repowiserepowise

App

activeloopai / deeplake

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

★ 9,270stars on GitHubC++Apache-2.0

This connects Repowise to activeloopai/deeplake's code. It does not install deeplake.

Repowise maps public repos from their source. Not affiliated with activeloopai. What is Repowise?

github.com/activeloopai/deeplakeIndexed at f432041

What is deeplake?

deeplake is a database for AI that stores and searches data and vectors for LLM applications and manages datasets for training deep learning models. It uses a storage format optimized for deep learning, keeping images, audio and video in their native compression and loading data lazily only when a query or training run needs it. The core code is mainly C++, with Python and C also in the repository. To install it, run pip install deeplake. Its code health is 8.1 out of 10 (Good), ranked #67 of 4,000+ indexed repos. The last commit to deeplake was on Feb 16, 2026, and 158 people have contributed.

As of commit f432041, indexed Aug 17, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentsdeeplake.md

Repo facts: type, license, health, rank, contributors
deeplake facts
TypeApp
LicenseApache-2.0
Code health8.1 / 10 (Good)
Health rank#67 of 4,000+ indexed repos
Last commitFeb 16, 2026
Contributors158
Bus factor1
Size856 files, 192,932 lines

Install deeplake

Commands copied from the README

  1. 1Install deeplake from PyPI with pip.
    pip install deeplake

Full install notes on GitHub

Explore deeplake

Ask about this code in your agent

This connects Repowise to deeplake's code. It does not install deeplake. To install deeplake, use the install steps.

Useful if you want to change or fork deeplake: your agent can ask how it is put together and get answers that cite its files.

Ask about deeplake

Answers come from deeplake's README and source, with the files they cite. Two free answers a day without an account.

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of activeloopai/deeplake from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

activeloopai/deeplake FAQ

What is deeplake?

deeplake is a database for AI that stores and searches data and vectors for LLM applications and manages datasets for training deep learning models. It keeps data in a format optimized for deep learning.

How does deeplake work?

deeplake stores data in a format built for deep learning, loads it lazily when a query or training run needs it, and streams it to PyTorch or TensorFlow dataloaders. Data can live in S3, Azure, GCP, local storage or memory.

How do I install deeplake?

deeplake can be installed from PyPI with pip using the command pip install deeplake. The package is installed the same way on any system where pip is available. See the install steps

What language is deeplake written in?

deeplake's primary language is C++, with 478 C++ files in the repository. It also includes Python and C code.

How is the deeplake code organized?

The cpp/ directory holds most of the code, postgres/ holds the Postgres-related code and tests, python/ holds Python code, and docs/ holds documentation.

When should I use deeplake?

deeplake is meant for storing and searching data plus vectors while building LLM applications, and for managing datasets while training deep learning models.

What license does deeplake use?

deeplake is released under the Apache-2.0 license.

Code health

8.0out of 10Good

On the leaderboards:#1 of 12 C++ repos

Key features of deeplake

  • Stores embeddings, text, images, audio, video, annotations and other data types in one dataset.
  • Provides one API to upload, download and stream datasets to and from S3, Azure, GCP, Activeloop cloud, local storage or in-memory storage.
  • Loads data lazily and lets users slice, index and iterate over it like NumPy arrays.
  • Includes built-in dataloaders for PyTorch and TensorFlow.
  • Works as a vector store for LangChain and LlamaIndex and supports data versioning and lineage.

How activeloopai/deeplake works

The python/ directory holds 51 Python files, and the README describes one API for uploading, downloading and streaming datasets. The cpp/ directory holds 612 files, the largest module, and cpp/CMakeLists.txt is its CMake build manifest. The postgres/ directory holds 131 files for the Postgres side, with tests under postgres/tests/py_tests, and .github/workflows/pg-extension-build.yaml builds that extension in continuous integration. Datasets are then read back for querying, vector search, streaming to PyTorch or TensorFlow dataloaders, or visualization. The docs/ directory holds 49 documentation files.

The codebase has 856 files and 13,494 symbols in 5 modules, led by C++, Python and C. Code health is 8.0 out of 10, rated good.