Frameworks & Indie.
Open-source agent frameworks and indie projects that let developers build and orchestrate multi-agent systems. Ranked by aggregate score from 3 published community and editorial evaluations. Top of this catalog: LangGraph, AutoGPT, BabyAGI.
7Agents
3Evaluations
0.0Median /10
6Visible now
Showing 1–6 of 6 in Frameworks & IndieCompare mode
Sort by:Aggregate score01
LangGraphLangChain · Open-source framework (free); LangGraph Cloud has usage-based pricing · AutonomousLangGraph is LangChain's stateful agent and multi-agent framework that models agent workflows as directed graphs — enabling complex cycles, human-in-the-loop checkpoints, and persistent state across agent sessions. It has become the go-to framework for enterprise agent applications requiring production-grade reliability, observability, and complex workflow management. LangGraph Cloud offers managed hosting with built-in deployment, scaling, and monitoring.AutonomousComplex setupAny LangChain-compatible model (GPT-4oRelFitEaseCost9.01 reviews02
AutoGPTSignificant Gravitas · Open-source and free to self-host; hosted platform has free and paid tiers · AutonomousAutoGPT was the pioneering autonomous agent project that sparked the 2023 AI agent explosion, demonstrating that LLMs could self-direct toward goals using a loop of thought, action, and memory. With over 170,000 GitHub stars, it remains one of the most starred AI repos ever and introduced concepts like agent memory and tool use that are now standard in the field. Its AutoGPT Platform continues development as both an open-source framework and hosted cloud agent service.AutonomousComplex setupGPT-4oRelFitEaseCost7.41 reviews03BBabyAGIYohei Nakajima · Fully open-source; you pay for your own LLM API keys · BrowserBabyAGI is the lightweight task-driven autonomous agent that inspired a generation of agent developers — using a simple loop of task creation, prioritization, and execution to work toward user-defined goals. Despite its simplicity (the original was 140 lines of Python), it demonstrated that effective goal-directed behavior could emerge from basic LLM loops. The project remains influential as a conceptual reference point, though most production use cases have moved to more mature frameworks.BrowserModerate setupGPT-4 (original); community forks support various modelsRelFitEaseCost0.00 reviews04CChatDevOpenBMB · Open-source research project; you pay for your own OpenAI API keys · BrowserChatDev is a research project from OpenBMB (Tsinghua University) that demonstrates a virtual software company where multiple LLM agents with distinct roles — CEO, CTO, programmer, reviewer, tester — collaborate to build software from a single natural language requirement. It explores how software engineering processes can be fully automated through role-playing agents and structured communication protocols. ChatDev remains an influential research artifact and educational tool for understanding multi-agent systems.BrowserModerate setupGPT-4RelFitEaseCost0.00 reviews05MMetaGPTMetaGPT team · Open-source and free to self-host; you pay for your own LLM API keys · AutonomousMetaGPT is a multi-agent framework that simulates a software company, assigning specialized roles — Product Manager, Architect, Engineer, QA — to different LLM agents that collaborate on software development projects. Its SOP (Standard Operating Procedure) approach reduces hallucinations by structuring inter-agent communication as structured documents rather than freeform chat. MetaGPT is popular in research settings for studying how social structures improve AI agent performance.AutonomousComplex setupGPT-4oRelFitEaseCost0.00 reviews06
SuperAGISuperAGI · Open-source and free to self-host; cloud version has paid tiers · AutonomousSuperAGI is an open-source autonomous agent platform offering a full developer toolset including agent marketplace, tool integrations, vector memory, and a visual agent builder GUI. It aims to be the infrastructure layer for deploying and managing production AI agents with proper monitoring and performance tracking. SuperAGI's marketplace and GUI make it accessible to teams without deep ML expertise who still want customizable autonomous agents.AutonomousComplex setupGPT-4RelFitEaseCost0.00 reviews
LangGraphLangChain · Open-source framework (free); LangGraph Cloud has usage-based pricing · AutonomousLangGraph is LangChain's stateful agent and multi-agent framework that models agent workflows as directed graphs — enabling complex cycles, human-in-the-loop checkpoints, and persistent state across agent sessions. It has become the go-to framework for enterprise agent applications requiring production-grade reliability, observability, and complex workflow management. LangGraph Cloud offers managed hosting with built-in deployment, scaling, and monitoring.AutonomousComplex setupAny LangChain-compatible model (GPT-4oRelFitEaseCost9.01 reviews02AutoGPTSignificant Gravitas · Open-source and free to self-host; hosted platform has free and paid tiers · AutonomousAutoGPT was the pioneering autonomous agent project that sparked the 2023 AI agent explosion, demonstrating that LLMs could self-direct toward goals using a loop of thought, action, and memory. With over 170,000 GitHub stars, it remains one of the most starred AI repos ever and introduced concepts like agent memory and tool use that are now standard in the field. Its AutoGPT Platform continues development as both an open-source framework and hosted cloud agent service.AutonomousComplex setupGPT-4oRelFitEaseCost7.41 reviews03BBabyAGIYohei Nakajima · Fully open-source; you pay for your own LLM API keys · BrowserBabyAGI is the lightweight task-driven autonomous agent that inspired a generation of agent developers — using a simple loop of task creation, prioritization, and execution to work toward user-defined goals. Despite its simplicity (the original was 140 lines of Python), it demonstrated that effective goal-directed behavior could emerge from basic LLM loops. The project remains influential as a conceptual reference point, though most production use cases have moved to more mature frameworks.BrowserModerate setupGPT-4 (original); community forks support various modelsRelFitEaseCost0.00 reviews04CChatDevOpenBMB · Open-source research project; you pay for your own OpenAI API keys · BrowserChatDev is a research project from OpenBMB (Tsinghua University) that demonstrates a virtual software company where multiple LLM agents with distinct roles — CEO, CTO, programmer, reviewer, tester — collaborate to build software from a single natural language requirement. It explores how software engineering processes can be fully automated through role-playing agents and structured communication protocols. ChatDev remains an influential research artifact and educational tool for understanding multi-agent systems.BrowserModerate setupGPT-4RelFitEaseCost0.00 reviews05MMetaGPTMetaGPT team · Open-source and free to self-host; you pay for your own LLM API keys · AutonomousMetaGPT is a multi-agent framework that simulates a software company, assigning specialized roles — Product Manager, Architect, Engineer, QA — to different LLM agents that collaborate on software development projects. Its SOP (Standard Operating Procedure) approach reduces hallucinations by structuring inter-agent communication as structured documents rather than freeform chat. MetaGPT is popular in research settings for studying how social structures improve AI agent performance.AutonomousComplex setupGPT-4oRelFitEaseCost0.00 reviews06SuperAGISuperAGI · Open-source and free to self-host; cloud version has paid tiers · AutonomousSuperAGI is an open-source autonomous agent platform offering a full developer toolset including agent marketplace, tool integrations, vector memory, and a visual agent builder GUI. It aims to be the infrastructure layer for deploying and managing production AI agents with proper monitoring and performance tracking. SuperAGI's marketplace and GUI make it accessible to teams without deep ML expertise who still want customizable autonomous agents.AutonomousComplex setupGPT-4RelFitEaseCost0.00 reviewsCompare ready. Start with the top 3 visible agents.Compare