Agentic Autonomous BI
🚀 Agentic Autonomous BI
The most advanced, fully autonomous, multi-platform BI agent: create, analyze, and publish your Power BI, Looker, Metabase, Next.js dashboards… with zero human intervention.
- Multi-agent orchestration: Planner, Data, Analytics, QA, Viz, Power BI, Integration
- Plug & Play: configure everything in
config.yaml, launch, and you’re ready - Multi-source: Excel, CSV, SQL, ERP, BigQuery, etc.
- Full automation: extraction, analysis, QA, BI publishing
- Extensible: add your own connectors, APIs, modules
📦 Installation
pip install agentic-autonomous-bi
🛠️ Configuration
- Clone the repo
- Edit
config.yaml(Azure credentials, data source, integrations) - Install dependencies
pip install -r requirements.txt
- Launch the agent
python orchestrator/orchestrator.py
🌐 BI Integrations
- Power BI: REST API, create datasets, dashboards, reports
- Looker Studio: CSV/Excel export, Google Drive/Sheets publishing
- Metabase: CSV/Excel export, watched folder/API publishing
- Next.js/React: JSON export, public folder publishing
🧠 Architecture
User
↓
Agentic BI Orchestrator (LangGraph / CrewAI)
↓
┌───────────────────────────────────┐
│ Planner Agent │
│ Data Agent (SQL, DAX) │
│ Analytics Agent (KPIs, trends) │
│ Visualization Agent (PowerBI JSON) │
│ QA Agent (Data quality & sanity) │
│ PowerBI Agent (REST API calls) │
│ Integration Agent (auto-publish) │
└───────────────────────────────────┘
✨ Features
- Multi-agent orchestration
- Multi-source extraction and analysis
- QA and data quality control
- Power BI, Looker, Metabase, Next.js dashboard generation
- Automated publishing
- Single YAML configuration
- Extensible and modular
🔒 Security
- Azure Service Principal authentication
- Secure credential management
🧪 Quick Test
python orchestrator/orchestrator.py
📖 Documentation
- Install Guide
- Install Guide
- Power BI Integration
- React/Next.js Integration
- Metabase Integration
- Looker Integration
Note: PyPI only displays this README. Documentation files (like integration guides) are not directly served by PyPI. All documentation links above point to GitHub and will always work. If you click a link that starts with https://pypi.org/..., it will result in a 404 error. Always use the GitHub links in this README for full documentation.
👤 Author
Idriss Bado
GitHub
⭐️ Contribute
Pull requests, issues, and suggestions welcome!
🏆 License
MIT License
📁 Project Structure
powerbi/: Power BI authentication and API integrationorchestrator/: Main orchestration logicdata/: Data sources and connectorsdashboards/: Exported dashboards and visualizationsagents/: Modular agents (Planner, Data, Analytics, QA, Visualization, Integration)config.yaml: Central configuration filerequirements.txt: Python dependenciesREADME.md: Project documentation
🧩 Extending
- Add SQL, ERP, BigQuery connectors in
agents/data_agent.py - Add new Power BI API methods in
powerbi/api.py - Add advanced analytics in
agents/analytics_agent.py
💬 Contact & Support
For questions, issues, or contributions, please open an issue or pull request on GitHub, or contact the author via the profile link above.
Metadata
Release files for agentic-dashboard-ai 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentic_dashboard_ai-0.1.3.tar.gz | 13.2 kB | Without provenance | Details for agentic_dashboard_ai-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentic_dashboard_ai-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for agentic_dashboard_ai-0.1.3-py3-none-any.whl |
Total release size: 18.0 kB
Release files / agentic_dashboard_ai-0.1.3.tar.gz
| Download URL | agentic_dashboard_ai-0.1.3.tar.gz |
|---|---|
| Size | 13.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f0b4f52485212711673e9da4386aa5f190b1035cbe06c518635d92df94468442
|
|
BLAKE2b-256 checksum How to use checksums |
64cad0136f19f4ab552d7fb9fe093122675fca04a2776db19074560a99ee0458
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|
Release files / agentic_dashboard_ai-0.1.3-py3-none-any.whl
| Download URL | agentic_dashboard_ai-0.1.3-py3-none-any.whl |
|---|---|
| Size | 4.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
aa0100d807d5f32b9047337c999a26bb5ac9b5f07dd8f3b253616078b4779b63
|
|
BLAKE2b-256 checksum How to use checksums |
0e86142541bde4b280682cab2ef9d191a9adf2cf599824a7929aa0107ae39f4e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|
Security for agentic-dashboard-ai 0.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.