Solitaire for Agents provides identity infrastructure for AI agents, enabling them to learn user preferences and improve collaboration over time through a dynamic memory system.
From the registry: Identity infrastructure for AI agents. Evolving persona, session continuity, self-tuning retrieval.

$ git clone https://github.com/PRDicta/Solitaire-for-Agents.git && cd Solitaire-for-Agents && pip install -e .https://github.com/PRDicta/Solitaire-for-AgentsPlease install the `solitaire` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.10+** — Python 3.10 or later required (https://www.python.org)
- **Clone and install** — Clone the repo and install Run: `git clone https://github.com/PRDicta/Solitaire-for-Agents.git && cd Solitaire-for-Agents && pip install -e .` (https://github.com/PRDicta/Solitaire-for-Agents)
Canonical MCP server config (stdio transport):
- command: `python`
- args: ["-m","solitaire.mcp"]
- optional environment variables:
- `SOLITAIRE_WORKSPACE`: Path to persistent workspace directory for storing memory data (example: `/path/to/workspace`)
Note: Identity infrastructure for AI agents (not a card game). Behavioral continuity, persona compilation, self-correcting memory. Local-first with SQLite. Recommended to use as Claude Code SKILL rather than standalone MCP. Install plugin: claude plugin marketplace add giancarloerra/socraticode.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.SOLITAIRE_WORKSPACErequiredPath on disk for persistent workspace directory.AI Agents Framework with Self Reflection and MCP support