--- title: Flux Agents: A Python First Framework for Building... description: Flux Agents is a new open-source Python framework for building production-grade agentic AI systems, designed around three core principles:... canonical: https://daily.dev/posts/flux-agents-a-python-first-framework-for-building-agentic-ai-systems-9bmnlnspg twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Flux Agents: A Python First Framework for Building Agentic AI Systems | daily.dev og:description: Flux Agents is a new open-source Python framework for building production-grade agentic AI systems, designed around three core principles:... og:url: https://daily.dev/posts/flux-agents-a-python-first-framework-for-building-agentic-ai-systems-9bmnlnspg og:image: https://api.daily.dev/og/posts/9bmnLNSPG.png og:image:alt: Flux Agents: A Python First Framework for Building Agentic AI Systems og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Flux Agents: A Python First Framework for Building Agentic AI Systems **[Medium](https://daily.dev/sources/medium_js)** · 20 min read · 3 upvotes · 0 comments ## Summary Flux Agents is a new open-source Python framework for building production-grade agentic AI systems, designed around three core principles: provider-agnosticism, async-first execution, and middleware-driven cross-cutting concerns. The author built it after frustration with existing frameworks that treat provider flexibility and async as afterthoughts. Key features include a decorator-based tool system that auto-generates schemas from type hints, agent handoffs for multi-agent coordination, composable middleware for logging/guardrails/retries, session and memory management, streaming responses, and a protocol-based provider architecture supporting OpenAI, Anthropic, and Ollama out of the box. The framework targets production use cases requiring audit trails, observability, and graceful degradation — not just demos. Roadmap includes MCP support, a visual workflow builder, Agent Studio, and enterprise observability tooling. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Flux Agents and how is it different from LangGraph or CrewAI? Flux Agents is an open-source, provider-agnostic, async-first Python framework for building single and multi-agent AI systems. Unlike LangGraph, which models orchestration as explicit graphs, or CrewAI, which uses role-based collaboration, Flux uses a protocol-based provider architecture and middleware pipeline, letting the same agent logic run against OpenAI, Anthropic, or Ollama without code changes. _Developers weighing agent framework tradeoffs can track new entrants like Flux Agents on daily.dev._ ### How do you make a Python AI agent work with multiple LLM providers like OpenAI, Anthropic, and Ollama without rewriting the code? Flux Agents solves this with a Provider Registry where every backend implements the same protocol interface for requests, tool calls, and streaming. An agent is instantiated with a provider object (OpenAIProvider, AnthropicProvider, or OllamaProvider) while the agent's instructions, tools, and logic stay identical, so switching providers is a config change rather than a refactor. _Teams avoiding vendor lock-in in their AI stack can follow provider-agnostic patterns like this on daily.dev._ ### How do I install the Flux Agents Python framework and add provider-specific dependencies? Install the base package with pip install flux-agents, then add provider extras such as pip install flux-agents[openai], flux-agents[anthropic], or flux-agents[ollama], or install everything with flux-agents[all]. The framework requires Python 3.10 or newer and relies on type hints to auto-generate tool schemas for the model. _daily.dev helps Python developers keep up with new agentic frameworks worth evaluating for production._ ## Similar posts on daily.dev - [OpenAgent: The Ultimate Framework for Modular AI Agent Orchestration](https://daily.dev/posts/openagent-the-ultimate-framework-for-modular-ai-agent-orchestration-vnfjn5z5b) · C\# Corner · 1 upvotes · 0 comments - [Flue: the open framework for building AI agents](https://daily.dev/posts/flue-the-open-framework-for-building-ai-agents-weweogaib) · Flavio Copes · 1 upvotes · 0 comments - [Agentic coding finally clicked when I wired it to a kanban board](https://daily.dev/posts/agentic-coding-finally-clicked-when-i-wired-it-to-a-kanban-board-8oagsdeet) · XDA Developers · 1 upvotes · 0 comments - [Community-powered security with AI: an open source framework for security research](https://daily.dev/posts/community-powered-security-with-ai-an-open-source-framework-for-security-research-zvkqecnsc) · GitHub Blog · 0 upvotes · 0 comments --- Tags: [#python](https://daily.dev/tags/python), [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents) [View this post on daily.dev](https://daily.dev/posts/flux-agents-a-python-first-framework-for-building-agentic-ai-systems-9bmnlnspg) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Flux Agents: A Python First Framework for Building Agentic AI Systems","url":"https://daily.dev/posts/flux-agents-a-python-first-framework-for-building-agentic-ai-systems-9bmnlnspg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/flux-agents-a-python-first-framework-for-building-agentic-ai-systems-9bmnlnspg"},"datePublished":"2026-07-23T00:12:07.791Z","dateModified":"2026-09-14T07:38:30.383Z","description":"Flux Agents is a new open-source Python framework for building production-grade agentic AI systems, designed around three core principles:...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/daa6fc0986a93d82a53331e7188a0628?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/daa6fc0986a93d82a53331e7188a0628?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/flux-agents-a-python-first-framework-for-building-agentic-ai-systems-9bmnlnspg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,llm,ai-agents","timeRequired":"PT20M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"Flux Agents: A Python First Framework for Building Agentic AI Systems"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/flux-agents-a-python-first-framework-for-building-agentic-ai-systems-9bmnlnspg#faq","mainEntity":[{"@type":"Question","name":"What is Flux Agents and how is it different from LangGraph or CrewAI?","acceptedAnswer":{"@type":"Answer","text":"Flux Agents is an open-source, provider-agnostic, async-first Python framework for building single and multi-agent AI systems. Unlike LangGraph, which models orchestration as explicit graphs, or CrewAI, which uses role-based collaboration, Flux uses a protocol-based provider architecture and middleware pipeline, letting the same agent logic run against OpenAI, Anthropic, or Ollama without code changes. Developers weighing agent framework tradeoffs can track new entrants like Flux Agents on daily.dev."}},{"@type":"Question","name":"How do you make a Python AI agent work with multiple LLM providers like OpenAI, Anthropic, and Ollama without rewriting the code?","acceptedAnswer":{"@type":"Answer","text":"Flux Agents solves this with a Provider Registry where every backend implements the same protocol interface for requests, tool calls, and streaming. An agent is instantiated with a provider object (OpenAIProvider, AnthropicProvider, or OllamaProvider) while the agent's instructions, tools, and logic stay identical, so switching providers is a config change rather than a refactor. Teams avoiding vendor lock-in in their AI stack can follow provider-agnostic patterns like this on daily.dev."}},{"@type":"Question","name":"How do I install the Flux Agents Python framework and add provider-specific dependencies?","acceptedAnswer":{"@type":"Answer","text":"Install the base package with pip install flux-agents, then add provider extras such as pip install flux-agents[openai], flux-agents[anthropic], or flux-agents[ollama], or install everything with flux-agents[all]. The framework requires Python 3.10 or newer and relies on type hints to auto-generate tool schemas for the model. daily.dev helps Python developers keep up with new agentic frameworks worth evaluating for production."}}]} ```