Search

More Filters

Show More
Add Listing
Go Back

agentsflow

0
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Agentsflow is a web-based tool to easily create, connect and run autonomous autogen AI agents from a streamlined interface. It provides a visual flow editor where users can add agents, connect them, see which agent is running and interact with each agent at runtime. The project targets both beginners who want an approachable way to compose agent-based software and more advanced users who want tooling to explore complex agent interactions. The repository includes instructions to run the app locally using git, nodejs, python 3.11 and poetry and exposes a development server and a production UI reachable at localhost:4200. The project is in early active development and integrates with Microsoft autogen for agent functionality. The codebase is GPLv3 licensed and invites contributions via GitHub issues, contribution guidelines and a community Discord.

Links

Stars
327
Language
App URL
https://github.com/jaemil/agentsflow
Github Repository
https://github.com/jaemil/agentsflow/blob/main/README.md

Categorization

App Details

Features
Implemented integrations and UI primitives include websockets to the autogen agent, support for letting agents execute code, a simple HTML websocket client, a nextjs frontend and use of react-flow to visualize flows. The UI supports drag-and-drop to add agents to a flow and runtime interaction to observe and control running agents. The repository provides npm scripts to install and run the application as well as a development server command. Roadmap items noted in the README include adding a vector database, agent and global settings (API key and model), the ability to save and export custom agents and flows, group chat and multimodal agents, export to Python scripts and a Docker Compose quickstart. Documentation and feature requests are tracked via GitHub issues.
Use Cases
Agentsflow lowers the barrier to building multi-agent systems by providing a visual, runnable environment that makes agent topology and activity explicit. Beginners can prototype agent interactions without wiring low-level infrastructure while advanced users gain a sandbox to iterate on agent behaviors, websocket communication and code execution inside agents. The local developer workflow (git, nodejs, python, poetry) enables rapid testing and modification. Roadmap items such as export/import, vector DB support, agent settings and Docker Compose aim to broaden deployment and persistence options. Community channels and contribution guidelines help teams and individuals collaborate on new agents, flows and integrations. The GPLv3 license clarifies reuse and contribution expectations.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

yutu

0 (0 review)
listing image

cyber-doctor

0 (0 review)
listing image

vibevideo-mcp

0 (0 review)
listing image

xpert

0 (0 review)
listing image

Curie

0 (0 review)

Featured Listings

Tags

Please fill the required fields*