TonyRainforest

What an agent can do with the context-canopy corpus

YusenZhang0601/context-canopy: Portable, local-first AI agent memory and personal context-switch agents without losing identity, goals, rules, or evidence

• Look up how context-canopy implements agent-memory, agent-skills, ai-agent, with answers cited to file and line.
• Reuse a worked example: the commit “release v1.1.0 with 3-layer BM25F graph search, CJK segmen…” (6 files · JavaScript).
• Answer from context-canopy's real JavaScript source instead of memory (AI, prompts and agents).

• How does context-canopy implement agent-memory?
• What does mcp do in context-canopy?

Search the GitHub repository YusenZhang0601/context-canopy with XERJ (https://hub.xerj.org/corpus/yusenzhang0601--context-canopy).
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/YusenZhang0601/context-canopy context-canopy && git -C context-canopy checkout 6f6616d0bf94c4a84c5d3929579c4ba069b9fab8
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./context-canopy --url http://127.0.0.1:9200 --prefix context-canopy --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 yusenzhang0601--context-canopy · AI, prompts and agents
Related corpora: dunorth595--ai-agent-memory, markdownlint, wosledon/Hetu, dreamforgestudiollc/EMET
AI search and retrieval with XERJ · Case study: reference coding for agents