Persome

Local-first Personal Model Runtime for macOS

View the Project on GitHub Persome-ai/persome-core

MCP

Persome exposes local capture context, durable personal memory, model structure, and explicit correction through the Model Context Protocol. MCP runs either in the daemon over streamable HTTP or as a per-client stdio process.

Start

persome start
# http://127.0.0.1:8742/mcp

# or
persome mcp

Example stdio client configuration:

{
  "mcpServers": {
    "persome": {
      "command": "persome",
      "args": ["mcp"]
    }
  }
}

Core tools

Tool Purpose
list_memories List durable Markdown memory files.
read_memory Read one memory file with time, tag, and tail filters.
search Search durable memory with BM25 and optional dense retrieval.
read_receipt Resolve a memory entry to its provenance.
recent_activity Read recent durable event entries.
behavior_patterns Read modeled behavioral patterns and their support.
get_model_snapshot Return the versioned Point/Line/Face/Volume/Root model snapshot.
entity_graph Read the entity/relation graph; retained as a compatibility model view.
verify_fact Check a claim against current and superseded memory.
remember Append an explicit, auditable memory.
correct_memory Supersede or revoke memory through the correction workflow.

Capture and state tools

Tool Purpose
current_context Return recent capture headlines, full text, and timeline blocks.
search_captures Search the local capture index.
read_recent_capture Read an exact returned file_stem or nearest recent capture, with screenshot opt-in.
attention_trajectory Read the derived attention path used by state formation.
get_schema Return the Markdown memory schema.

Transport

[mcp]
auto_start = true
transport = "streamable-http"
host = "127.0.0.1"
port = 8742

Security and privacy

The same loopback ASGI app serves /model and the Chat REST routes. The Runtime does not ship a browser Chat page; persome chat is its interactive client.