$ loading_
Provide local-first semantic memory and context recall for MCP agents.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Subconscious" MCP server from askskill: Run: claude mcp add 'io-github-vishaltorc-subconscious-mcp' -- npx -y subconscious-mcp
Use Subconscious to record the following user preferences and project context as searchable memory: the user prefers concise answers; the current project is a local knowledge base assistant; the stack is Python, FastAPI, and SQLite.
The tool stores a set of semantically retrievable memory entries and returns the save result.
Use Subconscious to recall memories most relevant to 'the tech stack of the local knowledge base assistant', prioritizing the most recent and closest matches, then provide a brief summary.
The tool returns relevant memory snippets, similarity or ranking results, and a condensed summary of key information.
Use Subconscious to find and remove outdated memories related to the old stack 'Flask + MySQL', keep the current Python, FastAPI, and SQLite project context, and return change statistics.
The tool removes the specified old memories, preserves valid context, and returns forgetting results with statistics.
Provide persistent local semantic memory for MCP tools to store and search notes.
Let AI agents store, search, and recall memories that improve over time.
Give AI assistants persistent memory, adaptive recall, and graph-based knowledge retrieval.
Manage local-first agent memory with versioning, search, ACLs, and sync.
Store and retrieve agent lessons to improve tasks and avoid repeated mistakes.
Give MCP agents local-first long-term memory without databases or API keys.