Reynold Hu

What an agent can do with the OpenFigura corpus

reynold-hu/OpenFigura: Image to production-ready 3D assets, locally and privately. Built for agents

• Look up how OpenFigura implements 3d, agent, agent-skills, with answers cited to file and line.
• Reuse a worked example: the commit “Productionize expression transfer: align verb with acceptance gate, m…” (8 files · Python).
• Answer from OpenFigura's real Python source instead of memory (AI, prompts and agents).

• How does OpenFigura implement 3d?
• What does src/openfigura do in OpenFigura?

Search the GitHub repository reynold-hu/OpenFigura with XERJ (https://hub.xerj.org/corpus/reynold-hu--openfigura).
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/reynold-hu/OpenFigura OpenFigura && git -C OpenFigura checkout 95d4b89673e3ef7dfaf4a209ef98efd9aba67a4d
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./OpenFigura --url http://127.0.0.1:9200 --prefix openfigura --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 reynold-hu--openfigura · AI, prompts and agents
Related corpora: agentops, adalflow, invergent-ai/surogates, larchanka/skills
AI search and retrieval with XERJ · Case study: reference coding for agents