Environment Variables

The 10xGraph API server and CLI read configuration from environment variables. This page lists every variable with its default and effect, grouped by area. Set server variables in a .env file referenced by 10xgraph.json or in the process environment. CLI variables control terminal output.

Setting server variables

Via .env file

In 10xgraph.json:

{
  "agent": "graph.react:app",
  "env": ".env"
}

In .env:

GOOGLE_API_KEY=your-key
JWT_SECRET_KEY=your-secret
MODE=production

At the process level

MODE=production 10xgraph api --no-reload

Application variables

The settings model allows extra variables, so unknown names in the environment are tolerated rather than rejected.

Security headers

Applied by the security-headers middleware when SECURITY_HEADERS_ENABLED is true.

CORS variables

Authentication variables

Both must be set when 10xgraph.json has "auth": "jwt"; the config load raises a ValueError otherwise and the server does not start. JWT support also needs the extra: pip install "10xgraph-api[jwt]".

Redis variables

REDIS_URL is optional everywhere. Two things use it:

• The ownership authorization cache (L2). The ownership and rbac backends resolve their Redis URL from the redis key in 10xgraph.json first, falling back to REDIS_URL. With neither set, or with the redis package not installed, the cache runs in-process only (L1) and the server logs a warning at startup. Nothing breaks; each worker just pays its own first lookup per thread.
• PgCheckpointer. It can use Redis as a hot cache layer in front of Postgres. This is a performance choice, not a requirement: PgCheckpointer runs without it.

The rate limiter does not read REDIS_URL. Configure its connection under rate_limit.redis.url in 10xgraph.json.

Snowflake ID variables

Read only by SnowFlakeIdGenerator, and only when it is constructed with no arguments.

See ID Generator for the constructor contract.

Observability

OpenTelemetry needs the extra: pip install "10xgraph-api[otel]", which also brings the FastAPI instrumentation and the OTLP exporter.

Logfire and LangSmith are configured through the observability block in 10xgraph.json; their secrets (LOGFIRE_TOKEN, LANGSMITH_API_KEY) come from the environment.

Error tracking and sampling

For Sentry integration, install: pip install "10xgraph-api[sentry]".

Media and multimodal

Document text extraction needs the extra: pip install "10xgraph-api[media]".

See Files and multimodal for how these fit together.

Request limits

MAX_REQUEST_SIZE is enforced by HTTP middleware and applies to requests that declare a Content-Length. It does not cover WebSocket frames (bounded separately at 1 MiB per frame on /v1/graph/live) or chunked uploads (bounded by MEDIA_MAX_SIZE_MB as the body is read).

API path variables

Server concurrency

Only Gunicorn reads this variable, for example when started as gunicorn -k uvicorn.workers.UvicornWorker tenxgraph_api.src.app.main:app. The development server (10xgraph api) does not use it.

LLM provider variables

Set these based on the provider you use on your Agent. They are read at client creation time.

LLM timeout

OpenAI (provider="openai")

Google Gemini (provider="google")

The Google provider supports two backends: the Gemini API (default) and Vertex AI. See Google integration.

Gemini API (Google AI Studio):

Vertex AI (enable with use_vertex_ai=True on the agent or GOOGLE_GENAI_USE_VERTEXAI=true):

Anthropic (provider="anthropic" or provider="anthropic_vertex" or provider="anthropic_bedrock")

For Vertex AI models, see Anthropic integration.

CLI variables

These variables control how the 10xgraph command-line interface renders output: animation, the full-screen frame, and Unicode symbols. A flag is on when the value is 1, true, yes, or on (case-insensitive). There is no TENXGRAPH_THEME variable; the CLI theme is fixed.

Each CLI variable has a deprecated AGENTFLOW_* equivalent that is used only when the TENXGRAPH_* name is not set. The AGENTFLOW_* names will be removed in 10xGraph 2.0.