$ loading_
Give AI agents persistent graph memory, semantic search, and safety protections.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Mnemosyne" yet — see the docs or source repo.
Store user preferences, project context, and past decisions as retrievable graph memory, and prioritize them in future conversations.
The agent persistently stores and retrieves past information for later responses and decisions.
Search memory for “release risks discussed last time” and return the most relevant nodes and their relationships.
Returns semantically relevant memory results and the relationships between graph nodes.
Check new memory entries for malicious or misleading content before writing them, and block suspicious items from long-term storage.
The system preserves useful memory while reducing the risk of polluted long-term memory.
Developers building MCP-based AI agents can use it to store long-term context, user preferences, and task history so the assistant stays consistent across sessions.
In research or product workflows, teams can use semantic search and wikilink traversal to recover relevant information and connected clues from prior memory.
When an AI agent needs to write long-term memory, its injection protection can help reduce the risk of malicious content contaminating the memory store.
It is an MCP tool that gives AI agents persistent graph-based memory. Known capabilities include semantic search, wikilink traversal, reminders, and injection protection.
It is suitable for AI agent projects that need long-term context, cross-session memory, or knowledge-linked retrieval. Examples include memory-enabled assistants, research agents, or systems needing more stable context management.
The provided material does not include installation steps, runtime dependencies, or key requirements. See the source repository for integration details.
Give AI agents persistent, self-managing memory with recall and forgetting.
Provide persistent memory, semantic search, and unified LLM routing for AI agents.
Give AI agents persistent memory with semantic search and automatic memory management.
Give AI agents local-first memory, retrieval, and spaced learning workflows.
Give AI agents persistent semantic memory with search, decay, and deduplication.
Give AI assistants local-first graph memory with semantic search tools.