BioPB - AI-assisted bio-image analysis
The repo provides the core harness framework of the biopb project. The goal is to coordinate a LLM agent with a user in an interactive session to perform complex image ananlysis tasks relavent to scientific researches.
Quick Start
curl -fsSL https://biopb.org/install.sh | bash
biopb-mcp
An MCP server + napari plugin that hands an AI agent a live, shared napari session wired to the data and algorithm servers, so analysis is driven in plain Python instead of fixed GUI buttons. Read More...
- Shared canvas: napari viewer is accessible and mutable by both the agent and the user
- Persistent kernel: agent code runs in a real ipython kernel with namespace persistence and full observability
- Perceive → act → verify: the agent runs code, then screenshots/inspects to confirm the result
biopb-tensor
A blazing-fast imaging data server for sharing your lab's petabyte-scale datasets to LLM agents and human team members alike. Read More...
- Uniform Representation: all source data mapped to a multi-resolution and lazy-read array for client access
- Multi-language: dask array for Python and ImgLib2.CellImg for Java
- Thread-safe & Serializable: compatible with dask.distribute for distributed computing on larger-than-memory dataset
- Metadata Server: full DuckDB SQL support to query your embedded metadata
- On-the-fly Build: keep your data in original format (.zvi, ndtiff etc). No staging or on-boarding process needed
- Built-in Viewer: browse all your data with any browser (e.g., on an ipad)
biopb-image-runtime
Deploy complex image processing algorithms (e.g., large deep-learning models) on the network as services. Read More...
SDK
Schema, utilities and cli for building your own workflow. Explore your data in jupyter notebook etc.
Python
pip install biopb[tensor]
Java
<dependency>
<groupId>io.github.jiyuuchc</groupId>
<artifactId>biopb</artifactId>
<version>CURRENT_VERSION</version>
</dependency>
Related Projects in BioPB
biopb-servers
Specific implementations of biopb-image-runtimes. Read More...
Contributing
Contributions are very welcome. Read the developement document first to understand the overall design architecture.
License
Distributed under the terms of the MIT license,
Issues
If you encounter any problems, please file an issue along with a detailed description.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file biopb-0.9.1.tar.gz.
File metadata
- Download URL: biopb-0.9.1.tar.gz
- Upload date:
- Size: 3.6 MB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f2b2bc04a9b8e2ae3f12a887f5a10751600eaf3f6f485d33baa8e6460a058076
|
|
| MD5 |
7efdc5ceb2e6abb49746f63deb045dda
|
|
| BLAKE2b-256 |
6786e65ec319ae70785cc1899b58139b5c45c691f30cdf4317c209e51f866fe8
|
Provenance
The following attestation bundles were made for biopb-0.9.1.tar.gz:
Publisher:
python-ci.yaml on biopb/biopb
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
biopb-0.9.1.tar.gz -
Subject digest:
f2b2bc04a9b8e2ae3f12a887f5a10751600eaf3f6f485d33baa8e6460a058076 - Sigstore transparency entry: 2498473102
- Sigstore integration time:
-
Permalink:
biopb/biopb@4278c2a75b3cef18840ff2e0580430edef28fb77 -
Branch / Tag:
refs/tags/v0.9.1 - Owner: https://github.com/biopb
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-ci.yaml@4278c2a75b3cef18840ff2e0580430edef28fb77 -
Trigger Event:
push
-
Statement type:
File details
Details for the file biopb-0.9.1-py3-none-any.whl.
File metadata
- Download URL: biopb-0.9.1-py3-none-any.whl
- Upload date:
- Size: 200.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f2e88c30d1c8afdaadd2a93cbf06f88777b6498403f64cd70f695a18c779d5db
|
|
| MD5 |
92a92835ee7abe1aa18c21d4230e9588
|
|
| BLAKE2b-256 |
971690c7cecb06830c95b554ebec45518ee41b1453ff7603d5fb069392101826
|
Provenance
The following attestation bundles were made for biopb-0.9.1-py3-none-any.whl:
Publisher:
python-ci.yaml on biopb/biopb
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
biopb-0.9.1-py3-none-any.whl -
Subject digest:
f2e88c30d1c8afdaadd2a93cbf06f88777b6498403f64cd70f695a18c779d5db - Sigstore transparency entry: 2498473108
- Sigstore integration time:
-
Permalink:
biopb/biopb@4278c2a75b3cef18840ff2e0580430edef28fb77 -
Branch / Tag:
refs/tags/v0.9.1 - Owner: https://github.com/biopb
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-ci.yaml@4278c2a75b3cef18840ff2e0580430edef28fb77 -
Trigger Event:
push
-
Statement type:
