What is BrainyFlow?
Last updated
Last updated
A radically minimalist AI framework (just ! 🤯) Build Powerful AI Agents with Minimal Code, Maximum Freedom. Let Agents build Agents with Zero bloat, dependencies, or vendor lock-in 😮
BrainyFlow is a framework enabling Agentic Coding through powerful abstractions.
It provides a simple interface for building complex AI applications based on nested directed graphs with shared state. It enables both humans and AI assistants to collaborate effectively on designing and implementing AI systems.
Brain-Easy 🧠: Intuitive for both humans and AI assistants
Minimalist Design ✨: Core abstractions in just (you heard it right!) 300 lines of code
Freedom 🔓: Zero bloat, dependencies, or vendor lock-in
Composable 🧩: Build complex systems from simple, reusable components
Agentic-Coding 🤖: Designed for AI-assisted development
Universal 🌈: Works with any LLM provider or API
Polyglot 🌍: Python and Typescript are both supported
Current LLM frameworks are bloated... You actually only need 300 lines for a robust LLM Framework!
Abstraction
App-Specific Wrappers
Vendor-Specific Wrappers
Lines
Size
LangChain
Agent, Chain
Many (e.g., QA, Summarization)
Many (e.g., OpenAI, Pinecone, etc.)
405K
+166MB
CrewAI
Agent, Chain
Many (e.g., FileReadTool, SerperDevTool)
Many (e.g., OpenAI, Anthropic, Pinecone, etc.)
18K
+173MB
SmolAgent
Agent
Some (e.g., CodeAgent, VisitWebTool)
Some (e.g., DuckDuckGo, Hugging Face, etc.)
8K
+198MB
LangGraph
Agent, Graph
Some (e.g., Semantic Search)
Some (e.g., PostgresStore, SqliteSaver, etc.)
37K
+51MB
AutoGen
Agent
Some (e.g., Tool Agent, Chat Agent)
Many [Optional] (e.g., OpenAI, Pinecone, etc.)
7K (core-only)
+26MB (core-only)
BrainyFlow .ts
Graph
None
None
300
few KB
BrainyFlow .py
Graph
None
None
300
few KB
From there, it's easy to implement all popular design patterns:
☆☆☆ Dummy
A basic chat bot with conversation history
☆☆☆ Dummy
A simple Retrieval-augmented Generation process
☆☆☆ Dummy
A writing workflow that outlines, writes content, and applies styling
☆☆☆ Dummy
A resume qualification processor using map-reduce pattern for batch evaluation
☆☆☆ Dummy
A research agent that can search the web and answer questions
☆☆☆ Dummy
A real-time LLM streaming demo with user interrupt capability
★☆☆ Beginner
A Taboo word game for asynchronous communication between two agents
★☆☆ Beginner
Research agent is getting unreliable... Let's build a supervision process
★☆☆ Beginner
A parallel execution demo that shows 3x speedup
★☆☆ Beginner
Solve complex reasoning problems through Chain-of-Thought
★☆☆ Beginner
A chat bot with short-term and long-term memory
We would like to extend our deepest gratitude to the creators and contributors of the PocketFlow framework, from which BrainyFlow originated as a fork.
We're looking for contributors for all aspects of the project. Whether you're interested in documentation, testing, or implementing features, we'd love your help!
BrainyFlow is provided "as is" without any warranties or guarantees. We do not take responsibility for how the generated output is used, including but not limited to its accuracy, legality, or any potential consequences arising from its use.
Powerful 🦾: Supports everything you love—(), , , and more
The single file in or capture the core abstraction of LLM frameworks: Graph!
handles simple (LLM) tasks with a clear lifecycle (prep
→ exec
→ post
).
connects nodes through Actions (labeled edges), orchestrating execution.
manages shared (global
) and isolated (local
) state, enabling communication between nodes.
autonomously makes decisions based on context.
chains multiple tasks into sequential pipelines.
integrates data retrieval with generation.
splits data tasks into Map and Reduce steps.
formats outputs consistently.
coordinate multiple agents.
And many more available for all levels!
New to BrainyFlow? Check out our guide to build your first flow in no time.
Check out , the fastest way to develop self-coding LLM projects with BrainyFlow!
Get involved by joining our .
BrainyFlow runs on 300 lines of code and your generosity! 💰 ☕ helps keep it minimal, powerful, and dependency-free! 🚀