# Rust CLI reference Generated from the CLI source in this checkout (package version **0.7.0**). Use `agentic --help` or `agentic --help` for your installed version. The Rust command-line interface is `agentic ...`. Use it from a terminal to start the gateway, launch Codex or Claude Code, attach a harness to an existing gateway, and validate your configuration. Both `cargo install agentic-server` and `pip install agentic-api` install `agentic`. The PyPI package also includes the separate [Python launcher](python-cli.md), invoked as `agentic-api ...` or `python -m agentic_api ...`. Its commands, flags, and defaults differ from the Rust CLI. See [Python installation and workflows](../guides/python-installation.md) for package installation. ## agentic ```text Agentic API — local agent gateway for Claude Code and Codex Usage: agentic Commands: run Start Agentic API and launch a coding harness harness Launch a coding harness against an already-running Agentic API gateway serve Start Agentic API without launching a harness validate Validate the local Agentic API session prerequisites help Print this message or the help of the given subcommand(s) Options: -h, --help Print help -V, --version Print version ``` ## agentic run ```text Start Agentic API and launch a coding harness Usage: agentic run Commands: codex Launch Codex with an isolated provider configuration claude Launch Claude Code with an isolated gateway environment help Print this message or the help of the given subcommand(s) Options: -h, --help Print help ``` ## agentic run codex ```text Launch Codex with an isolated provider configuration Usage: agentic run codex [OPTIONS] [-- ...] Arguments: [HARNESS_ARGS]... Arguments forwarded to the selected harness after `--` Options: --upstream Connect to an already-running OpenAI-compatible upstream (`http://` or `https://` base URL) --model Model to start with vLLM, or the model name to use with `--upstream`. When omitted alongside `--upstream`, the first model served by the upstream is used --llm-port vLLM port when starting a model [default: 8000] --gateway-host Gateway bind host [env: GATEWAY_HOST] [default: 127.0.0.1] --gateway-port Gateway bind port [env: GATEWAY_PORT] [default: 3000] --database-url `SQLite` or `PostgreSQL` storage URL [env: DATABASE_URL] [default: sqlite://./agentic_api.db] --max-request-body-size-bytes Maximum serialized request size in bytes accepted by the gateway. Left to the gateway's own configuration chain when omitted --api-key API key forwarded to the gateway and harness when configured [env: OPENAI_API_KEY] --skip-llm-ready-check Skip the upstream readiness probe --llm-ready-timeout-s Upstream readiness timeout in seconds [default: 600] --llm-ready-interval-s Upstream readiness poll interval in seconds [default: 2] --quiet Suppress lifecycle output --yolo Skip harness permission prompts and sandbox restrictions --no-color Disable ANSI color output -h, --help Print help ``` ## agentic run claude ```text Launch Claude Code with an isolated gateway environment Usage: agentic run claude [OPTIONS] [-- ...] Arguments: [HARNESS_ARGS]... Arguments forwarded to the selected harness after `--` Options: --upstream Connect to an already-running OpenAI-compatible upstream (`http://` or `https://` base URL) --model Model to start with vLLM, or the model name to use with `--upstream`. When omitted alongside `--upstream`, the first model served by the upstream is used --llm-port vLLM port when starting a model [default: 8000] --gateway-host Gateway bind host [env: GATEWAY_HOST] [default: 127.0.0.1] --gateway-port Gateway bind port [env: GATEWAY_PORT] [default: 3000] --database-url `SQLite` or `PostgreSQL` storage URL [env: DATABASE_URL] [default: sqlite://./agentic_api.db] --max-request-body-size-bytes Maximum serialized request size in bytes accepted by the gateway. Left to the gateway's own configuration chain when omitted --api-key API key forwarded to the gateway and harness when configured [env: OPENAI_API_KEY] --skip-llm-ready-check Skip the upstream readiness probe --llm-ready-timeout-s Upstream readiness timeout in seconds [default: 600] --llm-ready-interval-s Upstream readiness poll interval in seconds [default: 2] --quiet Suppress lifecycle output --yolo Skip harness permission prompts and sandbox restrictions --no-color Disable ANSI color output -h, --help Print help ``` ## agentic harness ```text Launch a coding harness against an already-running Agentic API gateway Usage: agentic harness Commands: codex Launch Codex with an isolated provider configuration claude Launch Claude Code with isolated provider and model configuration help Print this message or the help of the given subcommand(s) Options: -h, --help Print help ``` ## agentic harness codex ```text Launch Codex with an isolated provider configuration Usage: agentic harness codex [OPTIONS] --gateway-url --model [-- ...] Arguments: [HARNESS_ARGS]... Arguments forwarded to the selected harness after `--` Options: --gateway-url URL of an already-running Agentic API gateway --model Model ID served by the gateway --api-key API key forwarded to the gateway and harness when configured [env: AGENTIC_GATEWAY_API_KEY] --quiet Suppress lifecycle output --yolo Skip harness permission prompts and sandbox restrictions --no-color Disable ANSI color output -h, --help Print help ``` ## agentic harness claude ```text Launch Claude Code with isolated provider and model configuration Usage: agentic harness claude [OPTIONS] --gateway-url --model [-- ...] Arguments: [HARNESS_ARGS]... Arguments forwarded to the selected harness after `--` Options: --gateway-url URL of an already-running Agentic API gateway --model Model ID served by the gateway --api-key API key forwarded to the gateway and harness when configured [env: AGENTIC_GATEWAY_API_KEY] --quiet Suppress lifecycle output --yolo Skip harness permission prompts and sandbox restrictions --no-color Disable ANSI color output -h, --help Print help ``` ## agentic serve ```text Start Agentic API without launching a harness Usage: agentic serve [OPTIONS] Options: --upstream Connect to an already-running OpenAI-compatible upstream (`http://` or `https://` base URL) --model Model to start with vLLM, or the model name to use with `--upstream`. When omitted alongside `--upstream`, the first model served by the upstream is used --llm-port vLLM port when starting a model [default: 8000] --gateway-host Gateway bind host [env: GATEWAY_HOST] [default: 127.0.0.1] --gateway-port Gateway bind port [env: GATEWAY_PORT] [default: 3000] --database-url `SQLite` or `PostgreSQL` storage URL [env: DATABASE_URL] [default: sqlite://./agentic_api.db] --max-request-body-size-bytes Maximum serialized request size in bytes accepted by the gateway. Left to the gateway's own configuration chain when omitted --api-key API key forwarded to the gateway and harness when configured [env: OPENAI_API_KEY] --skip-llm-ready-check Skip the upstream readiness probe --llm-ready-timeout-s Upstream readiness timeout in seconds [default: 600] --llm-ready-interval-s Upstream readiness poll interval in seconds [default: 2] --quiet Suppress lifecycle output --yolo Skip harness permission prompts and sandbox restrictions --no-color Disable ANSI color output -h, --help Print help ``` ## agentic validate ```text Validate the local Agentic API session prerequisites Usage: agentic validate [OPTIONS] Options: --upstream Connect to an already-running OpenAI-compatible upstream (`http://` or `https://` base URL) --model Model to start with vLLM, or the model name to use with `--upstream`. When omitted alongside `--upstream`, the first model served by the upstream is used --llm-port vLLM port when starting a model [default: 8000] --gateway-host Gateway bind host [env: GATEWAY_HOST] [default: 127.0.0.1] --gateway-port Gateway bind port [env: GATEWAY_PORT] [default: 3000] --database-url `SQLite` or `PostgreSQL` storage URL [env: DATABASE_URL] [default: sqlite://./agentic_api.db] --max-request-body-size-bytes Maximum serialized request size in bytes accepted by the gateway. Left to the gateway's own configuration chain when omitted --api-key API key forwarded to the gateway and harness when configured [env: OPENAI_API_KEY] --skip-llm-ready-check Skip the upstream readiness probe --llm-ready-timeout-s Upstream readiness timeout in seconds [default: 600] --llm-ready-interval-s Upstream readiness poll interval in seconds [default: 2] --quiet Suppress lifecycle output --yolo Skip harness permission prompts and sandbox restrictions --no-color Disable ANSI color output --harness Also verify a harness binary without launching it [possible values: codex, claude] -h, --help Print help ```