Content
<div align="center">
<img src="docs/assets/amigo-walk.svg" alt="Amigo, the AgenticOS pet, walking" width="288">
<h1>AgenticOS</h1>
<p>
<b>Put AI agents to work on your team's tasks.</b><br>
Build agents in your browser, connect documents and tools, and run them on infrastructure you control.
</p>
<p>
<a href="#-quick-start">Quick start</a> ·
<a href="#what-it-looks-like">Screens</a> ·
<a href="https://vstorm-co.github.io/agenticos/presentation/">Presentation</a> ·
<a href="docs/index.md">Docs</a> ·
<a href="#the-best-agentic-os-you-can-run-yourself">Why an OS</a> ·
<a href="#compared-with-the-alternatives">Comparison</a>
</p>
<p>
<a href="https://github.com/vstorm-co/agenticos/actions/workflows/ci.yml"><img src="https://github.com/vstorm-co/agenticos/actions/workflows/ci.yml/badge.svg?branch=main" alt="CI"></a>
<a href="https://github.com/vstorm-co/agenticos/releases"><img src="https://img.shields.io/github/v/release/vstorm-co/agenticos?label=release&color=blue" alt="Release"></a>
<a href="docs/testing.md"><img src="https://img.shields.io/badge/platform%20layer-100%25-brightgreen" alt="Coverage"></a>
<a href="LICENSE"><img src="https://img.shields.io/badge/licence-Apache--2.0-blue" alt="Licence"></a>
<a href="https://ai.pydantic.dev"><img src="https://img.shields.io/badge/Powered%20by-Pydantic%20AI-E92063?logo=pydantic&logoColor=white" alt="Pydantic AI"></a>
<a href="https://github.com/vstorm-co/agenticos/stargazers"><img src="https://img.shields.io/github/stars/vstorm-co/agenticos?style=flat&logo=github&color=e3b341" alt="Stars"></a>
</p>
<p>
<b>English</b> ·
<a href="README.pl.md">Polski</a> ·
<a href="README.de.md">Deutsch</a> ·
<a href="README.es.md">Español</a>
</p>
</div>
---
A company ends up with agents in five places and cannot answer four questions:
**what do we run, what did it cost, what did it touch, and who said it could.**
AgenticOS is one place to build them and one set of books for all of them.
**The harness, as a product**: skills, context files — `AGENTS.md` as a page —
MCP at registry scale, automations on a schedule or a trigger, and a budget that
stops a run *before* the model call.
Below: a spreadsheet dropped into the chat, one sentence asking for charts. The
agent writes the code, runs it in a locked box, and answers.
<div align="center">
<video src="https://github.com/user-attachments/assets/9a8e0f44-781c-4f93-990d-b5b7094cc8fc" controls muted loop playsinline width="100%">
<img src="docs/assets/screens/chat-live-demo.webp" alt="Chat: a CSV becomes Python in a sandbox, then charts" width="100%">
</video>
</div>
**[Build your first document agent](docs/howto/first-document-agent.md)** · [Choose a task](docs/use-cases.md) · [Compare platforms](docs/about/comparison.md) · [Deploy and operate](docs/rollout.md) · [Get help](docs/help.md)
Start with a handbook answer you can check. Then try a request draft or a CSV chart, keeping the source and actual output together.
Your team owns operation. Models, parsing, embeddings, tools and tracing can use external services depending on configuration.
And the same console on the desktop, with company: the optional
[desktop app](#on-the-desktop-if-you-like), its pet, and a shortcut that screenshots
straight into a new chat.
<div align="center">
<video src="https://github.com/user-attachments/assets/b82867ae-3543-406e-a552-e3a8b61f1d10" controls muted loop playsinline width="100%">
<img src="docs/assets/desktop_no_more_caramba_pet.png" alt="Amigo, the desktop pet, in a sombrero, saying: No more caramba." width="270">
</video>
</div>
<div align="center">
<sub>
Not a reader? <a href="https://vstorm-co.github.io/agenticos/presentation/"><b>The whole thing in twenty slides</b></a> — what the problem is, what a spec holds, where it answers, and what it refuses.
</sub>
</div>
## ⚡ Quick start
One command, and Docker is all it needs. It downloads one compose file, pulls the
published images, asks four questions, and hands back a console with a working
agent in it. Your team owns operation. Models, parsing, embeddings, tools and tracing can use external services depending on configuration.
```bash
curl -fsSL https://raw.githubusercontent.com/vstorm-co/agenticos/main/scripts/quickstart.sh | bash
```
<details>
<summary><b>macOS</b></summary>
Docker Desktop or [OrbStack](https://orbstack.dev). Nothing else.
</details>
<details>
<summary><b>Linux</b></summary>
```bash
curl -fsSL https://get.docker.com | sh
sudo apt install docker-compose-plugin
```
</details>
<details>
<summary><b>Windows</b></summary>
Through WSL2. In an administrator PowerShell:
```powershell
wsl --install
```
Then Docker Desktop with WSL2 integration on, and run the installer inside the
Ubuntu shell it gives you.
</details>
### What it asks
| | |
|---|---|
| **Which model** | OpenAI, Anthropic, Google, OpenRouter — or *decide later*, which creates everything and lets you paste a key in the console |
| **Your key** | Typed hidden, stored encrypted in your own database, never printed back |
| **Your login and organization name** | Defaults are fine for a look around |
| **One switch** | Mirror the public MCP registry so all 5,802 tool servers are searchable by name |
Add `--check` to only find out what is missing, `--dry-run` to see every command
it would run without running one, or drive it unattended:
```bash
curl -fsSL https://raw.githubusercontent.com/vstorm-co/agenticos/main/scripts/quickstart.sh | bash -s -- \
--yes --provider anthropic --api-key sk-ant-... --org "Acme"
```
### Or type the three commands yourself
The installer is a wrapper around these, and there is no step it takes that you
cannot take by hand:
```bash
mkdir agenticos && cd agenticos
curl -fsSLO https://raw.githubusercontent.com/vstorm-co/agenticos/main/docker-compose.yml
docker compose up -d # postgres (pgvector), redis, api, prefect, console
docker compose exec -T -e BOOTSTRAP_API_KEY=sk-... app \
agenticos cmd bootstrap # an org, an owner, a key, a model, a published agent
open http://localhost:3000 # sign in as admin@example.com / admin123
```
The images are `ghcr.io/vstorm-co/agenticos-backend` and `agenticos-frontend`,
published for amd64 and arm64 by every release; `AGENTICOS_VERSION=x.y.z` in a
`.env` beside the file pins one. There is no `.env` to write first: every
compose variable has a default. To change the code, `git clone` and `make dev`
instead - a clone builds the same images from the tree.
If something does not come up, `docker compose exec app agenticos cmd doctor`
answers the only question that matters — can this deployment actually run an
agent — and [docs/install.md](docs/install.md) has the rest.
## What you get
- 🧰 **The harness, as configuration.** Retrieval over your documents, a real browser,
Python in a sandbox with files and a shell, charts, images, delegation —
switched on per agent, not wired into code.
- 📄 **Context files.** `AGENTS.md` and `CLAUDE.md` as a page: standing
instructions written once, attached to every agent that needs them.
- 🎓 **Skills.** A procedure written once in plain language, loaded when the
agent decides it is relevant. Edit it; live on the next answer, no release.
- 🔌 **MCP, at registry scale.** **5,802 servers** in the catalogue, searchable
by name — 99 of them checked by hand with their OAuth wired. Or a compatible endpoint.
- 📚 **Documents read properly.** Pick the PDF reader per collection, or for one
file: PyMuPDF built in, LlamaParse where the tables carry the meaning,
self-hosted LiteParse OCR for scans. Plus how it is split, and OCR language.
- ⏰ **Automations.** Schedules and event triggers — the 07:00 triage, the Monday
summary. Same limits and same record as anything a person asked for.
- 📡 **One runner, eight surfaces.** Web chat, a hosted page, a widget, the HTTP
API, a raw WebSocket, Slack, Telegram, Mattermost. Published once.
- 🖥️ **A browser is all it needs; a desktop app if you want one.** The console is
a web app. The [desktop app](docs/desktop.md) is the same console in a window of
its own - plus a pet on the desktop and a shortcut that screenshots straight into
a new chat. An add-on, never a requirement.
- 🛡️ Configurable human approval for supported tools, recorded spend checks before model requests, an audit trail and tenant-scoped access.
- 📊 **A dashboard each person arranges.** 35 cards — runs, spend, service
health, answer quality, sandbox capacity — each gated on what that reader may
see. A finance lead and an engineer keep different ones on one deployment.
**Code defines, configuration composes.** A business team assembles agents in a
browser and never opens Python; engineers extend what there is to assemble, and
configuration can only ever reach what code registered. The ceiling is the
registry, not a config file — and it is Apache-2.0, on your hardware.
## What it looks like
### Inside one agent
An agent is a **spec**: instructions, a model, the capabilities it may reach,
the knowledge bound to it, a budget, and where it answers. Nothing ships until
**Publish**, and every publish is a version.
<img src="docs/assets/screens/dark/builder-build.webp" alt="Defining an agent: instructions, model, and the version that is live" width="100%">
<table>
<tr>
<td width="50%">
**Toolbox** — What the agent may do, as switches — your documents, a browser, Python, charts, delegation. Each one can require a person's approval first. This is the **AI harness**, assembled in a form.
<img alt="Toolbox" src="docs/assets/screens/dark/builder-toolbox.webp" width="100%">
</td>
<td width="50%">
**Visual map** — The agent as a graph: what reaches it, what it reaches for. A dashed box is something nobody attached.
<img alt="Visual map" src="docs/assets/screens/dark/builder-visual-map.webp" width="100%">
</td>
</tr>
<tr>
<td width="50%">
**Limits** — A monthly cap per agent, checked *before* each model call rather than added up after — plus a step limit, for the loop that is cheap and never stops.
<img alt="Limits" src="docs/assets/screens/dark/builder-limits.webp" width="100%">
</td>
<td width="50%">
**History** — Every version it has had, still readable. Rolling back is a click.
<img alt="History" src="docs/assets/screens/dark/builder-history.webp" width="100%">
</td>
</tr>
</table>
<sub>These four are dark only — the light half has not been captured.</sub>
### The first screen
**Dashboard** — 35 cards, laid out by whoever is reading: runs, spend, service
health, answer quality, sync freshness, sandbox capacity. Each one gated on what
that person is allowed to see, so a finance lead and an engineer keep different
dashboards on the same deployment.
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/dashboard.webp">
<img alt="The dashboard: 35 arrangeable cards" src="docs/assets/screens/light/dashboard.webp" width="100%">
</picture>
### Running forty of them
<table>
<tr>
<td width="50%">
**Agents** — Every agent you run, with the version that is live and who may use it.
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/agents.webp">
<img alt="Agents" src="docs/assets/screens/light/agents.webp" width="100%">
</picture>
</td>
<td width="50%">
**Templates** — Start from one built for your industry; you get a draft to adjust and publish.
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/agents-templates-dialog.webp">
<img alt="Templates" src="docs/assets/screens/light/agents-templates-dialog.webp" width="100%">
</picture>
</td>
</tr>
<tr>
<td width="50%">
**One answer, opened up** — Every answer recorded: the question, what it looked at, every tool call, the duration, the cost to a fraction of a cent.
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/activity-run-detail.webp">
<img alt="One answer, opened up" src="docs/assets/screens/light/activity-run-detail.webp" width="100%">
</picture>
</td>
<td width="50%">
**How your documents are read** — Three PDF readers — PyMuPDF, LiteParse, LlamaParse — plus chunking and OCR. Per collection, overridable on the next file. A scanned price list and a contract do not want the same one.
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/knowledge-base-upload-parsing-dialog.webp">
<img alt="How your documents are read" src="docs/assets/screens/light/knowledge-base-upload-parsing-dialog.webp" width="100%">
</picture>
</td>
</tr>
<tr>
<td width="50%">
**Context** — Standing facts — product names, policy, house tone — in one place instead of forty prompts.
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/context.webp">
<img alt="Context" src="docs/assets/screens/light/context.webp" width="100%">
</picture>
</td>
<td width="50%">
**It asks before it acts** — Anything that sends, files or refunds waits for a person, with the intended action written out. Decided exactly once.
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/activity-approvals.webp">
<img alt="It asks before it acts" src="docs/assets/screens/light/activity-approvals.webp" width="100%">
</picture>
</td>
</tr>
<tr>
<td width="50%">
**What it costs** — Recorded spend is checked before model requests. A request already in progress or concurrent runs can exceed the cap. See [budget limits](docs/governance.md#budgets).
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/activity-spend.webp">
<img alt="What it costs" src="docs/assets/screens/light/activity-spend.webp" width="100%">
</picture>
</td>
<td width="50%">
**Keys and credentials** — Keys are encrypted at rest and scoped by owner. Ordinary console/API responses do not return their plaintext. The deployment operator remains part of the trust boundary.
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/vault.webp">
<img alt="Keys and credentials" src="docs/assets/screens/light/vault.webp" width="100%">
</picture>
</td>
</tr>
<tr>
<td width="50%">
**The tools you already pay for** — Connect compatible MCP servers using supported transports, credentials and permitted destinations. See [MCP setup](docs/mcp.md).
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/mcp-servers.webp">
<img alt="The tools you already pay for" src="docs/assets/screens/light/mcp-servers.webp" width="100%">
</picture>
</td>
<td width="50%">
**Where people meet it** — Slack, Telegram, Mattermost, a website widget, your own software over the API. Published once; same limits everywhere.
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/screens/dark/channels.webp">
<img alt="Where people meet it" src="docs/assets/screens/light/channels.webp" width="100%">
</picture>
</td>
</tr>
</table>
<sub>Screenshots follow your GitHub theme. <a href="docs/screens.md">All 35 screens</a>.</sub>
## The best agentic OS you can run yourself
That is a claim, and the only honest way to make one is to hand over the criteria
and let you count. An operating system does seven things. Each row below is a
mechanism you can read in the source, not a promise.
| What an operating system does | What AgenticOS does |
|---|---|
| **Runs and isolates processes** | Runs agents, stops one at its budget, isolates tenants in the schema rather than in service code, and keeps every run with what it cost |
| **Enforces resource limits** - quota, cgroups | Monthly budgets per agent, checked *before* each model request rather than tallied afterwards. A run that fails still records what it spent |
| **Controls access** - users, permissions, `sudo` | A [permission catalog](docs/permissions.md) in code, roles composed from it, per-resource grants that widen and never narrow. `approval: required` is the `sudo`: a tool that acts on the outside world waits for a person |
| **Reaches hardware through drivers** | One interface to [27 model providers](docs/models.md) and to [compatible MCP servers](docs/mcp.md). Change a model profile and every agent using it moves, without one of them being republished |
| **Keeps a filesystem** | [Collections, skills and attached context](docs/file-processing.md) in your own Postgres, with embeddings keyed per organization |
| **Gives many interfaces one shell** | One runner behind web chat, the HTTP API, Slack, Telegram, a widget, a hosted page and a schedule. Same budget, same approval gate, same audit trail |
| **Writes an audit log** - syslog, auditd | Who ran what, when, what it cost and who approved it. Written even when the run failed |
Apply the same seven to anything else in the category. That is the test we would
like to be judged on, and
[When to use something else](docs/about/comparison.md) is where we run it against
the alternatives - including the rows where the honest answer here is "not yet".
**Now apply the same seven to anything else in the category** — including the
ones with a thousand times our stars. None of them explains why it is an
operating system, because most of them are a workspace with the letters on the
box. That is the whole claim: not that we have the most users, but that we are
the only one that states the criteria and then meets them in code you can read.
Where the honest answer here is still "not yet", it is a row in the comparison
below and a line on the [roadmap](docs/ROADMAP.md).
[When to use something else](docs/about/comparison.md) is the long version,
including where this one loses, and
[what makes something an operating system for agents](docs/about/index.md) is the
criteria on their own — take them and score anybody, us included.
## What an agent can do
Switched on per agent, in the Builder. Each carries its own settings, its own
permission scope and — where it acts on the outside world — its own approval gate.
| | |
|---|---|
| **Answer from your documents** | Retrieval over collections in your own Postgres, plus [skills](docs/skills.md) it loads on demand and [context files](docs/context.md) bound across agents |
| **Go and find out** | Web search, fetch one page properly, or drive a **real browser** through a site that needs clicking |
| **Do the work** | Run Python, keep a [sandbox](docs/sandbox.md) with files and a shell, draw charts, generate images |
| **Handle what is too big for one answer** | Delegate to subagents, keep a task list, think longer, compact a long conversation |
| **Stay inside the lines** | Guardrails that redact or block, per-tool output caps, and the clock |
| **Anything else** | [Compatible MCP servers](docs/mcp.md) - 5,802 in the catalogue, 99 of them checked with their OAuth flows wired, and no connector to write |
## Where it answers
Publish once. The same runner serves all of these, so an answer does not depend
on where the question came from.
| | |
|---|---|
| **Web chat** | In the console, with attachments and slash commands |
| **The desktop app** | The same console in a window of its own, with a pet and a screenshot shortcut - an [optional shell](docs/desktop.md), not a second product |
| **A hosted page** | `/e/{key}` - send somebody a link, no account needed |
| **An embeddable widget** | On your own site, with variables from the address bar |
| **The HTTP API** | [One POST and you have an answer](docs/api.md) |
| **A raw WebSocket** | Stream tokens into a frontend you built yourself |
| **Slack, Telegram, Mattermost** | Where an `@mention` runs as **the person who sent it**, not as the bot |
| **Schedules and triggers** | A clock, a webhook, or a mailbox we poll - [routines](docs/triggers.md) |
## On the desktop, if you like
Everything above runs in a browser, and that is how most people use it. For those
who want it on the dock there is a [desktop app](docs/desktop.md): a thin shell
around the same console - same sign-in, same permissions, nothing bundled - with
two things a browser tab cannot do. A pet that lives on the desktop while you work,
and a global shortcut (`⌘⇧A`) that takes a screenshot of any region and opens a new
chat with it attached.
<div align="center">
<img src="docs/assets/desktop_no_more_caramba_pet.png" alt="Amigo, the desktop pet, in a sombrero, saying: No more caramba." width="270">
<sub>Amigo, one of five pets. Drag it, click it, stroke it; right-click for its menu. <b>No more caramba in your AI.</b></sub>
</div>
## Compared with the alternatives
Choose by the task and by who operates it. Each guide cites the vendor's own pages, shows where AgenticOS goes further, and names what it does not do yet.
- **Assistant apps:** [Claude](docs/about/claude-apps.md) · [ChatGPT](docs/about/chatgpt.md). Seats for employees, or agents your organization owns on any model.
- **Cloud-suite builders:** [Copilot Studio](docs/about/copilot-studio.md) · [Gemini Enterprise](docs/about/gemini-enterprise.md). A vendor's cloud and meter, or your infrastructure and your provider's prices.
- **Self-hosted builders:** [Dify](docs/about/dify.md) · [n8n](docs/about/n8n.md). Licence conditions and enterprise tiers, or Apache-2.0 with governance included.
- **Teammate service:** [Viktor](docs/about/viktor.md). One shared AI employee, or many agents with their own access and budgets.
- **Delivered platform:** [Wonderful](docs/about/wonderful.md). A platform a vendor delivers, or one you own from day one.
- **Coding agents:** [Claude Code](docs/about/claude-code.md) · [Codex](docs/about/codex.md) · [OpenCode](docs/about/opencode.md). Built for developers; AgenticOS is for everyone else, and they help extend it.
[All comparisons, and the gaps](docs/about/comparison.md).
## Why it exists
Most agent frameworks give you a library. You write Python, you deploy it, and
every change to an agent's behaviour is a pull request, a review and a release.
That is the right shape for a product feature and the wrong shape for the forty
small agents a company actually wants — because the person who knows what the
agent should say is not the person with commit access.
AgenticOS moves the agent out of the code and puts governance around it instead.
[Secrets](docs/secrets.md) are sealed per organization: a key copied from one
tenant's database row cannot be decrypted for another, and no API response ever
returns one.
## Docs
| | |
|---|---|
| [Install](docs/install.md) · [Your first agent](docs/first-agent.md) | From nothing to an agent that answers |
| [Concepts](docs/concepts.md) | Spec, version, exposure, trigger, run — the five nouns |
| [Permissions](docs/permissions.md) · [Governance](docs/governance.md) | Who may do what; budgets, approvals, audit |
| [Capabilities](docs/reference/capabilities.md) · [MCP](docs/mcp.md) | What an agent can do, and how to add a tool |
| [Models](docs/models.md) · [Secrets](docs/secrets.md) | Providers, profiles, cost; the vault |
| [Knowledge](docs/file-processing.md) · [Skills](docs/skills.md) | Parsers, chunking, OCR; written know-how |
| [Channels](docs/channels.md) · [API](docs/api.md) | Slack, Telegram, widget, WebSocket, HTTP |
| [Desktop app](docs/desktop.md) | The optional shell: the console in a window, the pet, the screenshot shortcut |
| [Architecture](docs/architecture.md) · [Testing](docs/testing.md) | How it is built, and how it is verified |
Built with MkDocs: `make docs` serves them on :8001. Stack, in one line: FastAPI
+ Pydantic v2, PostgreSQL with pgvector, Redis, Prefect,
[Pydantic AI](https://ai.pydantic.dev), Next.js 15. External destinations depend on model, parser, embedding, tool, channel, sandbox and tracing configuration. Review the [data-flow statement](docs/security.md).
## Contributing
`make check` before a pull request: every CI job except e2e, about five minutes.
New behaviour ships with a test; a bug ships with a regression test. The
**platform layer is held at 100% coverage** and CI fails below it.
Three things that trip up a first change: a tool is code and an agent is not
(there is no `@agent.tool` — a capability registers, and then it is a switch in
everybody's Builder); `require(...)` gates go on collection routes only; and if
the tool already exists as an MCP server, write none.
[CONTRIBUTING.md](CONTRIBUTING.md) has the rest, [`.claude/`](.claude/README.md)
has the same conventions written for a machine, and good first issues are
[labelled here](https://github.com/vstorm-co/agenticos/labels/good%20first%20issue).
<details>
<summary><b>The rest of the Vstorm OSS ecosystem</b></summary>
Everything below runs on [Pydantic AI](https://ai.pydantic.dev).
| Project | What it is | |
|---|---|---|
| **[full-stack-ai-agent-template](https://github.com/vstorm-co/full-stack-ai-agent-template)** | The generator AgenticOS was built from — FastAPI + Next.js 15, RAG, streaming, auth, 20+ integrations | [](https://github.com/vstorm-co/full-stack-ai-agent-template) |
| **[pydantic-deepagents](https://github.com/vstorm-co/pydantic-deepagents)** | Open-source, self-hosted Claude Code — a terminal assistant and the framework behind it | [](https://github.com/vstorm-co/pydantic-deepagents) |
| **[pydantic-ai-shields](https://github.com/vstorm-co/pydantic-ai-shields)** | Guardrails — cost tracking, prompt-injection detection, PII filtering, secret redaction | [](https://github.com/vstorm-co/pydantic-ai-shields) |
| **[subagents-pydantic-ai](https://github.com/vstorm-co/subagents-pydantic-ai)** | Nested subagent delegation, parallel execution, task cancellation | [](https://github.com/vstorm-co/subagents-pydantic-ai) |
| **[pydantic-ai-backend](https://github.com/vstorm-co/pydantic-ai-backend)** | File storage and Docker-isolated sandboxes, with a permission system | [](https://github.com/vstorm-co/pydantic-ai-backend) |
| **[pydantic-ai-todo](https://github.com/vstorm-co/pydantic-ai-todo)** | Hierarchical task planning with PostgreSQL storage and an event system | [](https://github.com/vstorm-co/pydantic-ai-todo) |
| **[production-stack-skills](https://github.com/vstorm-co/production-stack-skills)** | Skill pack that turns a coding agent into a senior production engineer | [](https://github.com/vstorm-co/production-stack-skills) |
| **[content-skills](https://github.com/vstorm-co/content-skills)** | Content studio skill pack for coding agents — brand-aware, with built-in anti-slop | [](https://github.com/vstorm-co/content-skills) |
Browse them all at **[oss.vstorm.co](https://oss.vstorm.co)**.
Browse them all at **[oss.vstorm.co](https://oss.vstorm.co)**.
</details>
## Licence
Apache License 2.0 - see [`LICENSE`](LICENSE) and [`NOTICE`](NOTICE).
[`THIRD_PARTY_NOTICES.md`](THIRD_PARTY_NOTICES.md) lists every component the
images ship and its licence; the review of what those licences oblige, and the
findings still open, is in [the documentation](https://vstorm-co.github.io/agenticos/licenses/).
Apache-2.0 rather than MIT because AgenticOS is meant to be deployed inside other
companies: the explicit patent grant is the part their legal review asks about,
and MIT is silent on it.
---
<div align="center">
### Need help putting agents into production?
<p>
Vstorm can help deploy AgenticOS in client infrastructure, write documentation, define processes and build custom elements. Maintenance and support are agreed for the project.
</p>
<a href="https://vstorm.co/">
<img src="https://img.shields.io/badge/Talk%20to%20us%20%E2%86%92-0066FF?style=for-the-badge&logoColor=white" alt="Talk to us">
</a>
<br><br>
Built with care by <a href="https://vstorm.co"><b>Vstorm</b></a> ·
<a href="https://oss.vstorm.co">oss.vstorm.co</a>
</div>
Connection Info
You Might Also Like
No recommendations available