Local AI research agent that generates structured research workspaces
Project description
Lens
Lens is a local AI research agent that takes a query, performs structured research, and stores results in a persistent workspace.
Installation
pip install lensdev
Usage
Run a research task:
lens research -q "how do vector databases work"
Workspace System
Every run generates a workspace:
workspace/<session_id>/
Example:
workspace/session_20260604_143210/
Structure:
report.mdsources.jsonmeta.json
CLI Commands
Run research:
lens research -q "query"
List sessions:
lens list
Resume session:
lens resume <session_id>
Output Behavior
After completion:
Research complete.
Workspace saved at: workspace/<session_id>/
Philosophy
Lens turns research into structured, persistent workspaces instead of temporary terminal output.
GitHub: https://github.com/developer8sarthak/lens-research
PyPI: https://pypi.org/project/lensdev/
Documentation: https://lensdev.pages.dev/
Project details
Release history Release notifications | RSS feed
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 lensdev-0.1.2.tar.gz.
File metadata
- Download URL: lensdev-0.1.2.tar.gz
- Upload date:
- Size: 3.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
96de4610791c55599059474c197014f1184756d48836e85deb678b9bcac71eaa
|
|
| MD5 |
02aad6304483ad626fe6d04d6103e32c
|
|
| BLAKE2b-256 |
94477ab8f92421651d9fcf37441e7eb789e8ee609b0d428a53ab33df0c8aa8ef
|
File details
Details for the file lensdev-0.1.2-py3-none-any.whl.
File metadata
- Download URL: lensdev-0.1.2-py3-none-any.whl
- Upload date:
- Size: 4.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b701fae475c8cee436b80cdcd0818c96108eff0b39e6fca16f04b170d7fed0ed
|
|
| MD5 |
35a2efcfc4fbc8c3502a93eb9edda739
|
|
| BLAKE2b-256 |
4314654e168c5454b2233a7cf33ab0be521ce933a79b08190eb43c83802ddbe5
|
