$ loading_
Build, capture, and search a persistent personal knowledge memory in Markdown.
This tool is described as a persistent memory system using plain Markdown in a local git repository, with no required secrets and no declared remote endpoints; no explicit high-risk red flags are evident from the provided materials. Caution is still warranted because it has normal MCP capabilities for local code execution and local data read/write, while the project comes from a third-party registry with low adoption and unknown maintenance status.
The materials explicitly state that no secrets or environment variables are required, and no handling of tokens, API keys, or account credentials is described; based on the available facts, credential exposure or abuse risk appears low.
No remote endpoint is declared, and the description only mentions local Markdown and a local git repository; the materials do not indicate that user data is sent to network services.
The objective checks mark this tool as executes-code, indicating it can run code/processes locally; this is a normal MCP capability, but its runtime environment should still be constrained and its actual system interactions verified.
The description says it persists, reads, searches, and captures memories in a local git repository, implying at least local file read/write access; no extra data privileges beyond the stated function are evident, but the accessed paths should be confirmed to be limited to a dedicated directory.
An open-source repository is available for review, which is a positive factor; however, the license is unspecified, community adoption is 0 stars, maintenance status is unknown, and the source is a third-party registry, so supply-chain trust is only moderate and source/dependency review is advisable before use.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "memory-wiki" yet — see the docs or source repo.
Turn the following meeting content into short-term memories for memory-wiki, extracting decisions, action items, and risks, and output in Markdown: ...
A well-structured Markdown note with conclusions, assignments, and follow-up items.
Based on the existing content in memory-wiki, find past notes about 'user interviews' and summarize key findings, recurring issues, and reusable conclusions.
A cross-note summary listing relevant sources and distilled insights.
Organize my recent scattered ideas into memory-wiki, create Markdown entries by topic, and add backlinks and short summaries: ...
Draft knowledge entries organized by topic, with category suggestions, relationships, and summaries.
Add per-repo persistent memory with versioned retrieval for Claude Code.
Manage persistent AI memories with tagging, search, retrieval, and trigger-based recall.
Enable persistent memory across Claude Code sessions for preferences, notes, and skills.
Provide local-first shared memory, auditing, and sync across AI clients.
Give AI agents persistent, searchable structured memory and bidirectional knowledge sync.
Provide durable local memory for Codex and other MCP-enabled agents.