memgrafter/flatagents

Flat, declarative agents and state machines for orchestrating LLMs.

47
/ 100
Emerging

This project helps developers orchestrate complex, multi-step workflows involving Large Language Models (LLMs) by defining their behavior using declarative YAML configurations rather than extensive Python code. It takes YAML files describing agents, states, and transitions, and outputs a managed, resilient LLM application capable of handling retries, parallelism, and error recovery. This is for software developers and AI engineers who are building robust LLM-powered applications and need to manage intricate interaction patterns between AI agents.

Available on PyPI.

Use this if you are building an application that requires several LLM calls or agents to work together in a structured sequence, need built-in reliability for these interactions, and prefer to manage workflow logic through configuration files.

Not ideal if your application involves a single, straightforward LLM call or if you need to implement highly dynamic, code-driven control flows for your agents.

LLM-orchestration AI-application-development workflow-automation declarative-programming agent-systems
Maintenance 10 / 25
Adoption 7 / 25
Maturity 20 / 25
Community 10 / 25

How are scores calculated?

Stars

27

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Mar 10, 2026

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/memgrafter/flatagents"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.