# CLI · Neural Inverse Build > It reads your code, runs commands and makes changes with the model of your choice, interactively or in CI. Source: https://neuralinverse.com/build/cli/ --- ![](/photos/bench.jpg) [Neural Inverse Build / CLI](https://neuralinverse.com/build/) # An AI coding agent for the terminal, under rules you control. It reads your code, runs commands and makes changes with the model of your choice, interactively or in CI. Part of Neural Inverse Build Command neuralinverse, alias ni Platforms macOS, Linux and Windows Install npm or a checksum-verified binary Models Gateway, provider key or local Overview The CLI works in your project folder. Every tool call is checked before it runs: first by your organisation's governance, then by the permission mode and rules you and your team set. It runs the same way in a terminal and in a pipeline. [What it does ↓](https://neuralinverse.com/#capabilities)[Workflow ↓](https://neuralinverse.com/#workflow)[Governance ↓](https://neuralinverse.com/#governance)[Permission modes ↓](https://neuralinverse.com/#modes)[Technical facts ↓](https://neuralinverse.com/#technical)[Get started ↓](https://neuralinverse.com/#get-started) What it does ## What the CLI does. A coding agent in the shell, with the controls a security team expects. - **An agent in your terminal:** Ask in plain language, attach files with @, run your own commands with ! and keep typing while it works. The conversation stays in your scrollback. - **Permission modes:** ask, auto-edit, read-only and full-auto, refined by allow and deny rules for commands, paths, hosts and MCP tools. Deny rules always win, in every mode. - **Sandbox:** Shell commands can run in an operating-system sandbox, bubblewrap on Linux and sandbox-exec on macOS, with the file system read-only outside the workspace and the network cut. - **Secrets kept out:** Processes the agent starts do not inherit variables that look like secrets, and secrets in tool output are redacted before it reaches the model. - **Sessions and checkpoints:** Sessions are saved and every prompt is a checkpoint you can return to. Project instructions live in AGENTS.md at the repository root and in subdirectories. - **Scripts and CI:** neuralinverse -p runs one prompt to completion and exits, with JSON output, turn, cost and time limits, and documented exit codes. A GitHub Action is included. - **Firmware and HDL environments:** Optional project environments add firmware tools for Cortex-M builds with Arm GCC, Arm Compiler 6 or IAR, and HDL tools for lint and simulation. - **MCP and checks:** Manage MCP servers, and check changes against your organisation's rules with the same findings as the Editor and CI. Key workflow ## From install to a reviewed change. 1. Install With npm, or as a standalone binary verified against the release checksums. 2. Connect a model Set a provider key, run neuralinverse setup, use a local model, or sign in with neuralinverse login. 3. Start in your project Run neuralinverse in the project folder and describe the task. 4. Approve or deny A call that needs you shows what it will do, with the diff for an edit. 5. Review and commit Inspect the diff, undo to any checkpoint, then commit or open a pull request. 6. Automate Run the same work non-interactively in scripts and CI. Who uses it ## Built for every role on the team. - **Terminal users:** Ask in plain language, approve each call that needs it, and undo to any checkpoint. - **Build engineers:** Run governed AI steps in CI, with cost and time limits and a work item for each run. - **Platform teams:** Ship a managed policy that fixes providers and models and requires sign-in. - **Security teams:** Deny secret files and risky commands, require the sandbox and forward the audit log to the SIEM. How it is governed ## Organisation governance comes first. Before the CLI's own rules and mode, every tool call is decided by the same decision point as the Editor and the Agents app. - **Deny wins, approval is a person:** A governance deny is refused. A call that needs approval asks you in every mode; no rule, hook or 'always allow' can pre-approve it. - **Managed policy:** A managed settings file locks every key it sets. Users can add deny rules but never remove the organisation's, and full-auto can be switched off. - **Remote signed policy:** The managed file can point to a policy served over HTTPS and signed with Ed25519. Unsigned or wrongly signed policies are rejected, and the CLI can refuse to start without one. - **Work items:** If policy requires a work item, an interactive session asks for it; headless runs are refused without one. - **No silent approvals in CI:** In a non-interactive run, anything that would ask is denied. A governance approval counts only if a signed approval of exactly that action is in the repository. - **Hardware needs a person:** Flashing always needs a person's approval, in every mode, and non-interactive runs cannot flash. Nothing is flashed if the image changed after approval. - **Audit log:** An append-only JSON Lines log of decisions, tool calls with a SHA-256 of their input, mode changes and MCP connections, ready for your log forwarder. File contents are not recorded. Permission modes ## Four modes. Rules refine each one. Switch with --mode, /mode or Alt+M. Deny rules apply in every mode. - **ask (default):** Reads in the workspace are allowed. File edits, commands and network ask, except recognisably read-only commands. - **auto-edit:** Edits in the workspace are allowed; commands and network ask. Git internals, shell start-up files and the CLI's own settings always ask. - **read-only:** Edits, commands and network are denied. The agent plans instead. - **full-auto:** Everything is allowed unless a deny rule or your organisation's governance says otherwise. Administrators can switch this mode off. Technical facts ## For your IT and security review. - **Install:** npm install -g @neuralinverse/cli with Node.js 22.19 or newer, or a standalone binary that needs no Node.js. The installer refuses any checksum mismatch and does not edit your shell profile. - **Platforms:** macOS on x64 and arm64; Linux on x64 and arm64, and musl-based distributions on x64; Windows on x64. - **Sign-in:** Optional unless your organisation requires it. Browser sign-in with PKCE, or a device code, used by itself over SSH and on Linux with no display. - **Models:** Anthropic, OpenAI, Google Gemini, AWS Bedrock, Claude on Vertex AI, Azure OpenAI and any OpenAI-compatible server. Ollama is detected automatically. Keys are kept in the operating system's keychain. - **Without internet access:** Host the release assets on an internal mirror, route model traffic through an internal gateway or a local model, and turn off the daily version check. Proxies and custom CA certificates are honoured. - **Telemetry:** Off by default, with no built-in destination. It can be sent only to an OpenTelemetry collector you configure, and tool inputs and outputs are never exported. - **Licence and status:** Proprietary, under your agreement with Neural Inverse; source review under NDA. Pre-release: interfaces and data formats may change between versions. Get started ## Install, sign in and read the documentation. - [Install the CLI](https://neuralinverse.com/docs/get-started/install/#the-cli) - [Sign in to your organisation](https://neuralinverse.com/docs/get-started/sign-in/) - [CLI documentation](https://neuralinverse.com/docs/cli/) - [CLI administration](https://neuralinverse.com/docs/cli/enterprise/) - [Models](https://neuralinverse.com/docs/build/models/) - [Policy, approvals and audit](https://neuralinverse.com/docs/build/governance/) Related [Editor → Hands-on development with AI you review line by line.](https://neuralinverse.com/build/editor/)[Agents → Delegate work to agents, run sessions in parallel and review their changes.](https://neuralinverse.com/build/agents/)[Neural Inverse Govern → Sign-in, approved models, policy and audit for every AI tool. Powered by Keystone.](https://neuralinverse.com/govern/) ![](/photos/team.jpg) ## Talk to our team. Neural Inverse is available by request. We work with your engineering, security and procurement teams from the first conversation. [Request access](https://neuralinverse.com/contact/?topic=access)[Contact us](https://neuralinverse.com/contact/)