Injects a learned cognitive fingerprint into Claude sessions and lets agents consult you at decision points. The server loads your Phaedo profile (sample included, real one synced from their app via pairing) and provides two operations: style injection fires automatically at session start, and consultation requests return proceed/clarify/escalate/decline signals when an agent hits a judgment call, gated by user-authored deference policies. Everything runs locally over stdio with encrypted on-device storage. Reach for this if you want agents to mirror your communication patterns and decision-making style without rehashing context every time, or to audit agentic choices against a calibrated model of how you'd actually respond.
Phaedo learns how you think — communication style, working style, decision pattern — into a portable, user-owned cognitive fingerprint, and carries it to any AI tool. This repo is the open half of that system:
spec/ — the Phaedo Protocol's machine-readable JSON Schemas (fingerprint
layers, consultation request/response, deference policies, receipts).docs/protocol/ — the protocol spec (v0.1), the MCP binding, and accepted
proposals.mcp/ — the reference MCP server (phaedo-mcp on npm): injects your
fingerprint at session start and answers agent consultations — an agent at a
decision point can ask "would my human proceed here?" and get a calibrated
proceed / clarify / escalate / decline signal (or an honest abstain), gated by
user-authored deference policies, with an encrypted on-device audit trail.npx phaedo-mcp # run the server over stdio
Or wire it into Claude Desktop / Cursor / Claude Code automatically:
npm install -g phaedo-mcp
cd "$(npm root -g)/phaedo-mcp" && npm run setup
Out of the box it serves a sample fingerprint, so every tool works immediately.
Your real fingerprint comes from the Phaedo app — currently in private beta
(phaedo.so) — learned on-device from your actual
usage; pair with npm run pair. See
mcp/README.md for the full guide (pairing, policies, receipts,
the agreement metric).
insufficient_signal, not a confident guess.The learning pipeline that builds fingerprints (conversation capture, on-device extraction models) is Phaedo's proprietary side. This repo is everything a client, agent, or independent producer needs to consume and interoperate: the spec, the schemas, and a complete reference server.
Apache-2.0. The Phaedo name and logo are trademarks; see phaedo.so.