memorylake-ai/memorylake-harness

README 摘要

memorylake-harness Client-side harnesses that connect coding agents to Memory Lake — cross-device long-term memory. (Two deployments, separate accounts: memorylake.ai international, memorylake.cn China; the CLI defaults to the international endpoint.) Harness Client Status claude-plugin/ Claude Code working — recall on read, sync on write, session status codex-plugin/ Codex working — recall skill, per-turn memory sync, session status dsh-plugin/ DeepSeek Harness (dsh) working — memory tools, prompt guidance, session status; published as @memorylake/dsh-plugin All harnesses share one identity and data tree ( /.memorylake/harness/ ): configure once, use from every client. Claude Code See claude-plugin/README.md for configuration, privacy notes, and design rationale. Codex The last line is asked inside a Codex session, after trusting the hooks via /hooks . See codex-plugin/README.md . DeepSeek Harness (dsh) The last line is typed in a session; machines already set up for Claude Code or Codex can skip it. See dsh-plugin/README.md .

分类