Skip to content
Back to search

azmx

AZMX AI — The sovereign agent platform.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/azmxai--azmx/badge.svg)](/listings/azmxai--azmx)

HTML

<a href="/listings/azmxai--azmx"><img src="/api/listings/azmxai--azmx/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

# macOS — Homebrew (live now via our tap; in homebrew-cask review)
brew install --cask AzmxAI/azmx/azmx

# macOS / Linux — one-line installer (live)
curl -fsSL https://azmx.ai/install | sh

# Windows — winget (manifest submitted to microsoft/winget-pkgs; live after review)
winget install AzmxAI.AZMX

Or grab a signed installer for your platform from the **[latest release](https://github.com/AzmxAI/azmx/releases/latest)**:

| Platform | File | | --- | --- | | macOS (Apple Silicon) | `AZMX.AI_<version>_aarch64.dmg` | | macOS (Intel) | `AZMX.AI_<version>_x64.dmg` | | Linux | `AZMX.AI_<version>_amd64.AppImage`, `.deb`, or `.rpm` | | Windows | `AZMX.AI_<version>_x64_en-US.msi` or `*_x64-setup.exe` |

Detailed walkthrough per platform: **[SETUP.md](SETUP.md)**.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 219 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. <!-- TODO(hero-asset): replace this with the actual logo when assets/ ships. -->
  3. <img src="https://azmx.ai/assets/logo.png" width="96" height="96" alt="AZMX AI" />
  4. # AZMX AI
  5. ### The sovereign agent platform.
  6. [![Download latest](https://img.shields.io/github/v/release/AzmxAI/azmx?label=download&style=for-the-badge&color=171717)](https://github.com/AzmxAI/azmx/releases/latest)
  7. [![Website](https://img.shields.io/badge/website-azmx.ai-171717?style=for-the-badge)](https://azmx.ai)
  8. [![Discussions](https://img.shields.io/github/discussions/AzmxAI/azmx?style=for-the-badge&color=171717)](https://github.com/AzmxAI/azmx/discussions)
  9. [![License](https://img.shields.io/badge/license-EULA-blue)](LICENSE.md)
  10. [![Platform](https://img.shields.io/badge/platform-macOS%20%C2%B7%20Linux%20%C2%B7%20Windows-lightgrey)](#install)
  11. [![Sponsor](https://img.shields.io/github/sponsors/AzmxAI?label=sponsor)](https://github.com/sponsors/AzmxAI)
  12. </div>
  13. <!--
  14. TODO(demo-gif): record a 6–10 second screen capture of the agent doing something
  15. undeniable — e.g. "explain the last error", "/init" a fresh repo, or running a
  16. parallel sub-agent against a real diff. Save as assets/demo.gif (<=4 MB) and
  17. uncomment the line below. This is the single highest-leverage change in the
  18. whole repo for repo-visit → star conversion.
  19. -->
  20. <!-- <p align="center"><img src="assets/demo.gif" alt="AZMX AI in action" width="720" /></p> -->
  21. ---
  22. ## Install
  23. ```bash
  24. # macOS — Homebrew (live now via our tap; in homebrew-cask review)
  25. brew install --cask AzmxAI/azmx/azmx
  26. # macOS / Linux — one-line installer (live)
  27. curl -fsSL https://azmx.ai/install | sh
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 38 on GitHub
  28. # Windows — winget (manifest submitted to microsoft/winget-pkgs; live after review)
  29. winget install AzmxAI.AZMX
  30. ```
  31. Or grab a signed installer for your platform from the **[latest release](https://github.com/AzmxAI/azmx/releases/latest)**:
  32. | Platform | File |
  33. | --- | --- |
  34. | macOS (Apple Silicon) | `AZMX.AI_<version>_aarch64.dmg` |
  35. | macOS (Intel) | `AZMX.AI_<version>_x64.dmg` |
  36. | Linux | `AZMX.AI_<version>_amd64.AppImage`, `.deb`, or `.rpm` |
  37. | Windows | `AZMX.AI_<version>_x64_en-US.msi` or `*_x64-setup.exe` |
  38. Detailed walkthrough per platform: **[SETUP.md](SETUP.md)**.
  39. ---
  40. ## Why AZMX
  41. - **Your code stays on your machine.** AZMX never proxies AI requests through our servers. Your prompts go directly from your device to whichever provider you chose, or to a local model. We don't sit in the middle — and we can't.
  42. - **Free local AI without an API key.** One-click Ollama setup. Curated coding models (Qwen2.5-Coder, Granite Code, Llama, all Apache 2.0). Your code never leaves the device.
  43. - **Or BYOK any major provider.** OpenAI, Anthropic, Google, Groq, xAI, Cerebras, DeepSeek, NVIDIA NIM, Azure OpenAI, any OpenAI-compatible endpoint. Pick whichever, switch any time.
  44. - **Per-call agent approval.** The agent asks before it writes a file or runs a shell command. Configurable from Permissive to Paranoid (typed confirmation for destructive ops).
  45. - **Hash-chained, tamper-evident audit log.** Every tool call recorded locally. Export to your SIEM on the paid tiers.
  46. - **Real terminal, real editor, real file explorer.** xterm.js terminal, CodeMirror editor with vim mode + inline AI autocomplete, file tree with git badges. Not a marketing page that calls itself "the future of terminals."
  47. - **MCP-native.** 17-server curated catalog (GitHub, GitLab, Kubernetes, Postgres, SQLite, Redis, Slack, Drive, …). Add your own in one JSON file.
  48. - **~10&nbsp;MB installer. Native. No Electron.** Cold-start under a second. No telemetry, no account, no email-required-to-use.
  49. > The application source is proprietary. **This repository publishes release artifacts and user-facing docs** — installers, the auto-updater manifest, and the community contribution surfaces (skills, agents, MCP servers, snippets, translations). Source contributions land upstream and ship to you via the auto-updater.
  50. ---
  51. ## First-run in under 3 minutes
  52. 1. Open AZMX AI.
  53. 2. The first-run tour appears. On step **"Free local AI"**, click **Set up local AI**.
  54. 3. AZMX walks you through installing [Ollama](https://ollama.com) (~150 MB).
  55. 4. Pick **Qwen2.5-Coder 7B** (default — ~4.7 GB, Apache 2.0). The pull streams in-app.
  56. 5. When the bar turns green, the AI panel is live. Ask anything.
  57. Prefer BYOK? Skip step 2's button and use the BYOK step instead. Both paths land at a working composer.
  58. ---
  59. <a id="extend-azmx"></a>
  60. ## 🛠 Extend AZMX
  61. **Your contribution ships to every AZMX user worldwide on next release.** No CLA. You keep copyright. You grant a permissive license. The bundled distribution gets richer every month because of community work.
  62. Five surfaces, every one of them a single Markdown (or JSON) file:
  63. | Build a … | What it is | Where to start |
  64. |---|---|---|
  65. | 🤖 **Skill** | A discipline the agent loads on demand to act like a domain expert (e.g. "Postgres query review"). One Markdown file. | [`skills/`](skills/) → [`SKILL_AUTHORING.md`](guidelines/SKILL_AUTHORING.md) |
  66. | 🧑‍🚀 **Sub-agent** | A specialist the main agent delegates to, with bounded tools + predictable output (e.g. `test-writer`, `migration-planner`). | [`agents/`](agents/) → [`AGENT_AUTHORING.md`](guidelines/AGENT_AUTHORING.md) |
  67. | 🔌 **MCP connector** | A new tool the agent can call — bridge to your service, your data, your internal CLI. | [`mcp-servers/`](mcp-servers/) → [`MCP_AUTHORING.md`](guidelines/MCP_AUTHORING.md) |
  68. | ✨ **Snippet** | A pre-baked prompt template accessible via `#name` in the composer. | [`snippets/`](snippets/) → [`SNIPPET_AUTHORING.md`](guidelines/SNIPPET_AUTHORING.md) |
  69. | 🌍 **Translation** | The onboarding card in your language — 5 seeded, ~10 priority next. | [`TRANSLATIONS.md`](guidelines/TRANSLATIONS.md) |
  70. **Plus:** add a [recipe](docs/RECIPES.md) to the cookbook, fix a doc, or [showcase](guidelines/SHOWCASE.md) someone else's work.
  71. Every contributor gets credit in release notes. Featured contributors get a complimentary Pro license; repeat featured contributors get Teams. **[Read the principles →](guidelines/README.md)**
  72. ---
  73. ## 📦 Official npm packages
  74. Two MIT-licensed packages ship under the [`@azmxailabs`](https://www.npmjs.com/org/azmxailabs) npm scope. Use them to make your AI assistant aware of AZMX, or to build your own approval-gated agent with the same primitives AZMX uses internally.
  75. | Package | What it does | Install |
  76. |---|---|---|
  77. | **[`@azmxailabs/mcp`](packages/mcp)** [![npm](https://img.shields.io/npm/v/@azmxailabs/mcp.svg?label=npm&color=171717)](https://www.npmjs.com/package/@azmxailabs/mcp) | Official Model Context Protocol server. Drop it into Claude Desktop, Claude Code, Cursor, Windsurf, Continue, OpenAI Codex CLI, Cline, or any other MCP client — and the assistant gains grounded, authoritative knowledge about AZMX (pricing, BYOK providers, security posture, comparisons, install steps, latest release). | `npx -y @azmxailabs/mcp` |
  78. | **[`@azmxailabs/agent-sdk`](packages/agent-sdk)** [![npm](https://img.shields.io/npm/v/@azmxailabs/agent-sdk.svg?label=npm&color=171717)](https://www.npmjs.com/package/@azmxailabs/agent-sdk) | TypeScript SDK that ships the four primitives behind AZMX as standalone, dependency-free modules — **approval gate, deny-list, hash-chained audit log, BYOK provider router**. Build your own agent (CI script, CLI, desktop app, server) with the same security posture AZMX has, none of the UI. | `npm install @azmxailabs/agent-sdk` |
  79. **Step-by-step walkthrough for either package:** **[docs/DEVELOPER-GUIDE.md](docs/DEVELOPER-GUIDE.md)**
  80. **Full reference docs on the website:**
  81. - MCP server (per-client setup recipes, tool/resource/prompt inventory, examples): **[azmx.ai/docs#azmxai-mcp](https://azmx.ai/docs#azmxai-mcp)**
  82. - Agent SDK (concepts, full API, recipes, production checklist): **[azmx.ai/docs#agent-sdk](https://azmx.ai/docs#agent-sdk)**
  83. **Source:** [`packages/`](packages/) — pure TypeScript, Node ≥ 18, ESM, MIT.
  84. ---
  85. ## Documentation
  86. ### Get started
  87. | | |
  88. | --- | --- |
  89. | **[SETUP.md](SETUP.md)** | Install per platform · first-run setup |
  90. | **[MANUAL.md](MANUAL.md)** | Full feature reference — every panel, every shortcut |
  91. | **[FAQ.md](FAQ.md)** | Common questions on privacy, licensing, performance, models |
  92. | **[CHANGELOG.md](CHANGELOG.md)** | Release notes (per-version detail on the releases page) |
  93. ### Reference
  94. | | |
  95. | --- | --- |
  96. | **[docs/TIERS.md](docs/TIERS.md)** | What's in Free / Pro / Teams / Enterprise |
  97. | **[docs/MODELS.md](docs/MODELS.md)** | Supported AI providers · BYOK · local models |
  98. | **[docs/CONNECTORS.md](docs/CONNECTORS.md)** | The bundled MCP catalog · custom + workspace MCP |
  99. | **[docs/AGENTS.md](docs/AGENTS.md)** | What the agent can + can't do · approval gates · audit log |
  100. | **[docs/KEYBINDINGS.md](docs/KEYBINDINGS.md)** | Every shortcut, by category |
  101. | **[docs/RECIPES.md](docs/RECIPES.md)** | Workflow cookbook — copy + adapt |
  102. | **[docs/GLOSSARY.md](docs/GLOSSARY.md)** | Terms you'll see across the docs |
  103. | **[docs/ROADMAP.md](docs/ROADMAP.md)** | What we're working on |
  104. ### Policies + posture
  105. | | |
  106. | --- | --- |
  107. | **[SECURITY.md](SECURITY.md)** | Vulnerability reporting · what's protected |
  108. | **[PRIVACY.md](PRIVACY.md)** | What we collect (nothing, by default) · what lives where |
  109. | **[LICENSE.md](LICENSE.md)** | EULA pointer · third-party notices · trademarks |
  110. | **[CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)** | How we behave on this project |
  111. | **[CONTRIBUTING.md](CONTRIBUTING.md)** | How to engage with this repo |
  112. | **[docs/COMPLIANCE.md](docs/COMPLIANCE.md)** | SBOM · SOC 2 · DPA · FIPS · PIV/CAC |
  113. | **[docs/TELEMETRY.md](docs/TELEMETRY.md)** | What gets sent (nothing, by default) |
  114. | **[docs/AIRGAPPED.md](docs/AIRGAPPED.md)** | Run AZMX with zero outbound |
  115. ### Operate
  116. | | |
  117. | --- | --- |
  118. | **[docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md)** | Problem → fix, by surface |
  119. | **[docs/DATA_PORTABILITY.md](docs/DATA_PORTABILITY.md)** | Export · backup · move between machines |
  120. | **[docs/UNINSTALL.md](docs/UNINSTALL.md)** | Clean removal per platform |
  121. | **[docs/SUPPORT.md](docs/SUPPORT.md)** | Where to go for what |
  122. ### Build with us
  123. | | |
  124. | --- | --- |
  125. | **[skills/](skills/)** | Community skills the agent can load (`load_skill("…")`) |
  126. | **[agents/](agents/)** | Community sub-agents the main agent delegates to |
  127. | **[mcp-servers/](mcp-servers/)** | Community MCP connector manifests |
  128. | **[snippets/](snippets/)** | Community prompt snippets (`#name` in the composer) |
  129. | **[guidelines/](guidelines/)** | Authoring standards for every contribution kind |
  130. | **[guidelines/SHOWCASE.md](guidelines/SHOWCASE.md)** | Featured community contributions |
  131. | **[packages/](packages/)** | Official npm packages — `@azmxailabs/mcp` + `@azmxailabs/agent-sdk` |
  132. | **[docs/DEVELOPER-GUIDE.md](docs/DEVELOPER-GUIDE.md)** | Step-by-step developer walkthrough for both npm packages |
  133. ---
  134. ## Auto-updates
  135. AZMX checks for updates on launch. New versions land via the in-app updater — no need to revisit this page once you're installed. Signed via a public minisign key bundled with the app.
  136. ---
  137. ## ⭐ Star this repo
  138. If AZMX saves you time, a star helps two things:
  139. 1. **Other developers find it.** GitHub stars are the single biggest discovery signal for dev tools.
  140. 2. **We know what to keep building.** Every star tells us "this is the kind of tool worth maintaining."
  141. It costs you one click and supports a small team trying to build the AI terminal we wanted for ourselves. Thank you 🙏
  142. <p align="center">
  143. <a href="https://github.com/AzmxAI/azmx/stargazers"><img src="https://img.shields.io/github/stars/AzmxAI/azmx?style=social" alt="Star history"/></a>
  144. </p>
  145. ---
  146. ## Featured by
  147. <!--
  148. Press / podcast / video mentions land here as they happen. Add as logo links
  149. when real coverage drops — keep it sparse and credible (no "as seen on" walls
  150. with 50 unverified logos).
  151. -->
  152. *(This space will fill in as AZMX is covered. [Tell us if you wrote about AZMX →](https://github.com/AzmxAI/azmx/discussions/new?category=show-tell))*
  153. ---
  154. ## License
  155. ## Support
  156. - **Manual / FAQ**: see the links above.
  157. - **Bugs**: open an issue against this repository — include OS, AZMX version, and steps to reproduce.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.