GraphCanon updated 4d · GitHub synced 4d
Decision brief
Agentflow simplifies the creation of complex workflows for large language models through simple JSON configurations.
Good fit when
- When you need to rapidly prototype LLM workflows with minimal coding via JSON configs
- For projects where workflow complexity needs to be managed without deep Python programming knowledge
Avoid when
- Avoid if requiring advanced customization that goes beyond basic JSON configurations
- Not suitable for scenarios needing real-time dynamic changes in workflow setup during execution
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (1100d since push)
- As of 4d
- Provenance
- Not a fork · Personal account
- As of 4d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install agentflowSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A tool for crafting complex workflows with large language models using simple JSON configurations.
Capability facts
- Languages
- python
Source: github.language · Aug 16, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 16, 2026)
1. Sign up for the [OpenAI API](https://platform.openai.com/overview) and get an [API key](https://help.openaiSource link
Source: README excerpt (regex_v1, Aug 16, 2026)
python -m run --flow=exampleSource link
Tags
README
Install and Use
Agentflow is currently in development. To try it:
- Sign up for the OpenAI API and get an API key
- Clone or download this repository.
- Create a
.envfile from example.env and add your OpenAI API key. - Run
pip install -r requirements.txtto install dependencies.
Now you can run flows from the command line, like this:
python -m run --flow=example
License
Agentflow is licensed under the MIT License.
For agents
This page has a .md twin and JSON over the API.