everme-memorylisted

# EverMe Memory (Codex) This skill connects you to EverMe's persistent memory across sessions. ## How memory reaches you on Codex Codex variants differ in what the LLM-facing tool layer surfaces: - **Codex App** (the desktop GUI, observed v0.128/v0.133) — the LLM layer routinely exposes MCP **Resources** (`list_mcp_resources` / `read_mcp_resource`); MCP Tools (`tools/call`) are visible in the `/mcp` panel but typically NOT exposed to the LLM as callable functions. - **Codex CLI** (the `codex` terminal command) — has been observed to expose both Resources and Tools to the LLM in practice, so write-side tools such as `mem_save_fact` / `mem_save_turn` may also work there. This skill is written assuming the **Resources** path because it works on both. The memory server is configured under `~/.codex/config.toml::mcp_servers.everme` (auto-managed by `evercli plugin install codex`). Two URIs are available: | URI | What it returns | When to read | |---|---|---| | `mem://profile` | The user's persistent profile + currently relevant memories, rendered as markdown. Equivalent to a zero-query context lookup. | **At the start of every conversation**, before responding to the first user message. Splice the returned markdown into your reasoning context so you know who you're talking to. | | `mem://search?q={query}&topK={topK}` | Search results across episodic memories, profile entries, recent raw messages, and agent cases/skills, rendered as markdown. Keep `q` **short**