$ loading_
Store, recall, and search structured memories for autonomous AI agents.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Tsumugi" yet — see the docs or source repo.
Use Tsumugi to store the following project memory: project name is Apollo, tech stack is Next.js, PostgreSQL, and Redis, and the current goal is to finish user login and access control within two weeks. Save it as structured memory and tag it with project, auth, and deadline.
The tool stores a project memory with structured fields and tags for later retrieval and task continuity.
Use Tsumugi to search historical memories related to "payment system architecture decisions." Focus on why we rejected a custom payment gateway, which third-party service we rely on, and the compliance constraints involved. Return the results as a summary.
The tool returns a summary of relevant past memories to quickly restore decision context and key constraints.
Use Tsumugi's recall or dreaming capability to analyze product feedback, bug logs, and user interview memories from the last 30 days. Identify three recurring issue patterns and suggest the next priorities.
The tool synthesizes stored memories into recurring patterns and produces actionable priority recommendations.
Give AI coding agents long-term memory, search, and organization across sessions.
Give LLMs persistent memory to store and retrieve information through MCP.
Build a self-evolving memory graph for coding agents with semantic search.
Give AI coding assistants persistent, conflict-aware memory across projects and sessions.
Store and retrieve project memory for coding assistants via MCP tools.
Give MCP-compatible AI tools four-layer long-term memory for persistent context.