Sinas

[Features]

(https://sinas.co/features)

[Contact]

(https://sinas.co/contact)

[GitHub]

(https://github.com/sinas-platform/sinas)

[Docs]

(https://docs.sinas.co/)

Open Source Self-hosted AGPL v3

#

Ship AI tools without shipping your data

Agents, functions, database queries, state, files, and templates, all behind a single API with role-based access control. Deploy with Docker Compose.

[Start on GitHub]

(https://github.com/sinas-platform/sinas)

[Read the Docs]

(https://docs.sinas.co/)

##

Why choose Sinas

###

Everything you need to ship AI applications

Six integrated subsystems, one unified API. Add what you need, ignore the rest.

AI Agents

Multi-provider LLM agents with tool calling, streaming, and agent-to-agent orchestration. OpenAI, Anthropic, Mistral, or Ollama.

Python Functions

Serverless Python in isolated Docker containers. Triggered by agents, webhooks, schedules, or the API. Automatic execution tracking.

Database Queries

SQL templates against external PostgreSQL, ClickHouse, or Snowflake. Parameterized, validated, and usable as agent tools.

Skills

Reusable instruction documents that agents retrieve on-demand or preload into system prompts. Share expertise without prompt bloat.

State Management

Persistent key-value storage with namespaces. Agents maintain memory and context across conversations with fine-grained access control.

Files & Templates

File collections with versioning and metadata validation. Jinja2 templates for emails and dynamic content. Upload hooks for processing.

##

Agents

###

Agents that call agents, use tools, and remember

Jump to any task, report, or invoice instantly. No digging, no delays – just clean, lightning-fast search across all your data.

Switch between OpenAI, Anthropic, Mistral, or Ollama per agent

Tool calling with functions, queries, skills, state, and file search

Agent-to-agent calls via async queue — no recursive blocking

SSE streaming with reconnectable Redis Streams

Jinja2 system prompts with input variable injection

##

Functions

###

Python functions with automatic execution tracking

Write Python, deploy instantly. Functions run in pre-warmed Docker containers with resource limits. Every call is tracked — including nested function calls that build execution trees.

Isolated containers with memory, CPU, and disk limits

Input/output validation via JSON Schema

Context injection: user_id, access_token, execution_id

Webhooks and cron schedules as triggers

Admin-approved package management

##

And more

###

Everything else included

Authentication, permissions, configuration management, and operational tooling — all built in.

Role-Based Access Control

Granular permissions with wildcard matching and scope hierarchy. :all automatically grants :own. Define custom permission prefixes for external apps.

Declarative Configuration

Define all resources in YAML. Idempotent apply with change detection, environment variable interpolation, reference validation, and dry-run mode.

Authentication

Passwordless OTP login, extensible authentication system, and API keys with scoped permissions. JWT access + refresh tokens.

Management Console

Web UI for managing agents, functions, queries, skills, users, and permissions. Configure everything visually, test functions, chat with agents.

Webhooks & Schedules

Expose functions as HTTP endpoints. Trigger functions or agents on cron schedules with timezone support. Input merging and default values.

Request Logging

Every API request logged to ClickHouse with method, path, status, duration, user, and permissions used. Auth endpoints automatically redacted.

##

Use cases

###

What you can build

Customer support

Agents that look up customer data via queries, follow tone guidelines via skills, and escalate via function calls. Full conversation history with state persistence.

Internal AI tools

Connect agents to internal databases and documentation. Role-based access ensures each team sees only their data. Deploy in hours, iterate in minutes.

Multi-tenant SaaS

Namespaces and RBAC make multi-tenancy native. Each customer gets isolated agents, functions, and state. Scale to thousands of tenants on one deployment.

Workflow automation

Receive webhooks, execute business logic in Python, trigger AI analysis, send templated emails. Visual execution trees show exactly what happened.

Client delivery

Agencies and consultancies: deploy one Sinas instance per client. Build 5-20 applications per deployment. Clean data sovereignty and easy handoff.

Research assistants

Agents with progressive skills for research methodology, file collections for document search, and state for tracking findings across sessions.

##

Deployment

###

Deploy anywhere, your way

Self-host on your infrastructure. Docker Compose handles everything — PostgreSQL, Redis, ClickHouse, workers, scheduler, and the console.

Self-hosted

Docker Compose on any Linux server, cloud VM, or on-premises. You own the data, the infra, and the deployment.

**Cloud VM**

Deploy to AWS, GCP, Azure, Hetzner, or DigitalOcean. Same Docker Compose setup. Optional Caddy for automatic HTTPS.

EU & GDPR

Host in EU data centers for full compliance. No data leaves your infrastructure. OIDC integration with your existing identity provider.

1 Command to install

4 LLM providers supported

2 API layers (runtime + MGMT)

Unlimited applications per deployment

###

Ownership. Control. Faster Time To Value

See how businesses use Sinas.

"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

"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

"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 at 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

##

GET STARTED IN MINUTES

###

Start building with Sinas

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

[Get started on GitHub]

(https://github.com/sinas-platform)

[Read Documentation]

(https://docs.sinas.co/)

Self-hosted & GDPR compliant

Open source (AGPL v3)

No vendor lock-in

One backend, unlimited apps

![Company Logo]

(https://)

Open source platform for building AI-powered applications. Agents, functions, state, queries, files, and templates — behind a single API.

An initiative of WeAreBrain

Product

[Features]

(https://sinas.co/features)

[Documentation]

(https://docs.sinas.co/)

Resources

[GitHub]

(https://github.com/sinas-platform/sinas)

[API Reference]

(https://sinas.co/)

[Contact]

(https://sinas.co/contact)

Social

[GitHub]

(https://github.com/sinas-platform)

[LinkedIn]

(https://www.linkedin.com/company/sinas-platform/)

© 2026 Sinas. Open source under AGPL v3.