OpenBB Open Data Platform
The open-source data infrastructure for analysts, quants, and AI agents — connect once, consume everywhere.
- Source repo
- openbq-org/OpenBB
- Stars
- ★ 74k
- Last updated
- today
- License
- NOASSERTION
- Primary language
- Python
- FA score
- 37/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platform
- Cost
- Free tier plus a paid hosted plan
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- Quantitative researchers pull historical stock data programmatically for backtesting.
- Not a fit if
- Teams that need fully offline operation with no data leaving the machine
- Closed-source commercial projects unwilling to accept AGPLv3 obligations
- Users wanting zero-config data without provider API keys or subscriptions
- Source review
- 37/100 · Major gaps 8 safety controls not found
What does this agent do, and when should you use it?
OpenBB Open Data Platform (ODP) is an open-source toolkit that helps data engineers integrate proprietary, licensed, and public data sources into downstream applications like AI copilots and research dashboards. It serves as a 'connect once, consume everywhere' infrastructure layer, exposing data to multiple surfaces: Python environments, OpenBB Workspace, Excel, MCP servers for AI agents, and REST APIs. The core library is installable via pip install openbb, providing the obb object for data access, e.g., obb.equity.price.historical("AAPL"). It also includes a CLI (openbb-cli) and a FastAPI server (openbb-api) that can be integrated with the OpenBB Workspace. Licensed under AGPLv3.
The platform provides a Python package (openbb) that exposes a unified data access interface through the obb object, covering asset classes like equities, crypto, derivatives, and more. Users can call functions such as obb.equity.price.historical("AAPL") from Python and convert output to DataFrames. It also offers a CLI (openbb-cli) and a REST API server (openbb-api) that starts on 127.0.0.1:6900. The API can be connected to OpenBB Workspace as a backend for data visualization. The available data integrations are listed in the documentation.
- Quantitative researchers pull historical stock data programmatically for backtesting.
- Data engineers integrate the REST API into internal data pipelines.
- Analysts connect the local ODP backend to OpenBB Workspace for interactive dashboards.
- AI application developers use MCP server endpoints to fetch financial data for agents.
- Hobbyist investors query market data from the command line using the CLI.
- Fintech startups leverage ODP as an open-source data layer to build custom research tools.
How do you install or deploy this agent?
Install via pip: pip install openbb (basic) or pip install "openbb[all]" for all extensions. Alternatively, clone the repository: git clone https://github.com/OpenBB-finance/OpenBB.git. For the CLI, install separately: pip install openbb-cli.
How do you use this agent?
In a Python environment, import the obb object and call methods, e.g.:
from openbb import obb
output = obb.equity.price.historical("AAPL")
df = output.to_dataframe()To start the API server, after installing openbb[all] in a Python 3.9.21-3.12 environment, run openbb-api. This launches a FastAPI server at 127.0.0.1:6900. Then, in OpenBB Workspace, navigate to the 'Apps' tab, click 'Connect backend', and enter the name and URL http://127.0.0.1:6900. Test the connection and add it.
What are this agent's strengths and limitations?
- Unified interface abstracts multiple data sources, reducing integration effort.
- Supports multiple consumption modes: Python, CLI, REST API, and MCP.
- Open-source with active community, allowing customization and extension.
- Seamless integration with OpenBB Workspace enhances analyst workflows.
- AGPLv3 license may require derivative works to be open-sourced.
- Some data providers may require API keys or paid subscriptions.
- Installing all extensions can increase dependency size and complexity.
- Data accuracy is not guaranteed; users must verify information.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| OpenBB Open Data Platform This agent | 37 · Major gaps | Library / SDKFreemium | ★ 74k | today | Python | — |
| AI Stock Analysis System | 46 · Major gaps | CLIFree + model costs | ★ 67k | 1d ago | Python | — |
| Lumibot Trading Framework | 57 · Major gaps | Library / SDKFree + model costs | ★ 2.1k | today | Python | Codex · Claude Code |
| A-Share Full-Stack Data Toolkit | 52 · Major gaps | Agent plugin / skillFree | ★ 11k | 7d ago | Python | Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows a security policy (SECURITY.md) and security scanning in CI workflows (bandit), but no specific implementation or documentation for least privilege, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, rollback, or source attribution. Therefore all trust criteria score 0.
Self-consistency: README, LICENSE, SECURITY.md, and CI workflows are broadly consistent in description, but code consistency not deeply verified, score 2. Dependency availability: README provides installation instructions and PyPI link, but no dependency locking or availability guarantees, score 2. Failure messages: Test files show error handling tests, but no user-facing failure message documentation, score 1.
Audience and scenarios: README clearly targets analysts, quants, and AI agents, and describes multiple use cases, score 2. Capability boundaries: No explicit statement of platform boundaries, score 1. Trigger precision: CLI and API documented, but trigger conditions not detailed, score 1. Environment fit: Multiple installation methods (pip, CLI, Dev Containers, Colab), score 2.
Information architecture: README well-structured with TOC and sections, score 2. Install notes: pip and CLI installation instructions provided, score 2. Naming stability: No naming conventions or stability guarantees, score 1. Examples and FAQ: Code examples and links to docs, but no FAQ, score 2. Known limitations: Disclaimer present, but no explicit list of limitations, score 1. License: LICENSE file clearly AGPLv3, score 2. Versioning and changelog: No changelog provided, score 1. Maintenance responsibility: Contribution guide and contact info, score 2.
Output usability: Multiple output methods (Python, API, CLI), score 2. Marginal value: Unique value as data integration platform, score 2. Cost benefit: No cost information, score 1.
Claim traceability: Claims in README not backed by specific evidence, score 1. Cross-source corroboration: No external verification, score 1. Fact-inference separation: No clear separation of facts and inferences, score 1.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- Publisher identity unverified, treat as unknown.
- Static review, no code execution, conclusions based on file contents only.
- Trust-related criteria all unmet, further review of permissions and data flow needed.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
openbb-v5.0.0 OpenBB V5
Release notes excerpt
OpenBB V5 Changelog OpenBB V5 is the new major-version line of the kept packages under openbb_platform/ and cli/. The openbb metapackage is now 5.0.0; the core, CLI, API, MCP server, routers and most providers are 2.0.0; exceptions include openbb-devtools (1.6.8 -> 2.0.1), openbb-charting (3.0.0 -> 4.0.0) and openbb-imf (2.1.3 -> 2.1.2 -> 3.0.0). The repository license changed from AGPL-3.0-only to Apache-2.0 in [#7677](https://github.com/OpenBB-finance/OpenBB/pull/7677), in the root LICENSE, every pyproject.toml and the desktop app. …View on GitHub ↗ -
ODP ODP Desktop (Latest Stable)
Release notes excerpt
This is the latest stable release (v2.0.0) This release always points to the most recent stable version. For version-specific details and release notes, see: [ODP Desktop v2.0.0](https://github.com/OpenBB-finance/OpenBB/releases/tag/Open-Data-Platform-v2.0.0) The latest.json file in this release is used by the auto-updater to check for new versions.View on GitHub ↗ -
Open-Data-Platform-v2.0.0 ODP Desktop v2.0.0