v1.0

v1.0

Build, run, and operate your AI agents. On your infrastructure.

ApowerB is thaink²’s open-source agent runtime. Build and orchestrate AI agents, connect the models and tools of your choice, self-host your stack, and keep control of your data.

Apache 2.0

Self-hosted

Multi-LLM

Python

FastAPI

Decorative abstract blue light texture.
Partner Logo
Partner Logo
Partner Logo
Partner Logo
Partner Logo

AI working on your data should not be a black box.

From day one, thaink² has built its Data Agents around a simple belief: when AI works with a company’s data, teams should be able to understand how it works, inspect its architecture, and retain control of their environment.

Decorative abstract red and blue light texture.

thaink²

|

+-------+--------+-------+

| | | |

Data Analyst BI Agent Knowledge Agent

| | | |

+-------+--------+-------+

|

ApowerB

Open-source runtime

Decorative abstract red and blue light texture.

thaink²

|

+-------+--------+-------+

| | | |

Data Analyst BI Agent Knowledge Agent

| | | |

+-------+--------+-------+

|

ApowerB

Open-source runtime

ApowerB is the technical core of that belief, made public.

It is the agent runtime powering our Data ecosystem, including our Data Analyst, BI, Predictive, and Knowledge Agents. Released under Apache 2.0, it can be audited, self-hosted, extended, and used to build your own agents.

Built for production. Not for demos.

ApowerB goes beyond a thin abstraction around an LLM. It provides the runtime environment required to build, expose, and execute agentic systems within a real-world architecture.

Decorative abstract red and blue light texture.

ApowerB UI

|

REST API

|

+------ ApowerB ------+

| |

Agent Runtime Orchestration

| |

Google ADK Tools / RAG

| |

LiteLLM Data

| |

Any LLM Provider PostgreSQL

Dynamically materialize your agents.

Your agent definitions are stored in the database and generated as executable Python modules at startup. You can evolve your agent catalog without rebuilding your entire architecture.

Agent definitions persisted in the database

Python modules generated automatically

Evolve without a full application rebuild

Decorative abstract blue light texture.

One runtime. Your choice of models.

LiteLLM provides a unified layer for connecting different model providers and compatible endpoints. Evolve your stack without rewriting your agents’ logic.

Multi-LLM through LiteLLM

Local models and custom endpoints

Switch providers without rewriting your agents

Decorative abstract blue light texture.

The essential capabilities are already built in.

RAG, Text-to-SQL, custom tools, integrations, webhooks, scheduled executions, and artifact generation: the building blocks required to turn an agent into a real system are built into the runtime.

RAG & Text-to-SQL

Tools, integrations & webhooks

Scheduled executions & artifact generation

Decorative abstract blue light texture.

Open source where it matters. Commercial where enterprise needs it.

No artificially limited open-source features designed to push you toward a higher plan. The agent runtime, agent materialization, multi-model connectivity, and core capabilities are available in the open-source core under Apache 2.0. Enterprise-specific operational capabilities and thaink² features are distributed separately as extensions.

ApowerB Open Source

Agent runtime

Agent orchestration

Agent materialization

Multi-LLM connectivity

RAG

Text-to-SQL

Custom tools & integrations

REST API & CLI

Self-hosting

Apache 2.0

thaink² / Extensions

AgentOps

Evaluation

Usage & cost controls

Enterprise monitoring

Advanced enterprise security

Organisation governance

Priority support

Managed implementation

Enterprise services

Commercial modules

Your infrastructure. Your models. Your data.

Deploy ApowerB in your own environment and retain control over where your agents run and where your data lives. The official deployment stack supports Docker Compose, Kubernetes, Helm, and VM deployments. The self-hosted Docker Compose setup starts PostgreSQL, the ApowerB backend, and ApowerB UI.

Docker

Kubernete

Helm

VM

Does aPowerB require a specific database?

Yes. aPowerB uses PostgreSQL. The official self-hosted Docker Compose stack includes a PostgreSQL service alongside the backend and UI.

Can I use my own LLM or a local model?

Yes. aPowerB uses LiteLLM as its multi-model connectivity layer, allowing you to work with different providers and endpoints without coupling your agents’ logic to a single model. The core documentation covers multi-provider compatibility through LiteLLM.

What is the difference between aPowerB and thaink²?

aPowerB is the open-source agent runtime that powers the thaink² ecosystem. You can use it to build and operate your own agents. thaink² adds ready-to-use Data Agents, along with Enterprise capabilities and services distributed separately.

Under which license is aPowerB distributed?

The aPowerB core is distributed under the Apache 2.0 license. The license allows the software to be used, modified, and redistributed, subject to its terms.

Launch your first instance.

Deploy the stack, explore the API, or start directly from the code.

Bash

git clone https://github.com/apowerb/apowerb-hosting.git

git clone https://github.com/apowerb/apowerb-hosting.git

cd apowerb-hosting

cd apowerb-hosting

cp .env.example .env

cp .env.example .env

docker compose -f docker-compose/docker-compose.yml --env-file .env up -d

docker compose -f docker-compose/docker-compose.yml --env-file .env up -d

An open-source foundation for building your own agents.

ApowerB is the open-source agentic framework developed by thaink² to build, orchestrate, and operate AI agents on your own stack, using your models, tools, and data.

What if your next analysis were ready before your next meeting?

Show us your environment and a use case. See how thaink² can query, monitor, and act on your data.

What is an Agentic Data Platform?

An Agentic Data Platform uses specialized AI agents to work with enterprise data. Unlike a static dashboard or a simple chatbot, agents can explore multiple sources, run analyses, generate visualizations, produce deliverables, and execute recurring missions.

What’s the difference between Proactive Mode and Exploratory Mode?

In Exploratory Mode, the user asks a question and thaink² runs the analysis on demand. In Proactive Mode, a mission is defined in advance: agents monitor the data based on a set schedule or specific conditions and automatically deliver the relevant results.

Do I need to know SQL to use thaink²?

Not for business use cases. Users can ask questions in natural language and get analyses, tables, charts, and dashboards without writing SQL queries themselves.

What data sources can thaink² connect to?

The platform is designed to work with the systems already in place across your organization: databases, data warehouses, ERP, CRM, APIs, files, and document repositories. Available connectors depend on your environment and use case.

What types of outputs can the agents produce?

Depending on the agent and use case, outputs can include analyses, tables, charts, dashboards, forecasts, alerts, summaries, and reports. The goal is to deliver an actionable result, not just a text response.

Can thaink² be deployed on our own infrastructure?

thaink² supports deployment options designed around enterprise requirements, including organizations that need greater control over their infrastructure, models, and data. Our teams help define the architecture that best fits the project.

Which part of the thaink² ecosystem is open source?

ApowerB is the open-source agentic framework developed by thaink². It enables technical teams to build and operate their own agents, with support for RAG, Text-to-SQL, multi-LLM setups, and APIs.

How do I get started with thaink²?

The easiest way to start is with a concrete use case: reporting, analysis, forecasting, document search, or monitoring. An initial session helps define the available data, expected outcomes, and the most suitable deployment approach.

Join our Discord community

Connect with builders, Data teams, and AI practitioners. Share ideas, get technical help, discuss agentic architectures, and follow the latest developments around ApowerB.

Our newsletter (Soon)

Data that takes action, straight to your inbox.

Field insights, agentic architectures, benchmarks, use cases, and the latest from ApowerB. Only what’s worth reading.

Agentic Data Platform for business teams.

Location

Metz, France

© All rights reserved.

An open-source foundation for building your own agents.

ApowerB is the open-source agentic framework developed by thaink² to build, orchestrate, and operate AI agents on your own stack, using your models, tools, and data.

What if your next analysis were ready before your next meeting?

Show us your environment and a use case. See how thaink² can query, monitor, and act on your data.

What is an Agentic Data Platform?

An Agentic Data Platform uses specialized AI agents to work with enterprise data. Unlike a static dashboard or a simple chatbot, agents can explore multiple sources, run analyses, generate visualizations, produce deliverables, and execute recurring missions.

What’s the difference between Proactive Mode and Exploratory Mode?

In Exploratory Mode, the user asks a question and thaink² runs the analysis on demand. In Proactive Mode, a mission is defined in advance: agents monitor the data based on a set schedule or specific conditions and automatically deliver the relevant results.

Do I need to know SQL to use thaink²?

Not for business use cases. Users can ask questions in natural language and get analyses, tables, charts, and dashboards without writing SQL queries themselves.

What data sources can thaink² connect to?

The platform is designed to work with the systems already in place across your organization: databases, data warehouses, ERP, CRM, APIs, files, and document repositories. Available connectors depend on your environment and use case.

What types of outputs can the agents produce?

Depending on the agent and use case, outputs can include analyses, tables, charts, dashboards, forecasts, alerts, summaries, and reports. The goal is to deliver an actionable result, not just a text response.

Can thaink² be deployed on our own infrastructure?

thaink² supports deployment options designed around enterprise requirements, including organizations that need greater control over their infrastructure, models, and data. Our teams help define the architecture that best fits the project.

Which part of the thaink² ecosystem is open source?

ApowerB is the open-source agentic framework developed by thaink². It enables technical teams to build and operate their own agents, with support for RAG, Text-to-SQL, multi-LLM setups, and APIs.

How do I get started with thaink²?

The easiest way to start is with a concrete use case: reporting, analysis, forecasting, document search, or monitoring. An initial session helps define the available data, expected outcomes, and the most suitable deployment approach.

Join our Discord community

Connect with builders, Data teams, and AI practitioners. Share ideas, get technical help, discuss agentic architectures, and follow the latest developments around aPowerB.

Our newsletter (Soon)

Data that takes action, straight to your inbox.

Field insights, agentic architectures, benchmarks, use cases, and the latest from ApowerB. Only what’s worth reading.

Agentic Data Platform for business teams.

Location

Metz, France

© All rights reserved.