Article
LLMGameHub: How We Won the Gradio Agents & MCP Hackathonย 2025
By
and 1 other
โข
โข
14Andreas PRO
azettl
AI & ML interests
Multi-Agent Debate, Open Floor Protocol
Recent Activity
upvoted
an
article
1 day ago
LLMGameHub: How We Won the Gradio Agents & MCP Hackathonย 2025
updated
a Space
7 days ago
azettl/consilium_ofp
updated
a Space
11 days ago
azettl/ofp_mcp
Organizations
upvoted
an
article
1 day ago
updated
a
Space
7 days ago
updated
a
Space
11 days ago
Looking for Feedback
7
#1 opened about 1 month ago
by
azettl
commented on
Consilium: When Multiple LLMs Collaborate
12 days ago
Thanks @Tonic !
published
an
article
12 days ago
Article
Building an Open Floor Parrot Agent in Python
By
โข
published
an
article
12 days ago
Article
Building an Open Floor Parrot Agent
By
โข
liked
2
Spaces
13 days ago
published
an
article
14 days ago
Article
Consilium: When Multiple LLMs Collaborate
By
โข
โข
18
posted
an
update
15 days ago
Post
1243
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.
โก๏ธ 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 (๐ค๐ถ๐ณ๐ณ๐ฆ๐ฏ๐ต๐ญ๐บ ๐ฐ๐ฏ๐ญ๐บ ๐ช๐ฎ๐ฑ๐ญ๐ฆ๐ฎ๐ฆ๐ฏ๐ต๐ช๐ฏ๐จ ๐ต๐ฉ๐ฆ ๐ถ๐ต๐ต๐ฆ๐ณ๐ข๐ฏ๐ค๐ฆ ๐ข๐ฏ๐ฅ ๐ฎ๐ข๐ฏ๐ช๐ง๐ฆ๐ด๐ต ๐ฆ๐ท๐ฆ๐ฏ๐ต๐ด) 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. ๐
โก๏ธ 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 (๐ค๐ถ๐ณ๐ณ๐ฆ๐ฏ๐ต๐ญ๐บ ๐ฐ๐ฏ๐ญ๐บ ๐ช๐ฎ๐ฑ๐ญ๐ฆ๐ฎ๐ฆ๐ฏ๐ต๐ช๐ฏ๐จ ๐ต๐ฉ๐ฆ ๐ถ๐ต๐ต๐ฆ๐ณ๐ข๐ฏ๐ค๐ฆ ๐ข๐ฏ๐ฅ ๐ฎ๐ข๐ฏ๐ช๐ง๐ฆ๐ด๐ต ๐ฆ๐ท๐ฆ๐ฏ๐ต๐ด) 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. ๐
updated
a
Space
18 days ago
updated
a
collection
19 days ago
published
a
Space
19 days ago
updated
a
Space
19 days ago
upvoted
an
article
21 days ago
Article
Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders
By
and 1 other
โข
โข
617
posted
an
update
22 days ago
Post
681
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.
๐๐ฒ๐ ๐ถ๐ป๐๐ฒ๐ฟ๐ฎ๐ฐ๐๐ถ๐ผ๐ป ๐ฝ๐ฎ๐๐๐ฒ๐ฟ๐ป๐:
โ ๐๐ฒ๐น๐ฒ๐ด๐ฎ๐๐ถ๐ผ๐ป - transferring control between agents
โ ๐๐ต๐ฎ๐ป๐ป๐ฒ๐น๐ถ๐ป๐ด - passing messages without modification
โ ๐ ๐ฒ๐ฑ๐ถ๐ฎ๐๐ถ๐ผ๐ป - coordinating behind the scenes
โ ๐ข๐ฟ๐ฐ๐ต๐ฒ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป - multiple agents collaborating
I am already working on a version of Consilium where you can add any Open Floor-compliant agents ๐.
โก๏ธ ๐๐ต๐ฒ๐ฐ๐ธ ๐ผ๐๐ ๐๐ต๐ฒ ๐ข๐๐ฃ ๐ฑ๐ฒ๐บ๐ผ ๐ณ๐ฟ๐ผ๐บ ๐๐บ๐บ๐ฒ๐๐: 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.
๐๐ฒ๐ ๐ถ๐ป๐๐ฒ๐ฟ๐ฎ๐ฐ๐๐ถ๐ผ๐ป ๐ฝ๐ฎ๐๐๐ฒ๐ฟ๐ป๐:
โ ๐๐ฒ๐น๐ฒ๐ด๐ฎ๐๐ถ๐ผ๐ป - transferring control between agents
โ ๐๐ต๐ฎ๐ป๐ป๐ฒ๐น๐ถ๐ป๐ด - passing messages without modification
โ ๐ ๐ฒ๐ฑ๐ถ๐ฎ๐๐ถ๐ผ๐ป - coordinating behind the scenes
โ ๐ข๐ฟ๐ฐ๐ต๐ฒ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป - multiple agents collaborating
I am already working on a version of Consilium where you can add any Open Floor-compliant agents ๐.
โก๏ธ ๐๐ต๐ฒ๐ฐ๐ธ ๐ผ๐๐ ๐๐ต๐ฒ ๐ข๐๐ฃ ๐ฑ๐ฒ๐บ๐ผ ๐ณ๐ฟ๐ผ๐บ ๐๐บ๐บ๐ฒ๐๐: https://ejtalk.com/Pages/ann2.html
Also see the specification on GitHub https://github.com/open-voice-interoperability/openfloor-docs.
updated
a
collection
26 days ago
updated
2
Spaces
26 days ago