Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

A lightweight framework to create agents based on the LangChain BaseModel interface.

Usage

Philosophy

I went with three guiding principles in writing this model.

  1. Everything is an agent: tools, buses, orchestrators are all agents.
  2. Final code should show the flow: You should be able scale while being able to see how agents connect to each other. This means that each agent relationship should be at most one line of code.
  3. Agents are minimal building blocks: one prompt per agent, one vector store per agent, one model per agent.

Development

Requirements

Just Docker. If you want to develop, you can use the .devcontainer on VS Code, you don't need to install anything.

This works with VS Code, however, if you want to use another IDE, you can also use the Dockerfile.dev to create your development environment.

Testing

Run:

docker-compose run --rm --build test

Contributing

  1. Branch out
  2. Add new code.
  3. Add tests.
  4. Push.
  5. Make a pull request.

Metadata

Release files for agents-on-langchain 0.1.0.dev202501292333

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agents-on-langchain 0.1.0.dev202501292333
File Size Uploaded
agents_on_langchain-0.1.0.dev202501292333.tar.gz 7.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for agents-on-langchain 0.1.0.dev202501292333
File Interpreter ABI Platform
agents_on_langchain-0.1.0.dev202501292333-py3-none-any.whl Python 3 none any Details

Total release size: 13.5 kB

Release files / agents_on_langchain-0.1.0.dev202501292333.tar.gz

Download URL agents_on_langchain-0.1.0.dev202501292333.tar.gz
Size 7.0 kB
Tags Source
SHA-256 checksum
How to use checksums
9da70b5fc8500c2679a63478fc0d3e93f4a1e1bdbae9be45f4af81d059886600
BLAKE2b-256 checksum
How to use checksums
c9cb70ae6d0c074d0b1af1ac302a4b7c25c4ff1408ab1735b741b2839d4c40a6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.16

Release files / agents_on_langchain-0.1.0.dev202501292333-py3-none-any.whl

Download URL agents_on_langchain-0.1.0.dev202501292333-py3-none-any.whl
Size 6.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
24bb44be613ffb11541dc69f71cb1f10fec798ea7d1f208781b3511ae9ac211c
BLAKE2b-256 checksum
How to use checksums
55c3cb5086cf9ac377abb167b434310753efeca9e9dfbba84de452e27019d8e2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.16
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page