imcreazy

What an agent can do with the DeepSeek-Reasonix corpus

esengine/DeepSeek-Reasonix: A reliable coding agent for complex software engineering tasks

• Look up how DeepSeek-Reasonix implements agent, agent-framework, deepseek, with answers cited to file and line.
• Reuse a worked example: the commit “keep the conversations 1.x had archived archived” (5 files · Go).
• Answer from DeepSeek-Reasonix's real Go source instead of memory (AI, prompts and agents).

• Where does DeepSeek-Reasonix handle “keep the conversations 1.x had archived archived”?
• How does DeepSeek-Reasonix implement agent?
• What does internal/state do in DeepSeek-Reasonix?

Search the GitHub repository esengine/DeepSeek-Reasonix with XERJ (https://hub.xerj.org/corpus/esengine--deepseek-reasonix).
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/esengine/DeepSeek-Reasonix DeepSeek-Reasonix && git -C DeepSeek-Reasonix checkout 67e3ff51b4258d024d317ef2b7db8b3a31940afa
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./DeepSeek-Reasonix --url http://127.0.0.1:9200 --prefix deepseek-reasonix --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: MIT. Keep the copyright notice and credit the authors.

corpus esengine--deepseek-reasonix · AI, prompts and agents
Related corpora: gorilla, haystack, Marco-Cricchio/moh, csr1010/wappy-kit
AI search and retrieval with XERJ · Case study: reference coding for agents