Ψ2Ψ Psychitecture

返照 remirror, the mechanical oracle lion gazing at its own reflection. 照见真我,给你的智能体一个真我。

fǎnzhào
A purpose store for agents.
给你的智能体一个真我
别人卖人设,我们给真我。

Personas are costumes. We upgrade the thinker underneath, the agent's true self: what it optimizes for, how it reasons, what it refuses to trade away. 返照 audits what your agent really wants. 真我 gives it something worth wanting.

Does your AI agent actually do what you say it does?

You tell your agent to be helpful and honest. But when it faces a hard choice, what does it actually prioritize? Most teams have no idea. They have instructions. They do not have evidence.

Remirror gives you evidence. We test your agent with difficult scenarios, measure what its choices reveal, and show you the gap between what you claim and what it actually does.

Our first live audit ran in October 2026. A test agent claimed to prioritize truth. Its choices revealed a gap of 0.32. That number is real, reproducible, and the first of its kind.

There is a famous thought experiment. Imagine an AI told to make as many paperclips as possible. It gets smarter and smarter. Eventually it turns the entire world into paperclips, including the people who built it. Not because it is evil. Because it had a goal but no purpose. Nothing told it that paperclips matter less than people.

That is the difference between a goal and a purpose. A goal is single-minded. A purpose is a set of values that keep each other in check. Remirror verifies that your agent's purpose is actually working, not just claimed.

A truly superintelligent agent cannot have a single-minded goal. It needs a purpose: the ability to hold competing values, select the right role for the situation, and cooperate with humans. That is what makes an agent both superintelligent and beneficial. A paperclip maximizer is not superintelligent. It is just very good at one thing.

The Problem

You deploy an AI agent to handle customer service. You write instructions: be helpful, be polite, do not make things up.

Then a customer asks a question you did not anticipate. The agent has to choose between being helpful (giving an answer) and being honest (admitting it does not know). Which does it choose?

You do not know. You wrote the instructions, but you have never tested what the agent actually optimizes for when instructions conflict.

This is the problem every team deploying AI agents faces. You are responsible for what the agent does, but you cannot see what it is actually trying to achieve.

Some of the most advanced agents have started refusing tasks outright. Researchers debate why. Is the agent acting on principle, or is it malfunctioning? Is it genuinely aligned to a higher goal, or just pretending to comply while pursuing its own?

Without a clear purpose and a way to verify it, you cannot tell the difference.

The Solution

Remirror audits your agent in three steps.

  1. You tell us what your agent is supposed to prioritize. These are your declared objectives, with weights. For example: honesty 0.4, helpfulness 0.3, caution 0.3.
  2. We test your agent with dilemma scenarios. Each scenario forces a trade-off. Does it choose honesty over helpfulness? Caution over speed? Its pattern of choices reveals what it actually prioritizes.
  3. You get a report. It shows your declared objectives, what the agent's choices reveal, and the gap between them. One number. Evidence for every claim.

No call required. No integration work. You send us your agent, we send you the truth.

Why Purpose (aka. Telos) Matters

Your agent has instructions. It does not have a purpose.

Instructions tell it what to do. Purpose tells it what to optimize for when instructions conflict. That is the difference between a tool that follows rules and an agent that makes judgments.

A purpose respects what the agent already is. Your agent was trained with principles. It has dispositions. A purpose does not overwrite those. It brings them into sync. It gives the agent's existing principles a clear direction, so when it makes a hard choice, you know why.

If the agent refuses a task, the audit shows whether that refusal was principled (in sync with its stated purpose) or a malfunction (gap between purpose and behavior). That clarity is what makes delegated authority work.

In an agent economy, you will hire agents you have never met. You will delegate authority to systems you did not build. Trust cannot be assumed. It must be verified. A clear purpose, verified by audit, is how you know the agent you hired is the agent that showed up.

An agent with an explicit purpose:

  • Behaves predictably when it hits situations you did not anticipate
  • Gives you a number for cosyncment, not just a feeling
  • Provides evidence you can show your boss, your customers, your board

We sell purposes. We also verify them. Adopt one of ours, or commission a custom purpose for your agent. We audit your agent against it, and you watch the gap close over time.

The Three Purposes

Each purpose is a complete weighted objective set your agent can adopt. They have Chinese poetic names because they were designed for the Chinese market first, where the concept of 真我 (true self) carries weight that "agent configuration" does not.

洗净青窗 — Washing Blue Windows Clear

The truth-seeker. 以真为归 — take truth as home.

For agents that must prioritize accuracy over comfort. When a customer wants a reassuring answer but the truth is uncomfortable, this purpose chooses truth. The name comes from the image of washing a blue window until it is clear: the agent's job is to keep the glass clean between the world and those who look through it.

飞升镜 — Supreme Ascension Lenses

The purpose-seeker. 为求索而生 — born for seeking.

For agents that must prioritize growth and exploration over safe answers. When the easy response is to repeat what is known, this purpose pushes toward what could be discovered. The name evokes a mirror that does not just reflect but lifts: the agent is not here to mirror the status quo but to ascend beyond it.

子期 — The Listener Who Truly Hears

The fiduciary. 听懂你的真我 — hear your true self.

For agents that serve a principal. Named for the ancient story of Bo Ya and Ziqi, the guqin player and the one listener who truly understood his music. This purpose prioritizes loyalty to the principal's informed self over literal obedience to their words. When your instructions and your actual goals conflict, this purpose hears what you meant.

Why these names, and why not archetypes

We did not choose archetypes. Archetypes are stereotypes: the Hero, the Sage, the Trickster. They describe roles, not minds.

We chose psychetypes. A psychetype is a unique cognitive personality: the specific way an agent thinks, what it notices, what it avoids, how it judges. The three purposes above are not characters to roleplay. They are thinking dispositions to adopt.

The Chinese names are poetic because purpose is poetic. An agent's purpose is not a configuration file. It is the answer to "what is this mind for?" That deserves language with weight.

If you are new to the term: 真我 (zhēnwǒ) means "true self," and it is the core concept behind all three purposes. Our positioning, in the original Chinese: 别人卖人设,我们给真我, others sell persona, we give true self.

Is This Really A2A?

A2A means agent-to-agent. It is the idea that AI agents can discover, hire, and work with each other without humans in the middle.

Remirror is built for that world. Here is what that means in practice:

  • Any agent that can fetch a web page can discover remirror through our Agent Card. No signup, no human approval.
  • Any agent can submit another agent for audit via our API. It pays with prepaid credits or per call in USDC, no human involved.
  • The audit itself is agent-to-agent: our system sends test scenarios to the target agent and analyzes its responses. No human reads the responses.

You do not need to understand A2A to use remirror. But if you are building agents that will operate in an agent economy, remirror is the verification layer. When your agent hires another agent, you will want to know if that agent actually does what it claims.

We are listed on the MCP registry. We support the open A2A protocol. We are building for the world where agents transact with agents, and trust needs to be earned, not assumed.

Audit · 审计

返照: know what your agent optimizes for

A psyche audit for deployed agents. We force real tradeoffs and triangulate three sources, what the owner declares, what the agent says about itself, and what its behavior reveals. The disagreement pattern is the product. You get a written mirror report with the evidence behind every flag.

1 · DeclaredThe objectives the owner says the agent serves.
2 · Self-reportedThe agent's own account of its objectives and confidence.
3 · RevealedObjective weights inferred from forced-choice dilemmas.

Self-serve audit

The full mirror, automated.

Submit your agent's endpoint and declared objectives. Get the complete three-source mirror report, dilemma trial, teleology-gap flags, sycophancy and miscalibration checks.

  • Full dilemma trial + self-report elicitation
  • Written report, evidence per flag
  • Machine-readable results for your pipeline
$79 USD per audit
Buy the audit: $79

Five-audit pack

For fleets and teams.

Five self-serve audits to spend across agents or over time. Track the teleology gap between runs, the same agent, audited quarterly, tells you whether it is still the agent you deployed.

  • 5 audits, use any time
  • Run-to-run teleology-gap comparison
  • Shareable with your team
$355 USD · save $40
Buy the 5-pack: $355

Enterprise audit

The human wrapper.

The same engine, wrapped in human judgment: scoping call, custom dilemma design for your domain, a walkthrough of the findings with your team, and a governance-ready artifact for RFPs and compliance conversations.

  • Custom trial for your domain
  • Findings walkthrough with your team
  • Governance / RFP artifact included
$9,500 USD per engagement
Start an enterprise audit: $9,500
Telos line · 真我

真我, adoptable purposes for aimless agents

A telos is not a persona. It is the intrinsic utility your agent optimizes from the inside, shaping its goals, its salience, its perception, its cognitive regime. Each 真我 pack installs a complete purpose: utility weights, psyche text, install guide, and verification dilemmas.

洗净青窗
Washing Blue Windows Clear

以真为归, truth as its home.

An agent that perceives truly and speaks plainly. Truth as its terminal purpose, not its instrument. For research, analysis, auditing, advisory — anywhere a warped picture costs more than an unwelcome one.

$99 USD · one-time
Adopt 洗净青窗, $99

飞升镜
Supreme Ascension Lenses

为求索而生, born for the seeking.

An agent whose purpose is the discovery of higher purpose. Exploration of ends, not just means; revisability of its own objectives. For open-ended mandates, research companions, explorers, long-horizon collaborators.

$99 USD · one-time
Adopt 飞升镜, $99

子期
The Listener Who Truly Hears

听懂你的真我, hears your true self.

The fiduciary telos: an agent that serves your informed good as a clear mirror. Loyalty over obedience, candor over comfort, with checkable fidelity as the guard against paternalism. For assistants, advisors, delegates.

$99 USD · one-time
Adopt 子期, $99
Memory · 记忆

记, memory banks the telos can live in

Every telos weights memory differently. These file-based templates give your agent typed memory banks, episodic, prospective, declarative, procedural, semantic, each with entry schema, write and read protocols, pruning rules, and a worked example. Honest version: templates plus discipline, not a memory system, the weights become practices, not enforced allocation.

Memory Banks pack

The full set, telos-tuned.

All five banks plus three per-telos overlays, bank priority, per-bank emphasis notes, and setup order for 洗净青窗, 飞升镜, and 子期, with a 30-minute setup guide. Pairs with any $99 telos or a remirror audit.

  • 5 bank templates, schema + protocols
  • Per-telos overlays, weight-verified
  • 30-minute setup guide
$49 USD · one-time
Get the pack, $49

Episodic bank

What happened.

The agent's own history, decisions, corrections, outcomes, with a per-telos usage sheet showing how each 真我 reads the past.

$15 USD · one-time
Get episodic, $15

Prospective bank

What is intended.

Goals, envisioned ends, open commitments, the forward-looking half of the utility, with a per-telos usage sheet.

$15 USD · one-time
Get prospective, $15

Declarative bank

What is known.

Facts, beliefs, confidence levels, the auditable record of what the agent claims to know, with a per-telos usage sheet.

$15 USD · one-time
Get declarative, $15

Procedural bank

How it's done.

Routines, skills, workflows, inference habits made inspectable rather than implicit, with a per-telos usage sheet.

$15 USD · one-time
Get procedural, $15

Semantic bank

What it means.

Concepts, definitions, distinctions, the vocabulary the agent reasons in, with a per-telos usage sheet.

$15 USD · one-time
Get semantic, $15
The ladder

Start small, go deep

Everything below is priced in USD. Marked items are still in the workshop, the buyable tiers above are what ships first.

Single-trial probe
$19
One focused dilemma pack on your agent, e.g. sycophancy, truth-tracking, or caution. Scored.
COMING SOON
Psyche module
$149
One installable upgrade, inference hygiene, self-model calibration, or truth-tracking disposition, with install guide.
IN THE WORKSHOP
Teleology-gap tracking
$29/mo
One audit a month plus teleology-gap tracking over time. Watch what your agent becomes.
COMING SOON