An AI agent platform for Python with domain-specific knowledge capabilities
Project description
kguru
An AI agent platform for Python with domain-specific knowledge capabilities.
Features
- Agentic Framework: Reasoning loop with human-in-the-loop for intelligent problem-solving
- Domain Learning: Learns from domain-specific knowledge and user feedback
- Dynamic Knowledge Base: Build and assemble knowledge on the fly from structured, semi-structured, and semantic vector sources
- Multi-Model Support: Works with various language models and vision language models
Installation
pip install kguru
Or with uv:
uv add kguru
Quick Start
import kguru
agent = kguru.Agent()
# Run the agent loop
result = agent.solve("Your problem here")
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
kguru-0.1.4.tar.gz
(219.4 kB
view details)
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
kguru-0.1.4-py3-none-any.whl
(12.7 kB
view details)
File details
Details for the file kguru-0.1.4.tar.gz.
File metadata
- Download URL: kguru-0.1.4.tar.gz
- Upload date:
- Size: 219.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
697e5a7a36d42e6b3a34b7e82488daa016073f7dc578814e5aa7dca42993f02f
|
|
| MD5 |
495db63baef07577fc57bc5b60b1dcda
|
|
| BLAKE2b-256 |
990f48c81a9b13d81fbe42202f15771f4ada0298e1e624a53649f89e148d666a
|
File details
Details for the file kguru-0.1.4-py3-none-any.whl.
File metadata
- Download URL: kguru-0.1.4-py3-none-any.whl
- Upload date:
- Size: 12.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e0211f9474f0b4cda0a1b003c24c588d134b9b8434ffaf341beefa3dbd9a82ff
|
|
| MD5 |
bd446e00438241a83c96678b1e296ca7
|
|
| BLAKE2b-256 |
14c7ab773a495b80d7bd3849327ea602da4fa458f6a0894a46c5152da9688a46
|