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.
The idea is to make it easy to a multi-agent platform.
Usage
Basic Example
(TODO)
Complex Journal Multi-Agent Platform
(TODO)
Philosophy
I went with three guiding principles in writing this model.
- Everything is an agent: tools, buses, orchestrators are all agents.
- 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.
- Agents are minimal building blocks: one prompt per agent, one vector store per agent, one model per agent.
Deployment
The mode of deployment is as follows:
Make sure that there is a model and an API, based on the BaseModelin LangChain.
Put all agents in the same piece of code.
Run this code on a loop - the loop can also be an "orchestrator" agent.
Note that you can also host the model on the same pod / instance / computer as the agents. This is how I (the author) tested it.
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
- Branch out
- Add new code.
- Add tests.
- Push.
- Make a pull request.
Metadata
Release files for agents-on-langchain 0.1.0.dev202502010505
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agents_on_langchain-0.1.0.dev202502010505.tar.gz | 10.3 kB | Without provenance | Details for agents_on_langchain-0.1.0.dev202502010505.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agents_on_langchain-0.1.0.dev202502010505-py3-none-any.whl | Python 3 | none | any | Details for agents_on_langchain-0.1.0.dev202502010505-py3-none-any.whl |
Total release size: 18.6 kB
Release files / agents_on_langchain-0.1.0.dev202502010505.tar.gz
| Download URL | agents_on_langchain-0.1.0.dev202502010505.tar.gz |
|---|---|
| Size | 10.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d8b74983c3c0ee8a58cdfc8c6e4f1be31a0b94fb1b7866fee762288576b6e704
|
|
BLAKE2b-256 checksum How to use checksums |
314e6ea209deb7f0a2c6e7ce9a7ef87499c4bb07d19eb88af6dba09fc7873b02
|
| 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.dev202502010505-py3-none-any.whl
| Download URL | agents_on_langchain-0.1.0.dev202502010505-py3-none-any.whl |
|---|---|
| Size | 8.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ec78a656ea0a1bc5401fe33fcc52801c2afe3336c482b08f1795aeb2019d1853
|
|
BLAKE2b-256 checksum How to use checksums |
69cec1bc2e8f39e7da42e4e602035ef2c280901eb01d078190401b9141e26fb8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.10.16
|
Security for agents-on-langchain 0.1.0.dev202502010505
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.