Mini LLM Flow

Minimalist 100-line LLM framework for building self-programming agent workflows

4.8 (6)

Granskat av Daniel Nikulshyn·Uppdaterad maj 2026

Agents Open Source Educational Minimalist Developer Tools LLM Framework Workflow Orchestration

Översikt

Mini LLM Flow is a lightweight open-source framework that distills LLM orchestration down to roughly 100 lines of code. It provides the essential building blocks for chaining prompts, managing state, and constructing agent workflows without the overhead of larger frameworks. The project's core idea is that a minimal abstraction is easier for LLMs themselves to understand, extend, and generate code against. This makes it well-suited for experiments in self-programming agents, where models reason about and modify their own workflow logic. Developers can use it as a learning tool, a foundation for custom agent systems, or a stripped-down alternative to heavier orchestration libraries.

Nyckelfunktioner

Around 100 lines of core code
Prompt chaining and flow control
Support for agent-style workflows
Designed for LLM self-programming
Minimal dependencies
Open and easily forkable

Användningsfall

Learn agent workflow fundamentals

Study a compact ~100-line codebase to understand how prompt chaining, state, and agent orchestration work without wading through a large framework.

Build custom lightweight agent systems

Fork the minimal core as a foundation for bespoke agent workflows, avoiding heavy dependencies and lock-in from larger orchestration libraries.

Experiment with self-programming agents

Leverage the minimal abstraction so LLMs can read, reason about, and generate modifications to their own workflow code more reliably.

Prototype LLM pipelines quickly

Use the stripped-down primitives to spin up prompt chains and flow control for proofs of concept before committing to a heavier stack.

Fördelar och nackdelar

Fördelar

Extremely small and readable codebase
Easy for LLMs to understand and extend
No heavy dependencies or lock-in
Good educational resource for agent design

Nackdelar

Limited built-in features compared to larger frameworks
Requires more manual setup for complex use cases
Smaller community and ecosystem

Recensioner

4.8

Genomsnitt från 6 betyg.

Logga in för att lämna en recension.

Daniel Schmidt

Years in this space

I've evaluated a lot of these over the years. What stands out here is minimal dependencies — handled better than most — and no heavy dependencies or lock-in. Limited built-in features compared to larger frameworks is my one real gripe. Worth the time if this is your use case.

Leila Hassan

Years in this space

I've evaluated a lot of these over the years. What stands out here is open and easily forkable — handled better than most — and extremely small and readable codebase. Worth the time if this is your use case.

Sanjay Gupta

Years in this space

I've evaluated a lot of these over the years. What stands out here is prompt chaining and flow control — handled better than most — and extremely small and readable codebase. Smaller community and ecosystem is my one real gripe. Worth the time if this is your use case.

Gunnar Eriksson

Years in this space

I've evaluated a lot of these over the years. What stands out here is designed for LLM self-programming — handled better than most — and extremely small and readable codebase. Worth the time if this is your use case.

Linda Petersen

Solid for our team

We rolled this out across the team last quarter and extremely small and readable codebase. Support for agent-style workflows fits neatly into how we already work, and prompt chaining and flow control removed a step we used to do by hand. but it has held up under daily use.

Yuki Mori

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on minimal dependencies, and no heavy dependencies or lock-in caught me off guard. still, I'd recommend giving it a real trial.