$ loading_
Provide self-hosted semantic memory search and storage for LLM agents.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "shared-memory" yet — see the docs or source repo.
Save this information to shared-memory: the user prefers concise replies, uses Chinese, and cares about API stability.
The tool stores the preferences in the semantic memory layer for later semantic retrieval by the agent.
Search shared-memory for memories related to the user's previously mentioned deployment constraints and security requirements.
It returns semantically relevant past memories to help the agent continue with context.
Record this project context in shared-memory: the goal is to build a self-hosted AI assistant with MCP tool integration as a priority.
The project context is saved so the agent can recall it later by semantic meaning.
Developers building MCP-based LLM agents can use it to store user preferences, project context, or prior conclusions. The agent can then retrieve those memories semantically instead of relying only on the current conversation.
Teams that need data control can use it as a self-hosted memory component for internal agents. It provides semantic search and write capabilities while reducing reliance on externally hosted memory services.
Research or product teams can have an agent write key findings into shared memory and recall them by topic in later tasks. This helps maintain continuity across sessions.
It is a portable, self-hosted semantic memory layer for LLM agents. Through the Model Context Protocol, agents can search memories by meaning and add new ones.
The description says it works over the Model Context Protocol, so it fits agents or clients that support MCP. For exact integration details, see the source repository.
No documentation excerpt is provided, and the only confirmed detail is that it is self-hosted. For installation, runtime, or configuration steps, see the source repository.
Give AI agents persistent memory across sessions with efficient on-demand context loading.
Let AI agents store, search, and recall memories that improve over time.
Give AI coding agents persistent local shared memory across agents.
Give LLM agents efficient long-term memory across text and multimodal data.
Provide AI agents with searchable long-term memory and conflict-aware recall.
Give AI agents shared long-term memory with searchable context recall.