About Esme (mente en marcha)
Esme is a local memory system for people who use multiple AI tools and want them to share useful context. Its learned retrieval selects context for each AI, while feedback helps refine what is recalled; memory stays on the user's computer.
Key features
- 01Store facts, decisions, and preferences
- 02Retrieve relevant context with source IDs
- 03Learn from usefulness feedback
- 04Adapt context selection for each AI
- 05Distill recurring people, scenes, and tasks
Use cases
- 01Share personal context across AI clients
- 02Save a decision for later retrieval
- 03Improve recalled context using feedback
MCP support
Esme exposes `recall`, `remember`, and `feedback` as tools through an MCP server, allowing compatible clients to retrieve and update its local memory.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://{esme_host}/mcpclaude mcp add --transport http shiuglen-esme-remoto https://{esme_host}/mcp{"mcpServers":{"shiuglen-esme-remoto":{"type":"http","url":"https://{esme_host}/mcp"}}}Open in Cursor{"servers":{"shiuglen-esme-remoto":{"type":"http","url":"https://{esme_host}/mcp"}}}Open in VS Code{"mcpServers":{"shiuglen-esme-remoto":{"type":"http","url":"https://{esme_host}/mcp"}}}{"mcpServers":{"shiuglen-esme-remoto":{"serverUrl":"https://{esme_host}/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://{esme_host}/mcpAuth requiredTools
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.