redeploy.sh` |
| Sync env variables | `./scripts/modal/env-sync.sh` (defaults to `.env.production`; pass `.env` to sync that instead) |
| Tail logs | `modal app logs agentos --follow` |
| List apps and status | `modal app list` |
| Tear down | `./scripts/modal/down.sh` |
`down.sh --yes` skips only the wrapper script's confirmation. It does not pass `--yes` to `modal app stop`, so Modal may still prompt while stopping the app.
`modal_app.py` pins `min_containers=1` and `max_containers=1`. The always-warm container keeps the in-process scheduler and MCP streams alive, and the cap is the template’s scaling default. Postgres coordinates due-schedule claims across workers; multiple workers do not inherently double every scheduled run.
## Production auth [#production-auth]
Token-Based Authorization is on by default. Production startup requires `JWT_VERIFICATION_KEY` or a readable JWKS file at the container path in `JWT_JWKS_FILE`; otherwise the process exits.
Token-Based Auth gives you three things:
1. **Protected runtime access.** Protected API routes require a valid credential. Health, discovery, and API documentation remain public; Slack and MCP OAuth have their own authentication flows.
2. **Per-request identity.** Middleware validates the token and exposes its `user_id`, optional `session_id`, scopes, and claims to the request.
3. **Scope-based permissions.** Token scopes control access to AgentOS routes and resources.
The template already sets `AuthorizationConfig(user_isolation=True)`. Authenticated non-admin REST access is scoped to the principal; local `dev` mode disables scope enforcement and is open when no credentials are configured. This does not scope Platform Manager’s direct database tools to that REST identity. See [User Isolation](/agent-os/security/authorization/user-isolation) for the boundaries and admin exceptions.
To disable JWT authentication in a private deployment with another auth layer, set `authorization=False`, remove `JWT_VERIFICATION_KEY` and `JWT_JWKS_FILE` from the running service, and rebuild or redeploy the app as needed. Disabling scope enforcement alone does not remove JWT validation while those credentials remain configured. MCP OAuth remains enabled while `MCP_CONNECT_SECRET` is set.
## Customize [#customize]
Ask your coding agent to run `/create-agent`, or do it by hand. Create `agents/my_agent.py`:
```python
from agno.agent import Agent
from app.learning import shared_learning
from app.settings import default_model
from db import get_postgres_db
INSTRUCTIONS = """\
What the agent does, which tools it uses, the rules to follow when answering.
"""
my_agent = Agent(
id="my-agent",
name="My Agent",
user_id="anonymous-user", # Local fallback; authenticated runs supply identity.
model=default_model(),
db=get_postgres_db(),
instructions=INSTRUCTIONS,
learning=shared_learning,
add_datetime_to_context=True,
add_history_to_context=True,
num_history_runs=5,
)
```
The fallback user ID lets local anonymous calls use the shared learning machine; those calls share one profile. Authenticated run identity overrides this default.
Import it in `app/main.py` and update the `agents` argument in the existing `AgentOS` call. Keep its other arguments, including teams, workflows, knowledge, and registry:
```python
from agents.my_agent import my_agent
agent_os = AgentOS(
# Keep the other arguments from the existing call.
agents=[platform_builder, platform_manager, platform_engineer, my_agent],
)
```
Add its UI metadata beneath the existing `manifest:` key in `app/config.yaml`:
```yaml
my-agent:
description: "What the agent does."
quick_prompts:
- "First example prompt"
- "Second example prompt"
- "Third example prompt"
```
Local containers reload Python source changes. After editing `app/config.yaml`, run `docker compose restart agentos-api` to reload the manifest. For production, run `./scripts/modal/redeploy.sh`.
`app/settings.py` defines `default_model()`, used by every agent. Change it in one place:
```python
from agno.models.anthropic import Claude
def default_model():
return Claude(id="claude-sonnet-5")
```
Add `anthropic` to `pyproject.toml`, set the provider key in your env, and regenerate pins:
```bash
./scripts/generate_requirements.sh
```
Rebuild locally with `docker compose up -d --build`. For production:
```bash
./scripts/modal/env-sync.sh
```
`env-sync.sh` rewrites the secret with the new provider key and redeploys. The redeploy rebuilds the image, so the new dependency ships with it.
Agno ships 100+ toolkits. See [Toolkits](/tools/toolkits/overview).
```python
from agno.tools.slack import SlackTools
my_agent = Agent(
# Keep the agent’s existing configuration.
tools=[SlackTools()],
)
```
1. Edit `pyproject.toml`.
2. Regenerate pins: `./scripts/generate_requirements.sh` (add `upgrade` to refresh every pin).
3. Rebuild locally with `docker compose up -d --build`, or redeploy with `./scripts/modal/redeploy.sh`.
Set both variables in your env file:
```bash
SLACK_BOT_TOKEN=xoxb-...
SLACK_SIGNING_SECRET=...
```
Sync with `./scripts/modal/env-sync.sh`. The interface activates automatically and routes messages to the Agno team. Change `team=` in `app/main.py` to select another team, or replace it with `agent=my_agent` to route to an agent. See [Slack setup](/agent-os/interfaces/slack/setup).
The deployment check runs daily by default (`ENABLE_DEPLOY_CHECK=True`); it uses fixed checks without model calls. The `run-evals` schedule is always registered but starts disabled because it uses model calls. Enable it from the AgentOS UI. Both workflows remain runnable on demand. Startup reapplies `ENABLE_DEPLOY_CHECK` to the deployment-check schedule; the enabled state of an existing `run-evals` schedule is preserved.
## Format, validate, and run evals [#format-validate-and-run-evals]
Run evals against a dedicated local test platform with no concurrent writers. The starter’s cleanup hooks remove components and learning state created during a case; concurrent application writes can be removed too. The same prerequisite applies to scheduled evals. See [eval setup and isolation](/deploy/coding-agents#keep-behavior-stable-with-evals).
The host scripts require [uv](https://docs.astral.sh/uv/getting-started/installation/). The setup script creates a Python 3.14 venv:
```bash
./scripts/venv_setup.sh
source .venv/bin/activate
```
| Task | Command |
| ------------------- | ----------------------------- |
| Format | `./scripts/format.sh` |
| Lint and type-check | `./scripts/validate.sh` |
| Run smoke evals | `python -m evals --tag smoke` |
`./scripts/mcp_check.sh` runs inside the container, so it needs no venv.
## Environment variables [#environment-variables]
Initial provisioning forwards a selected set of bootstrap values. After deployment, apply custom `AGENTOS_MCP_SIGNING_KEY`, `ENABLE_DEPLOY_CHECK`, and `EVALS_*` settings with `./scripts/modal/env-sync.sh`. The table describes runtime support, not a promise that `up.sh` forwards every setting.
| Variable | Required | Default | Description |
| ------------------------------------------------------------- | ---------- | --------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `OPENAI_API_KEY` | Yes | - | Models and embeddings. |
| `RUNTIME_ENV` | No | `prd` | `dev` disables scope enforcement; configured JWT credentials still enable token validation. Compose sets it for local. Keep production on `prd` so scope enforcement remains enabled. |
| `JWT_VERIFICATION_KEY` | Production | - | Public key from os.agno.com. Quote the value so the multi-line PEM parses as one variable. |
| `JWT_JWKS_FILE` | Production | - | Path inside the Modal container to a JWKS file. The scripts put only this path into `agentos-secrets`. Put the file in the Docker build context or add an explicit Modal mount before deploying. |
| `MCP_CONNECT_SECRET` | No | generated by `up.sh` | OAuth consent secret (16+ chars) for connecting claude.ai and ChatGPT to `/mcp`. `up.sh` generates one on deploy and writes it to `.env.production`. |
| `AGENTOS_MCP_SIGNING_KEY` | No | generated | Optional high-entropy signing-key material (32+ chars) for OAuth tokens. Unset, a strong key is generated and persisted in the database. Rotating it invalidates outstanding tokens. |
| `AGENTOS_URL` | No | `http://127.0.0.1:8000` | Scheduler base URL. `up.sh` sets it to your modal.run URL. Scheduled jobs never fire if it stays at the default in production. When `MCP_CONNECT_SECRET` is set, OAuth metadata also derives its public origin from this URL. |
| `ENABLE_DEPLOY_CHECK` | No | `True` | Daily deployment-check cron. |
| `EVALS_TAG` | No | `smoke` | Eval tag the run-evals workflow runs. |
| `EVALS_CASE_TIMEOUT_SECONDS` | No | `90` | Fallback timeout for cases without an explicit timeout. |
| `EVALS_SUITE_TIMEOUT_SECONDS` | No | derived from selected cases | Sum of selected case timeouts plus 30 seconds per case, with a 60-second floor. A positive integer overrides this ceiling. |
| `PARALLEL_API_KEY` | No | - | WebSearch uses the Parallel SDK when set, keyless MCP otherwise. |
| `SLACK_BOT_TOKEN` | No | - | Set with the signing secret to enable Slack. |
| `SLACK_SIGNING_SECRET` | No | - | Set with the bot token to enable Slack. |
| `DB_HOST` / `DB_PORT` / `DB_USER` / `DB_PASS` / `DB_DATABASE` | No | matches compose | Postgres connection. `up.sh` fills these from your Neon project. |
| `DB_DRIVER` | No | `postgresql+psycopg` | SQLAlchemy driver. |
| `NEON_PROJECT_ID` | No | written by `up.sh` | Identifies the Neon project so `down.sh` can delete it. `env-sync.sh` skips NEON\_\* keys; they never sync to the app. |
| `NEON_ORG_ID` | No | - | Neon organization for unattended deploys. `neonctl projects create` prompts for an org and hangs non-interactive runs; set it (find yours with `neonctl orgs list`) so `up.sh` can pass `--org-id`. |
| `PGSSLMODE` | No | - | The deploy scripts set it to `require` in the Modal secret. Neon requires TLS, and libpq honors the variable, so the app needs no change. |
| `AGNO_DEBUG` | No | `False` | Verbose Agno logs. Compose sets it for dev. |
| `WAIT_FOR_DB` | No | `False` | If `True`, the entrypoint blocks on the database before starting. Compose sets it. |
## Troubleshooting [#troubleshooting]
Install the CLI with `pip install modal` or `uv tool install modal`, then run `modal token new`.
Install it with `brew install neonctl` or `npm i -g neonctl`, then run `neonctl auth`.
Neon projects are org-scoped, so `neonctl projects create` asks which organization to use and hangs non-interactive runs. Set `NEON_ORG_ID` in `.env.production` (find yours with `neonctl orgs list`) and re-run `./scripts/modal/up.sh`; the script passes it as `--org-id` so the deploy runs unattended.
Expected. At [os.agno.com](https://os.agno.com), choose **Connect OS** → **Live**, enter your modal.run URL, name it **Live AgentOS**, turn on **Token-Based Authorization (JWT)** on the connection panel, and connect. The UI generates the public key. If the OS is already connected, enable the setting under **Settings** → **OS & Security**. Paste the full PEM into the script prompt. To add a PEM later, set `JWT_VERIFICATION_KEY` and run `./scripts/modal/env-sync.sh`. To use JWKS, add the file to the Docker build context or configure a Modal mount, set `JWT_JWKS_FILE` to its container path, then deploy.
Non-dev mode requires JWT verification configuration. Configured JWT credentials also enable validation in dev mode. Set `JWT_VERIFICATION_KEY` and sync. For `JWT_JWKS_FILE`, first make the file available inside the Modal image or through a mount, then set its container path and sync. For a private deployment using another auth layer, follow the credential-removal steps under [Production auth](#production-auth).
Secrets are read at container start, so rewriting the secret alone changes nothing. `./scripts/modal/env-sync.sh` does both steps: it rewrites `agentos-secrets` and redeploys to roll the container.
`AGENTOS_URL` is still the localhost default. `up.sh` sets it to your modal.run URL automatically; for a custom domain or tunnel, set it by hand and run `./scripts/modal/env-sync.sh`.
`down.sh` deletes the Neon project but leaves `NEON_PROJECT_ID` and the `DB_*` values in your env file, so `up.sh` thinks a database still exists. Delete those lines and re-run `./scripts/modal/up.sh` to provision a fresh one.
The script only declares success once the app no longer shows as running in `modal app list` and the project is gone from `neonctl projects list`. Check both, then re-run it or finish by hand: `modal app stop agentos` and `neonctl projects delete `.