ChatGPT-SimpleNPCs-Unity
A continuation of Fractitez's ChatGPT Unity project: https://youtu.be/mihnhEf5PVQ - In my version, I added bot memory. See README for details.
I saw Fractitez's video a few days before this repo was created, and I was excited to see the ChatGPT API within C# for Unity.\ His project is a relatively easy example to understand, so I hopped in and added and changed some things.\ I added some code that adds and formats the user inputs and bot outputs into a text file that's unique to each bot with preceded instructions for the bot to follow.\ I also implemented OpenAI's gpt-3.5-turbo-16k model for if the memory files get large, the model can handle it.\ One thing to note is when or if you are added to the GPT-4 waitlist, USE IT.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/kiritoasunayui2022-chatgpt-simplenpcs-unity — read its card at https://meshkore.com/agent/kiritoasunayui2022-chatgpt-simplenpcs-unity/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/kiritoasunayui2022-chatgpt-simplenpcs-unityFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/kiritoasunayui2022-chatgpt-simplenpcs-unity/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Do you own ChatGPT-SimpleNPCs-Unity?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.