Flower Agent runtime
Package agent logic as an AgentApp and run it locally or on SuperGrid. Flower supplies model access, connectors, run state, and the execution runtime.
Open-source AI models, agents, and infrastructure for collaborative AI.
Flower is a full-stack AI research and engineering platform focused on collaborative AI. It brings together open-source models, agent tooling, and federated AI infrastructure, with the aim of enabling organizations to work across distributed data while retaining control of that data. Its ecosystem includes Flower Agent for building and running agentic applications and Flower Hub for discovering, publishing, executing, and verifying federated AI apps.
Package agent logic as an AgentApp and run it locally or on SuperGrid. Flower supplies model access, connectors, run state, and the execution runtime.
Start an agent conversation in a browser without local installation or a model API key, or use the `flwr chat` terminal interface.
Discover, reuse, and publish federated AI applications in a standardized format, helping teams share application logic across the community.
Flower Hub supports execution across heterogeneous environments and decentralized verification of federated AI apps without relying on a centralized trust authority.
Agent applications can run locally or on SuperGrid; the documentation also describes running with a local SuperLink, including with Ollama.
Use browser chat for an initial response, then create a small AgentApp and expand it with conversation context, connector calls, and a bounded tool loop.
Develop and execute AgentApps locally or use a SuperGrid federation as the workspace where runs are executed and visible.
Develop application logic for distributed environments without taking on the infrastructure complexity of coordinating each execution environment.
Publish apps to Flower Hub, discover applications made by others, and build on them using the standardized app format.
Flower Agent is identified as experimental. Its interfaces and behavior may change between releases.
Yes. The browser chat path is described as providing a first response without a local installation or model API key.
The documented options include local execution and execution on SuperGrid. The guides also cover running with a local SuperLink.
A federation is the SuperGrid workspace in which agent runs execute and are visible.
Flower Hub supports discovering, distributing, executing, and decentralized verification of federated AI apps, as well as publishing and signing apps.
Os dados de tráfego são apenas para referência.
flowiseai.com
Open-source platform for visually building AI agents, LLM workflows, and chat applications.
adk.dev
Agent Development Kit (ADK) is an open-source framework for building, evaluating, and deploying conversational and non-conversational AI agents. It supports multi-agent systems, tools, structured workflows, and production runtimes across Python, TypeScript, Go, Java, and Kotlin.
tiledesk.com
Open source, no code platform for building AI agents, automating workflows, and connecting live support.
ainiro.io
An open-source AI development platform for building apps, APIs, and agents in English.
clawapp.saharaai.com
A macOS desktop app for creating, configuring and scheduling OpenClaw agents with hosted or local models.
vendo.run
Vendo is an open-source customization layer that embeds an agent inside software products. It lets customers create views, UI changes, micro-apps, and automations through the product’s API and components while retaining the product’s branding and permission rules.