Home/AI Agents/agentflow

agentflow

simonmesmith/agentflow

Complex LLM Workflows from Simple JSON

GitHub

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

217views this month

320 stars27 forksLast push Aug 11, 2023 Python MIT

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

agentflow alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Dormant (1100d since push); As of Aug 16, 2026
Provenance: Not a fork · Personal account; As of Aug 16, 2026
Security (OSV): No lockfile; As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install agentflow

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

dify

Build Agentic workflows and RAG pipelines with rich AI model and tool support on one collaborative workspace.

156k★

anything-llm

Self-hosted AI agent experience

66k★

AgentGPT

Assembler for autonomous AI Agents

36k★

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

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

OpenAI APIOpenAI API

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.openai

Source link

Python runtimePython

Source: README excerpt (regex_v1, Aug 16, 2026)

python -m run --flow=example

Source link

README

Install and Use Agentflow is currently in development. To try it: 1. Sign up for the OpenAI API and get an API key 2. Clone or download this repository. 3. Create a file from example.env and add your OpenAI API key. 4. Run to install dependencies. Now you can run flows from the c...

For agents

This page has a .md twin and JSON over the API.

/tools/simonmesmith-agentflow.md GET /api/graphcanon/tools/simonmesmith-agentflow GET /api/graphcanon/graph?tool=simonmesmith-agentflow