AI. On Your Terms.

Ship AI tools without shipping your data

The infrastructure layer between your AI powered applications and the models. Your data stays where it is, the instance is yours, and you choose which model sees what, including one on your own hardware.

Start free on Sinas Cloud

View on GitHub

Backed by

Ownership

Built so your data stays yours.

Every AI feature sends data somewhere. The question is who decides what leaves, and whether you can see it afterwards. With Sinas that's configuration you control, not a policy you accept: your provider, your keys, your permissions, and no one else reading your data.

Your provider, your key

Connect an agent to OpenAI, Anthropic or Mistral with your own account. The contract is between you and the provider, so their data terms apply directly to you, with no one in the middle.

Your hardware, your model

Prefer to keep the model in-house? Run it with Ollama on hardware you control, and set it up like any other provider. For work that can never leave the building, it doesn't have to.

Permissions decide what a model can see

An agent can only reach what the person using it can reach, and that is checked again every time it uses a tool. What can be sent to a model is limited before anyone writes a prompt.

We are not in your data

We don't read what's in your instance, mine it, or use it to train anything. That's in our terms, and since the platform is open source, you can check the code that handles it.

Platform

Everything you need to ship AI applications

Agents and functions to build with, connectors and triggers to reach the rest of your stack, storage and permissions underneath. All behind one API, and you can ignore the parts you do not need.

See every feature in detail

AI Agents

Agents that call tools, stream responses and hand work to other agents. Choose OpenAI, Anthropic, Mistral or Ollama per agent.

Python Functions

Run your own Python in isolated containers. Start it from an agent, a webhook, a schedule or the API, with every run logged.

Connectors

Turn any OpenAPI spec into tools your agents can call. Each user signs in with their own account, so one integration works for everyone.

Components

UI widgets you can embed in your own app. They talk to agents and functions through Sinas, so credentials never reach the browser.

Data & State

Query PostgreSQL, ClickHouse or Snowflake with safe SQL templates. Store files with versions, and give agents memory that can be encrypted per record.

Triggers

Start work from webhooks, schedules, or changes in your database, without installing anything on the database itself.

Who it's for

Who is Sinas for?

Two kinds of team, the same platform. What differs is what you are optimising for.

Developers and product teams who need the AI feature shipped, not a platform to build first

Agents, functions, queries, state, files and skills behind one API, with permissions and logging already handled, so your team spends its time on the part users actually see.

Read the developer case

Agencies and consultancies who ship AI products for clients, one engagement after another

One isolated instance per client, a package library you reuse from the second project onwards, and a licence answer your client’s legal reviewer will accept.

Read the agency case

Use cases

What teams have built

Real applications WeAreBrain built for clients on Sinas: what the problem was, what was assembled, and what changed.

All use cases

Browse packages

Procurement

Supplier onboarding as one guided workflow instead of forms, handovers and repeated checks.

IT and customer support

A support agent running entirely inside a closed infrastructure, for a platform rollout across 4,000 employees.

Sales and lead generation

Scheduled collection, AI analysis and scoring that hands sales teams prioritised leads instead of a search task.

In their words

Ownership, control, and a shorter road to working AI applications

From the people who build on it, including our own team and the partners who put it into production first.

It handles the “boring” parts of AI, state management and file handling, so I can focus on the prompts and the logic. Simple, powerful, and honestly, a joy to build with.
Mario Grunitz
Co-founder, WeAreBrain
The “no vendor lock-in” wasn’t just a marketing pitch. We have full RBAC and data sovereignty because it’s self-hosted. It’s rare to find a tool that offers this much power without forcing you into their cloud ecosystem.
Maurice
Co-founder, TITAN
We had a production-ready AI agent running in under 20 minutes. Being able to deploy the entire stack via Docker Compose meant we spent our afternoon building features instead of debugging environment variables.
Dmitry Ermakov
CTO - Head of Engineering
This tool replaced that entire mess with a single endpoint. We’ve cut our backend codebase by 30% and improved our response latency significantly. It’s the ultimate shortcut for complex AI apps.
Tanya Lyabik
Head of Product
Finally, someone put agents, state, and files behind one clean API. It’s the abstraction layer we’ve been waiting for: clean, logical, and incredibly fast to implement.
Enrico Karsten
CEO, Pulsr

This tool replaced that entire mess with a single endpoint. We’ve cut our backend codebase by 30% and improved our response latency significantly. It’s the ultimate shortcut for complex AI apps.
Tanya Lyabik
Head of Product
We had a production-ready AI agent running in under 20 minutes. Being able to deploy the entire stack via Docker Compose meant we spent our afternoon building features instead of debugging environment variables.
Dmitry Ermakov
CTO - Head of Engineering
It handles the “boring” parts of AI, state management and file handling, so I can focus on the prompts and the logic. Simple, powerful, and honestly, a joy to build with.
Mario Grunitz
Co-founder, WeAreBrain
The “no vendor lock-in” wasn’t just a marketing pitch. We have full RBAC and data sovereignty because it’s self-hosted. It’s rare to find a tool that offers this much power without forcing you into their cloud ecosystem.
Maurice
Co-founder, TITAN
Finally, someone put agents, state, and files behind one clean API. It’s the abstraction layer we’ve been waiting for: clean, logical, and incredibly fast to implement.
Enrico Karsten
CEO, Pulsr

Finally, someone put agents, state, and files behind one clean API. It’s the abstraction layer we’ve been waiting for: clean, logical, and incredibly fast to implement.
Enrico Karsten
CEO, Pulsr
This tool replaced that entire mess with a single endpoint. We’ve cut our backend codebase by 30% and improved our response latency significantly. It’s the ultimate shortcut for complex AI apps.
Tanya Lyabik
Head of Product
It handles the “boring” parts of AI, state management and file handling, so I can focus on the prompts and the logic. Simple, powerful, and honestly, a joy to build with.
Mario Grunitz
Co-founder, WeAreBrain
We had a production-ready AI agent running in under 20 minutes. Being able to deploy the entire stack via Docker Compose meant we spent our afternoon building features instead of debugging environment variables.
Dmitry Ermakov
CTO - Head of Engineering
The “no vendor lock-in” wasn’t just a marketing pitch. We have full RBAC and data sovereignty because it’s self-hosted. It’s rare to find a tool that offers this much power without forcing you into their cloud ecosystem.
Maurice
Co-founder, TITAN

It handles the “boring” parts of AI, state management and file handling, so I can focus on the prompts and the logic. Simple, powerful, and honestly, a joy to build with.
Mario Grunitz
Co-founder, WeAreBrain
The “no vendor lock-in” wasn’t just a marketing pitch. We have full RBAC and data sovereignty because it’s self-hosted. It’s rare to find a tool that offers this much power without forcing you into their cloud ecosystem.
Maurice
Co-founder, TITAN
We had a production-ready AI agent running in under 20 minutes. Being able to deploy the entire stack via Docker Compose meant we spent our afternoon building features instead of debugging environment variables.
Dmitry Ermakov
CTO - Head of Engineering
This tool replaced that entire mess with a single endpoint. We’ve cut our backend codebase by 30% and improved our response latency significantly. It’s the ultimate shortcut for complex AI apps.
Tanya Lyabik
Head of Product
Finally, someone put agents, state, and files behind one clean API. It’s the abstraction layer we’ve been waiting for: clean, logical, and incredibly fast to implement.
Enrico Karsten
CEO, Pulsr

It handles the “boring” parts of AI, state management and file handling, so I can focus on the prompts and the logic. Simple, powerful, and honestly, a joy to build with.
Mario Grunitz
Co-founder, WeAreBrain
The “no vendor lock-in” wasn’t just a marketing pitch. We have full RBAC and data sovereignty because it’s self-hosted. It’s rare to find a tool that offers this much power without forcing you into their cloud ecosystem.
Maurice
Co-founder, TITAN
We had a production-ready AI agent running in under 20 minutes. Being able to deploy the entire stack via Docker Compose meant we spent our afternoon building features instead of debugging environment variables.
Dmitry Ermakov
CTO - Head of Engineering
This tool replaced that entire mess with a single endpoint. We’ve cut our backend codebase by 30% and improved our response latency significantly. It’s the ultimate shortcut for complex AI apps.
Tanya Lyabik
Head of Product
Finally, someone put agents, state, and files behind one clean API. It’s the abstraction layer we’ve been waiting for: clean, logical, and incredibly fast to implement.
Enrico Karsten
CEO, Pulsr

Deployment

Ready to start? You choose where it runs.

Sinas Cloud and the self-hosted edition are the same open-source platform, released under AGPL v3 and driven by the same configuration files. Start on Cloud in minutes with no card, or install it on your own infrastructure with one command.

We host

Sinas Cloud

A managed instance with upgrades, backups, monitoring and the console operated for you. Live in minutes, with no servers to size.

Your own instance, operated for you

Managed upgrades, monitoring and daily backups

Every feature from the free tier up, nothing held back

Priority email support on every paid plan

See Cloud pricing

You host

Self-hosted

The same AGPL v3 platform on your own infrastructure. You own the data, the infra and the deployment.

One command on any Linux VPS: 2 cores, 4GB RAM, 50GB disk

Or the Helm chart on Kubernetes: kind, k3s, GKE or EKS

Airgapped, with password auth and no mail server at all

Terminal

AGPL V3 · ONE COMMAND

copy

$ sudo curl -fsSL https://raw.githubusercontent.com/sinas-platform/sinas/main/install.sh \n \t -o /tmp/sinas-install.sh && sudo bash /tmp/sinas-install.sh \n # Running at localhost:80 (API) & localhost:51245 (Console)

$ sudo curl -fsSL https://raw.githubusercontent.com/sinas-platform/sinas/main/install.sh \

-o /tmp/sinas-install.sh && sudo bash /tmp/sinas-install.sh

# Running at localhost:80 (API) & localhost:51245 (Console)

View on GitHub

Deployment guide

Ready to start?

Start with an instance of your own

Free plan on Sinas Cloud, no credit card, live in a couple of minutes.

Open source. Deploy in minutes.
No vendor lock-in.

Start free on Sinas Cloud

Read documentation