Redacted excerpt; full evidence withheld.

$ cd <guest-path> && ls -la && cat README.md | head -c 7000 && python3 --version && echo "CDP=$CDP_URL" && curl -sS -m 10 -i "$CDP_URL/json/version"
exit: 0
TS.md`, `GEMINI.md`) already exists, memd copies it to `CLAUDE.md.bak` beside it and appends the memd section to the end; it never overwrites an existing backup. A file that already has the section is left alone, so running `memd init` again changes nothing.

For two conventions memd doesn't write — GitHub Copilot's `.github/copilot-instructions.md` and Cursor's `.cursor/rules/memd.mdc` — plus longer versions of all of the above, see [`contrib/agents/`](contrib/agents/).

### What's agent-agnostic (and what isn't yet)

The core of memd doesn't care which agent or model you use: the memory files are plain markdown, the inbox accepts notes from anything that can write a file, `memd brief` prints to stdout for any tool to consume, and the `curator_cmd` config key lets any LLM command do the distilling. The parts that are currently tool-specific:

*   **Automatic transcript ingestion** understands `claude-code` session logs and `antigravity-cli` databases natively, and digests *any other* CLI's session logs via content sniffing and
[excerpt truncated]