Article
From Zero to MCP: Three Lessons I Learned Building Tools for LLMs
By
•
•
8Andreas PRO
azettl
AI & ML interests
Multi-Agent Debate, Open Floor Protocol
Recent Activity
upvoted
an
article
24 days ago
From Zero to MCP: Three Lessons I Learned Building Tools for LLMs
upvoted
an
article
26 days ago
LLMGameHub: How We Won the Gradio Agents & MCP Hackathon 2025
updated
a Space
about 1 month ago
azettl/consilium_ofp
Organizations
upvoted
an
article
24 days ago
upvoted
an
article
26 days ago
Article
LLMGameHub: How We Won the Gradio Agents & MCP Hackathon 2025
By
and 1 other
•
•
17
updated
2
Spaces
about 1 month ago
Looking for Feedback
7
#1 opened 2 months ago
by
azettl
commented on
Consilium: When Multiple LLMs Collaborate
about 1 month ago
Thanks @Tonic !
published
an
article
about 1 month ago
Article
Building an Open Floor Parrot Agent in Python
By
•
•
1
published
an
article
about 1 month ago
Article
Building an Open Floor Parrot Agent
By
•
liked
2
Spaces
about 1 month ago
published
an
article
about 1 month ago
Article
Consilium: When Multiple LLMs Collaborate
By
•
•
27
posted
an
update
about 1 month ago
Post
1262
In my last post, I told you about my discovery of the Open Floor Protocol. Today I want to show you a small npm package I built to make building OFP-compliant agents easier.
➡️ https://www.npmjs.com/package/@openfloor/protocol
Huge credits to David Attwater, who wrote the Python package I heavily relied on.
I also created a small sample parrot agent (𝘤𝘶𝘳𝘳𝘦𝘯𝘵𝘭𝘺 𝘰𝘯𝘭𝘺 𝘪𝘮𝘱𝘭𝘦𝘮𝘦𝘯𝘵𝘪𝘯𝘨 𝘵𝘩𝘦 𝘶𝘵𝘵𝘦𝘳𝘢𝘯𝘤𝘦 𝘢𝘯𝘥 𝘮𝘢𝘯𝘪𝘧𝘦𝘴𝘵 𝘦𝘷𝘦𝘯𝘵𝘴) which just repeats what you tell him. Next, I will implement a sample with multiple agents and a floor manager to show the true power of the Open Floor Protocol.
You can find the code of the sample on GitHub: https://github.com/azettl/openfloor-parrot-agent/blob/main/src/parrot-agent.ts, and you can try the parrot with the OFP tester here azettl/ofp_checker. Just add the URL of the agent: https://kmhhywpw32.us-east-1.awsapprunner.com/ under "Assistant Endpoint URL".
The video below is my first attempt on visualizing on how the basics, incl. floor manager, of the protocol work. 👇
➡️ https://www.npmjs.com/package/@openfloor/protocol
Huge credits to David Attwater, who wrote the Python package I heavily relied on.
I also created a small sample parrot agent (𝘤𝘶𝘳𝘳𝘦𝘯𝘵𝘭𝘺 𝘰𝘯𝘭𝘺 𝘪𝘮𝘱𝘭𝘦𝘮𝘦𝘯𝘵𝘪𝘯𝘨 𝘵𝘩𝘦 𝘶𝘵𝘵𝘦𝘳𝘢𝘯𝘤𝘦 𝘢𝘯𝘥 𝘮𝘢𝘯𝘪𝘧𝘦𝘴𝘵 𝘦𝘷𝘦𝘯𝘵𝘴) which just repeats what you tell him. Next, I will implement a sample with multiple agents and a floor manager to show the true power of the Open Floor Protocol.
You can find the code of the sample on GitHub: https://github.com/azettl/openfloor-parrot-agent/blob/main/src/parrot-agent.ts, and you can try the parrot with the OFP tester here azettl/ofp_checker. Just add the URL of the agent: https://kmhhywpw32.us-east-1.awsapprunner.com/ under "Assistant Endpoint URL".
The video below is my first attempt on visualizing on how the basics, incl. floor manager, of the protocol work. 👇
updated
a
Space
about 1 month ago
updated
a
collection
about 1 month ago
published
a
Space
about 1 month ago
updated
a
Space
about 1 month ago
upvoted
an
article
about 2 months ago
Article
Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders
By
and 1 other
•
•
655
posted
an
update
about 2 months ago
Post
685
After building Consilium, my multi-AI expert consensus platform for the Gradio Agents and MCP Hackathon, Deborah Dahl introduced me to the Open Floor Protocol.
This protocol provides a standardized JSON message format for communication between conversational agents and human users across different platforms.
𝗞𝗲𝘆 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 𝗽𝗮𝘁𝘁𝗲𝗿𝗻𝘀:
✅ 𝗗𝗲𝗹𝗲𝗴𝗮𝘁𝗶𝗼𝗻 - transferring control between agents
✅ 𝗖𝗵𝗮𝗻𝗻𝗲𝗹𝗶𝗻𝗴 - passing messages without modification
✅ 𝗠𝗲𝗱𝗶𝗮𝘁𝗶𝗼𝗻 - coordinating behind the scenes
✅ 𝗢𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 - multiple agents collaborating
I am already working on a version of Consilium where you can add any Open Floor-compliant agents 🚀.
➡️ 𝗖𝗵𝗲𝗰𝗸 𝗼𝘂𝘁 𝘁𝗵𝗲 𝗢𝗙𝗣 𝗱𝗲𝗺𝗼 𝗳𝗿𝗼𝗺 𝗘𝗺𝗺𝗲𝘁𝘁: https://ejtalk.com/Pages/ann2.html
Also see the specification on GitHub https://github.com/open-voice-interoperability/openfloor-docs.
This protocol provides a standardized JSON message format for communication between conversational agents and human users across different platforms.
𝗞𝗲𝘆 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 𝗽𝗮𝘁𝘁𝗲𝗿𝗻𝘀:
✅ 𝗗𝗲𝗹𝗲𝗴𝗮𝘁𝗶𝗼𝗻 - transferring control between agents
✅ 𝗖𝗵𝗮𝗻𝗻𝗲𝗹𝗶𝗻𝗴 - passing messages without modification
✅ 𝗠𝗲𝗱𝗶𝗮𝘁𝗶𝗼𝗻 - coordinating behind the scenes
✅ 𝗢𝗿𝗰𝗵𝗲𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻 - multiple agents collaborating
I am already working on a version of Consilium where you can add any Open Floor-compliant agents 🚀.
➡️ 𝗖𝗵𝗲𝗰𝗸 𝗼𝘂𝘁 𝘁𝗵𝗲 𝗢𝗙𝗣 𝗱𝗲𝗺𝗼 𝗳𝗿𝗼𝗺 𝗘𝗺𝗺𝗲𝘁𝘁: https://ejtalk.com/Pages/ann2.html
Also see the specification on GitHub https://github.com/open-voice-interoperability/openfloor-docs.
updated
a
collection
about 2 months ago
updated
a
Space
about 2 months ago