Open Source Alternatives
Open source alternatives to Phidata
Open source alternatives to Phidata, ranked by GitHub stars and freshness.
19 open-source alternatives in the index, ranked by GitHub stars and freshness.
AI
Community
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
Best for: TypeScript developers building AI features in Next.js applications who want lightweight, unopinionated orchestration
MemGPT
Community
Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.
Best for: Developers building conversational or autonomous agents that need to learn and maintain state across extended interactions.
DB GPT
Community
open-source agentic AI data assistant for the next generation of AI + Data products.
Best for: Teams building internal AI data assistants who can maintain Python codebases and want to avoid vendor lock-in
Marvin
Community
an ambient intelligence library
Best for: Developers building context-aware automation and intelligent assistants in Python
Cheshire Cat
Community
AI agent microservice
Best for: Python developers building custom agent-based applications with memory and plugin extensibility
Griptape
Community
Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
Best for: Python developers building custom AI agents and multi-step workflows
Lagent
Community
A lightweight framework for building LLM-based agents
Best for: Developers and researchers who want a minimal, hackable foundation for building custom LLM agents.
AgentsMesh
Community
The AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.
Best for: Development teams seeking to automate and augment their workforce with coordinated AI agents
Autochain
Community
AutoChain: Build lightweight, extensible, and testable LLM Agents
Best for: Developers who need a simple, testable framework for building and evaluating LLM agents in Python.
llm-chain
Community
llm-chain is a powerful rust crate for building chains in large language models allowing you to summarise text and complete complex tasks
Best for: Rust developers building high-performance, multi-step LLM workflows for production systems
ThinkGPT
Community
Agent techniques to augment your LLM and push it beyong its limits
Best for: Python developers who want to add agent-like behaviors to their LLM applications without a heavy framework
Ax
Community
The TypeScript framework for AI development
Best for: TypeScript developers building structured AI workflows and agents
LLM Agents
Community
Build agents which are controlled by LLMs
Best for: Python developers who want a minimal library to prototype LLM-driven agent workflows.
MicroAgent
Community
Agents Capable of Self-Editing Their Prompts / Python Code
Best for: Developers exploring autonomous agent behavior and dynamic self-improvement in Python
llama-agents
Community
Llama Agents + Workflows are an event-driven, async-first, step-based way to control the execution flow of AI applications like agents.
Best for: Developers building custom agent orchestration with async workflows
Funcchain
Community
⛓️ build cognitive systems, pythonic
Best for: Developers prototyping cognitive systems in Python who want a simple orchestration layer
Instrukt
Community
Integrated AI environment in the terminal. Build, test and instruct agents.
Best for: Developers who want a terminal-native environment for prototyping and testing AI agents
bondai
Community
BondAI is an open-source tool for developing AI Agent Systems. BondAI handles the implementation complexities including memory/context management, error handling, vector/semantic s
Best for: Python developers who want a lightweight, open-source framework to build AI agents without managing low-level infrastructure.
Transformers Agents
Community
Provides a natural language API on top of transformers
Best for: Developers building natural language interfaces over existing transformer models