Jingkun Zhuang

What an agent can do with the agent-desk corpus

dylan-murray/agent-desk: Local agent development workspace with coordinators, terminals, task automation, and annotation feedback

• Look up how agent-desk implements agent-orchestration, agentic-coding, ai-agents, with answers cited to file and line.
• Reuse a worked example: the commit “Preserve desktop sessions on quit and refine native controls” (15 files · Python, Objective-C).
• Answer from agent-desk's real Python source instead of memory (AI, prompts and agents).

• Where does agent-desk handle “Preserve desktop sessions on quit and refine native controls”?
• How does agent-desk implement agent-orchestration?
• What does tests do in agent-desk?

Search the GitHub repository dylan-murray/agent-desk with XERJ (https://hub.xerj.org/corpus/dylan-murray--agent-desk).
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/dylan-murray/agent-desk agent-desk && git -C agent-desk checkout c925e6d140f63232b98ca068ebea62ee63458de7
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./agent-desk --url http://127.0.0.1:9200 --prefix agent-desk --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: Apache-2.0. Keep the copyright notice and credit the authors.

corpus dylan-murray--agent-desk · AI, prompts and agents
Related corpora: texio, vanguard-context-burn, dagoSte/squadra, erickb336/sage
AI search and retrieval with XERJ · Case study: reference coding for agents