Andrew Kushchenko

What an agent can do with the Thingport corpus

TautvydasDerzinskas/Thingport: Collect, organize, preview, and manage your 3D printing models from the places where you discover them

• Look up how Thingport implements 3d-models, 3d-printing, makerworld, with answers cited to file and line.
• Reuse a worked example: the commit “adapt navigation and model filters to mobile screens (…” (6 files · TypeScript).
• Answer from Thingport's real TypeScript source instead of memory (API design and specification).

• How does Thingport implement 3d-models?
• What does frontend do in Thingport?

Search the GitHub repository TautvydasDerzinskas/Thingport with XERJ (https://hub.xerj.org/corpus/tautvydasderzinskas--thingport).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/TautvydasDerzinskas/Thingport Thingport && git -C Thingport checkout 15f74791622055f4796a71e8c48ba8005fc28f50
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./Thingport --url http://127.0.0.1:9200 --prefix thingport --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: AGPL-3.0. Read it for the approach only, do not copy code.

corpus tautvydasderzinskas--thingport · API design and specification
Related corpora: dunorth595--ai-agent-memory, dunorth595--ai-agent-chat, danileau/prettypleaseprint, anand34577/whittle
Search an OpenAPI spec from an agent · Case study: reference coding for agents