# AI use cases for MemPalace (MemPalace/mempalace) Repo: [MemPalace/mempalace](https://github.com/MemPalace/mempalace) | Use cases: 3 | Page: https://dedupedai.com/use-cases/mempalace-mempalace/ MemPalace is a local-first AI memory system. It stores your conversation history as verbatim text and retrieves it with semantic search, without summarizing or paraphrasing. People and projects become wings, topics become rooms and original content lives in drawers, so searches can be scoped. ChromaDB is the default backend, the retrieval layer is pluggable, and it ships a CLI, an MCP server, a Docker image and skills for coding agents. Nothing leaves your machine unless you opt in. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Give Claude Code searchable memory of your past sessions: https://dedupedai.com/use-cases/mempalace-mempalace/give-claude-code-searchable-memory-of-past-sessions/ - Run a Docker MCP server for Claude Code memory: https://dedupedai.com/use-cases/mempalace-mempalace/run-mempalace-as-a-docker-mcp-server/ - Let your coding agent install agent memory through skills: https://dedupedai.com/use-cases/mempalace-mempalace/let-your-coding-agent-install-mempalace-with-skills/ ## How to give Claude Code searchable memory of your past sessions with MemPalace Repo: [MemPalace/mempalace](https://github.com/MemPalace/mempalace) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README Install the MemPalace CLI, mine your Claude Code transcripts and project files into a local palace, then search them and load context into a new session. **Who it is for:** A developer who keeps re-explaining past decisions to Claude Code because each session starts from zero. **The problem:** Old Claude Code sessions are hard to search, and the README warns they expire in 30 days without auto-save hooks wired. **The outcome:** A local palace of verbatim sessions and project files you can search in plain language, plus a wake-up command that loads context for a new session. ### Steps 1. Run `uv tool install mempalace` to put the MemPalace CLI in an isolated environment on your PATH (or `pipx install mempalace`) 2. Run `mempalace init ~/projects/myapp` with the path to your own project 3. Run `mempalace mine ~/projects/myapp` to mine the project files into the palace 4. Run `mempalace mine ~/.claude/projects/ --mode convos` to mine your Claude Code sessions (scope with --wing per project) 5. Run `mempalace search "why did we switch to GraphQL"` with your own question to find the original conversation 6. Run `mempalace wake-up` to load context for a new session 7. Run `mempalace audit` to score how well organized the palace is (read-only) ### Prompt to paste into your agent ```text Install MemPalace/mempalace with `uv tool install mempalace`, run `mempalace init` on this project, then mine my Claude Code sessions with `mempalace mine ~/.claude/projects/ --mode convos`. Before answering any question about past decisions in this repo, run `mempalace search` with the question and quote the matching original text. Do not delete or move any transcript files. ``` ### Caveat The palace holds your full transcripts verbatim, so keep it on a disk you trust. The README points to its Claude Code retention setup checklist for wiring the auto-save hooks and backing up existing JSONL transcripts. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mempalace-mempalace/give-claude-code-searchable-memory-of-past-sessions/ ## How to run a Docker MCP server for Claude Code memory with MemPalace Repo: [MemPalace/mempalace](https://github.com/MemPalace/mempalace) | Difficulty: Intermediate | Time: 25 minutes | Basis: From the README Pull the multi-arch MemPalace image and wire it into an MCP client as a stdio server, with the palace persisted in a Docker volume. **Who it is for:** A developer who wants agent memory over MCP without installing a local Python toolchain. **The problem:** Installing chromadb, numpy and grpcio into a global Python can conflict with other tools, and some Pythons block it with PEP 668 errors. **The outcome:** An MCP server your agent can call for palace reads and writes, with the palace, config and embedding model kept under /data in a named volume. ### Steps 1. Run `docker pull ghcr.io/mempalace/mempalace:latest` (multi-arch, runs natively on Apple Silicon) 2. Start the MCP server over stdio with `docker run -i --rm -v mempalace-data:/data ghcr.io/mempalace/mempalace` (keep the -i flag, JSON-RPC needs stdin) 3. Add a MemPalace entry under mcpServers in your MCP client config with command docker and the same run arguments, mounting your .claude/projects folder read-only at /transcripts 4. Use a real absolute path for the transcripts mount, because ~ and $HOME are not expanded by every MCP client 5. Test retrieval from the CLI with `docker run --rm -v mempalace-data:/data ghcr.io/mempalace/mempalace search "why GraphQL"` ### Prompt to paste into your agent ```text Set up MemPalace/mempalace as a stdio MCP server for Claude Code using the Docker image: run `docker pull ghcr.io/mempalace/mempalace:latest`, then add a mempalace entry to my MCP config that runs the image with -i, the mempalace-data volume on /data and my Claude Code projects folder mounted read-only at /transcripts, using an absolute path. Show me the config before saving it. ``` ### Caveat The first command that needs embeddings downloads the model into /data (about 80 MB for minilm, about 300 MB for embeddinggemma), so the first call is slow and needs network. On Linux the image runs as uid 1000, so a 0700 mounted folder fails with a PermissionError. Risk, remote script: This pulls and runs a container image from ghcr.io; the README warns about impostor sites, so pull only the official ghcr.io/mempalace image. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mempalace-mempalace/run-mempalace-as-a-docker-mcp-server/ ## How to let your coding agent install agent memory through skills with MemPalace Repo: [MemPalace/mempalace](https://github.com/MemPalace/mempalace) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Add the MemPalace skills, then have your coding agent detect your system, install the package, configure MCP and verify the connection. **Who it is for:** A developer who wants agent memory working without reading every install option. **The problem:** Choosing between uv, pipx, pip, Docker and MCP config by hand is easy to get wrong. **The outcome:** A working MemPalace install with MCP configured, set up as a private local palace, a shared-brain hub or a client of an existing hub. ### Steps 1. Run `npx skills add MemPalace/mempalace` to install the MemPalace skills 2. Ask your coding agent to set up MemPalace; the MemPalace skill handles guided installation and operations 3. Answer the agent's question: a private local palace, a shared-brain hub, or a client connected to an existing hub 4. Let the agent install the Python package, configure MCP and verify the live connection 5. Use the mempalace-recall skill for search-before-answer recall, and mempalace-task for logstream delegation ### Prompt to paste into your agent ```text I ran `npx skills add MemPalace/mempalace`. Use the mempalace skill to set up MemPalace as a private local palace on this machine: detect my system, install the package with uv tool if available, configure MCP and verify the live connection. Tell me every system change before you make it, and leave weekly release checks disabled. ``` ### Caveat The README notes that installing a skill does not by itself install the MemPalace CLI or MCP server; the setup skill guides the agent through those changes. Risk, remote script: npx fetches and installs the skills from the internet and the agent then makes system changes, so review each change it proposes. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mempalace-mempalace/let-your-coding-agent-install-mempalace-with-skills/