A simple library to build compute graphs for logical flows like agents.
Project description
Micro-Graph
If all the fancy langgraph etc. libraries are too heavyweight and complex for you, look no further.
A tiny library allowing you to build graphs for executing workflows. It is focused purely on minimalism, simplicity and ease of understanding. It does not need any dependencies.
🛠️ Installation
pip install micro-graph
# to also install `micro_graph.ai` dependencies
pip install micro-graph[ai]
👨💻 Usage
See the testcases for example uses, e.g. test_simple.py.
👥 Contributing
Feel free to make this code better by forking, improving the code and then pull requesting.
However, the goal of this repo is to be the minimal functionallity required and implementing it without any external dependencies. Please keep this in mind if you modify this repo.
Keep it simple!
⚖️ License
Micro-Graph is licensed under the permissive MIT license -- see LICENSE for details.
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 micro_graph-0.2.0.tar.gz.
File metadata
- Download URL: micro_graph-0.2.0.tar.gz
- Upload date:
- Size: 8.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d13a93477711aeeef418d07304254b576977bd9c2aed972b2dacb20dee219b03
|
|
| MD5 |
b007ff3172d1a52f794cf9dbc789921e
|
|
| BLAKE2b-256 |
bdc9425dbcb2180adeeab070733e4fa8c1f2708aa5485b02f3609973ad4bde80
|
Provenance
The following attestation bundles were made for micro_graph-0.2.0.tar.gz:
Publisher:
python-publish.yml on penguinmenac3/micro-graph
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
micro_graph-0.2.0.tar.gz -
Subject digest:
d13a93477711aeeef418d07304254b576977bd9c2aed972b2dacb20dee219b03 - Sigstore transparency entry: 332683654
- Sigstore integration time:
-
Permalink:
penguinmenac3/micro-graph@e637d0e38754a5845d23a5a0479492db28ef5307 -
Branch / Tag:
refs/tags/V0.2.0 - Owner: https://github.com/penguinmenac3
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-publish.yml@e637d0e38754a5845d23a5a0479492db28ef5307 -
Trigger Event:
release
-
Statement type:
File details
Details for the file micro_graph-0.2.0-py3-none-any.whl.
File metadata
- Download URL: micro_graph-0.2.0-py3-none-any.whl
- Upload date:
- Size: 7.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
88c9561c3ed829fee654476e5ea0a90faf2775060e6928beac7b5a1a70e268b6
|
|
| MD5 |
045f77003bcd309a12dd9f69ce83faea
|
|
| BLAKE2b-256 |
91279abdb36f88e0584bf0671955c30535789ff280c2009effcd4769e0d3d6ed
|
Provenance
The following attestation bundles were made for micro_graph-0.2.0-py3-none-any.whl:
Publisher:
python-publish.yml on penguinmenac3/micro-graph
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
micro_graph-0.2.0-py3-none-any.whl -
Subject digest:
88c9561c3ed829fee654476e5ea0a90faf2775060e6928beac7b5a1a70e268b6 - Sigstore transparency entry: 332683671
- Sigstore integration time:
-
Permalink:
penguinmenac3/micro-graph@e637d0e38754a5845d23a5a0479492db28ef5307 -
Branch / Tag:
refs/tags/V0.2.0 - Owner: https://github.com/penguinmenac3
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-publish.yml@e637d0e38754a5845d23a5a0479492db28ef5307 -
Trigger Event:
release
-
Statement type:
