MemPalace is a local-first AI memory system that stores conversation history verbatim and retrieves relevant passages through semantic search. It is for AI-agent users who want searchable, structured memory on their own machine, with a replaceable retrieval backend.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/mempalace/mempalace/mempalace-initgit clone --depth 1 https://github.com/MemPalace/mempalaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/mempalace/mempalace/mempalace-init)<a href="https://agentmods.dev/commands/mempalace/mempalace/mempalace-init"><img src="https://agentmods.dev/badge/commands/mempalace/mempalace/mempalace-init.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00026 | $0.00162 |
| Opus 5 | $0.00013 | $0.00081 |
| Sonnet 5 | $0.00005 | $0.00032 |
| Haiku 4.5 | $0.00003 | $0.00016 |
Grade A, and why
mempalace-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Invoke the mempalace skill from this plugin and run the init instructions, then follow them.
Concretely: run mempalace instructions init in a terminal, then carry out the steps it prints.
Cursor-specific extras after init:
- The
mempalace-mcpserver is already auto-registered by this plugin — no manualmcp.jsonedit needed. - For automatic background saves and session-start memory recall, also run
hooks/cursor/install.sh --scope userfrom a cloned MemPalace repo. Seewebsite/guide/cursor-hooks.mdfor the walkthrough.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 13 lines · 26 tokens per session scan A 2e48522ea628
mempalace-init is a command published in the GitHub repository MemPalace/mempalace (58,778 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 162 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
remember
Extract and save important information from this conversation to ContextFS long-term memory.
recall
Search ContextFS memory for relevant context based on the current task or query.
sync
Sync local memories with ContextFS Cloud for backup and cross-device access.
ingest
Ingest source material into an active wiki. Accepts URLs, file paths, PDFs, freeform text, or processes the inbox. Supports tweets via Grok MCP.
compact-prep
Ask the agent to prepare for conversation compaction by updating any relevant state and providing guidance for the compaction agent and to kick off the session there after.
fire-reflect
After any failure (debug resolution, test failure, approach rotation, stalled loop), capture what was tried, why it failed, and what actually worked as a persistent reflection. Future sessions search these before investigating.