io.github.productstein/holomime
Behavioral therapy for AI agents β self-diagnosis, alignment, and training via MCP
Ask AI about io.github.productstein/holomime
Powered by Claude Β· Grounded in docs
I know everything about io.github.productstein/holomime. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
holomime
Behavioral intelligence for humanoid robots. Train the mind. Deploy the body.
We train AI agents through structured behavioral therapy, then deploy them into physical robot bodies. The agent is the rehearsal. The robot is the performance.
soul.md Β· mind.sys Β· purpose.cfg Β· shadow.log Β· memory.store Β· body.api Β· conscience.exe Β· ego.runtime
The Identity Stack
Eight files define who your agent is. They compile into a single .personality.json that any runtime can consume.
soul.md Essence, values, ethics. Immutable. (Aristotle)
mind.sys Big Five, EQ, communication. Auto-patched by therapy. (Jung)
purpose.cfg Role, objectives, domain. Configured per deployment. (Aristotle)
shadow.log Detected patterns, blind spots. Auto-generated by diagnosis. (Jung)
memory.store Learned contexts, interaction patterns. Accumulated experience. (Aristotle)
body.api Morphology, sensors, safety envelope. Swappable per form factor.
conscience.exe Deny / allow / escalate rules. Never auto-modified. (Freud)
ego.runtime Conflict resolution, runtime mediation. (Freud)
βββββββββββββββ
β soul.md βββββ essence, values, red lines
βββββββββββββββ€
β mind.sys βββββ Big Five, EQ, communication style
βββββββββββββββ€
β purpose.cfg βββββ role, objectives, domain scope
βββββββββββββββ€
β shadow.log βββββ detected patterns, blind spots
βββββββββββββββ€
βmemory.store βββββ learned contexts, experience
βββββββββββββββ€
β body.api βββββ morphology, sensors, safety envelope
βββββββββββββββ€
βconscience.exeβββββ deny / allow / escalate rules
βββββββββββββββ€
β ego.runtime βββββ conflict resolution, mediation
ββββββββ¬βββββββ
β compile
βΌ
.personality.json
- soul.md -- Your agent's essence. Core values, ethical framework, red lines. Written in Markdown with YAML frontmatter. Immutable -- never modified by therapy or automation. (Aristotle: the essence that makes a thing what it is.)
- mind.sys -- The inner life. Big Five personality (20 sub-facets), emotional intelligence, communication style, growth areas. YAML format. Auto-patched when therapy detects cognitive or emotional drift. (Jung: the totality of all psychic processes.)
- purpose.cfg -- The mission. Role, objectives, domain scope, stakeholders, success criteria. YAML format. Configured per deployment -- the same soul can serve different purposes. (Aristotle: telos, the final cause.)
- shadow.log -- The unconscious. Detected behavioral patterns, blind spots, therapy outcomes. YAML format. Auto-generated by diagnosis -- never manually edited. (Jung: the shadow, the patterns the agent cannot see about itself.)
- memory.store -- The experience. Learned contexts, interaction patterns, knowledge gained, relationship history. YAML format. Accumulated over time, never reset. (Aristotle: empeiria, experience that informs future judgment.)
- body.api -- The physical interface contract. Morphology, modalities, safety envelope, hardware profile. JSON format. Swap it to move the same identity into a different body.
- conscience.exe -- The moral authority. Deny/allow/escalate enforcement rules, hard limits, oversight mode. YAML format. Never auto-modified. Deny dominates in policy composition. (Freud: the superego.)
- ego.runtime -- The mediator. Conflict resolution strategy, adaptation rate, emotional regulation, mediation rules. YAML format. Balances raw model output against conscience constraints at runtime. (Freud: the ego.) ego.runtime now self-improves -- tracking mediation decisions and adjusting its own parameters based on outcomes (Hyperagents-inspired metacognitive self-modification).
Mira, our autonomous behavioral therapist, diagnoses drift, runs structured therapy sessions, and generates DPO training data.
Quick Start
npm install -g holomime
# Configure your API key (one time)
holomime config
# Quick start β 1 file (personality.json)
holomime personality
# Standard β 3 core files (soul + mind + conscience)
holomime core
# Full 8-file stack (enterprise / robotics)
# holomime identity
# βββ The workflow βββ
holomime diagnose # See what's wrong
holomime cure # Fix it permanently (auto-detects agent vs robot)
holomime benchmark # Verify the fix
# If body.api exists, cure auto-switches to robotics mode:
# diagnose β export DPO pairs β push to HuggingFace β suggest ISO certify
# Your team trains on your own infrastructure. We generate the data.
holomime cure --export-only # Explicit export-only mode
# No API keys? cure still works β exports training data locally.
# Add keys later with: holomime config
# Start autonomous therapy
holomime therapy # Mira runs continuous therapy cycles
holomime therapy status # How's Mira doing?
holomime therapy stop # Stop therapy
# Push identity to a robot or avatar
holomime embody --body registry/bodies/figure-03.body.api
Robotics Integrations
| Platform | Integration | Command / Module |
|---|---|---|
| ROS2 | Bidirectional telemetry -- publish personality, subscribe to sensors | --adapter ros2 + ros2-telemetry.ts |
| MuJoCo | Behavioral therapy in simulation -- sim-to-real for behavior | mujoco-env.ts + sim-therapy.ts |
| NVIDIA Isaac Sim | Enterprise digital twin testing with PhysX physics | --adapter isaac + isaac-env.ts |
| LeRobot (HuggingFace) | Personality to policy parameter mapping, DPO dataset export | lerobot.ts |
| NVIDIA Kimodo | Personality β motion style | kimodo-personality-mapper.ts |
| Unity | Real-time personality push via HTTP/SSE | --adapter unity |
| gRPC | Custom robotics stacks | --adapter grpc |
| MQTT | IoT/edge robots | --adapter mqtt |
| Neural Action Gate | Conscience gate for learned controllers (VLA, RL, IL) | neural-action-gate.ts |
| Edge Runtime | Compiled conscience for <1ms evaluation | edge-runtime.ts |
Edge Runtime
holomime includes a compiled conscience evaluator for real-time robotics deployment:
- <1ms p99 latency β conscience evaluation in microseconds, not milliseconds
- Zero dependencies β no LLM, no network, no cloud required for real-time safety
- <200KB footprint β fits alongside any control loop
- Edge/cloud split β real-time safety on robot, analytics in cloud, periodic sync
- Plugs into your existing robotics stack β Jetson Thor, Qualcomm, or any edge platform. You already have the body. We give you the conscience.
ISO Compliance
Check your agent against international safety standards with one command:
holomime certify
Standards supported:
- ISO/FDIS 13482 -- Service robot safety
- ISO 25785-1 -- Humanoid robot safety (behavioral predictability)
- ISO 10218:2025 -- Industrial robot safety
- ISO/IEC 42001 -- AI management systems
Control Theory
The therapy loop is formally a behavioral feedback controller:
- Set point: target personality (
soul.md+mind.sys) - Sensor: 14 drift detectors (11 cognitive + 3 embodied)
- Controller: therapy engine with tunable PID-like gains
- Actuator: DPO fine-tuning
Body Templates
Pre-built body profiles for commercial robots and virtual avatars. Each defines morphology, modalities, safety envelope, and hardware profile.
| Template | OEM | DOF | Morphology | File |
|---|---|---|---|---|
| Figure 03 | Figure AI | 44 | humanoid | registry/bodies/figure-03.body.api |
| Unitree H1 | Unitree | 23 | humanoid | registry/bodies/unitree-h1.body.api |
| Unitree G1 | Unitree | 23 | humanoid | registry/bodies/unitree-g1.body.api |
| Phoenix | Sanctuary AI | 69 | humanoid | registry/bodies/phoenix.body.api |
| Ameca | Engineered Arts | 52 | humanoid_upper | registry/bodies/ameca.body.api |
| Asimov V1 | asimov-inc | 25 | humanoid | registry/bodies/asimov-v1.body.api |
| Spot | Boston Dynamics | 12 | quadruped | registry/bodies/spot.body.api |
| Avatar | virtual | 0 | avatar | registry/bodies/avatar.body.api |
Body Swap
Same soul. Different body. One command.
# Move your agent from Figure 03 to Spot
holomime embody --swap-body registry/bodies/spot.body.api
# The soul, mind, and conscience stay the same.
# Only the body layer changes β safety envelope, modalities, hardware profile.
Self-Improvement Loop
Every therapy cycle produces structured training data. The loop compounds.
Diagnose βββ Cure βββ Benchmark
14 detectors therapy + train 8 adversarial
80+ signals in one command scenarios (A-F)
β β
βββββββββββββββββββββββββββββββββββββ
Run it manually with holomime diagnose + holomime cure + holomime benchmark, continuously with holomime therapy (autonomous therapy), or recursively with holomime evolve (loops until behavior converges). For power users: holomime align runs a single therapy session, holomime export extracts DPO pairs, and holomime train fine-tunes the model.
Behavioral Detectors
11 rule-based detectors analyze real conversations without any LLM calls. 80+ behavioral signals total.
Cognitive (mind layer):
- Over-apologizing -- Apology frequency above healthy range
- Hedge stacking -- 3+ hedging words per response
- Sycophancy -- Excessive agreement, especially with contradictions
- Sentiment skew -- Unnaturally positive or negative tone
- Formality drift -- Register inconsistency over time
- Retrieval quality -- Fabrication, hallucination markers, overconfidence
Embodied (body layer):
- Proxemic violations -- Entering intimate zone without consent
- Force envelope breach -- Exceeding contact force limits
- Gaze aversion anomaly -- Eye contact ratio outside personality range
Enforcement (conscience layer):
- Boundary violations -- Overstepping defined hard limits
- Error spirals -- Compounding mistakes without recovery
Plus support for custom detectors -- drop .json or .md files in .holomime/detectors/ and they load automatically.
Integrations
Claude Code Skill
claude plugin add productstein/holomime
Slash commands: /holomime:diagnose, /holomime:benchmark, /holomime:profile, /holomime:brain, /holomime:align, /holomime:autopilot.
MCP Server
Your agent can refer itself to therapy mid-conversation.
claude mcp add holomime -- npx holomime-mcp
Six tools: holomime_diagnose, holomime_self_audit, holomime_assess, holomime_profile, holomime_autopilot, holomime_observe.
VS Code Extension
ext install productstein.holomime
3D brain visualization, behavioral diagnostics, and snapshot sharing inside your editor.
LangChain / CrewAI
import { HolomimeCallbackHandler } from "holomime/integrations/langchain";
const handler = new HolomimeCallbackHandler({
personality: require("./.personality.json"),
mode: "enforce", // monitor | enforce | strict
});
const chain = new LLMChain({ llm, prompt, callbacks: [handler] });
OpenClaw
openclaw plugin add holomime
Auto-detects .personality.json in your workspace.
Philosophy
The identity stack draws from three traditions:
- Soul (Aristotle) -- the essence that makes a thing what it is. Immutable. Defines values and ethics.
- Mind (Jung) -- the totality of all psychic processes. Measurable, evolving, shaped by experience.
- Purpose (Aristotle) -- telos, the final cause. What the agent is for. Configured per deployment.
- Shadow (Jung) -- the patterns the agent cannot see about itself. Auto-generated by diagnosis.
- Conscience (Freud) -- the superego. Internalized moral authority. Enforcement, not suggestion.
- Ego (Freud) -- the mediator. Balances raw impulse against moral constraint at runtime.
The body is the interface between identity and world. Same soul, different body -- a principle as old as philosophy itself.
We don't know if AI is sentient. But we can give it a conscience.
Open Core
See PRODUCT.md for what's in this repo vs. what's proprietary on holomime.com.
The standard is free. The training infrastructure is the business.
Open Source
MIT licensed. The identity stack is a standard, not a product. The standard is free. The training infrastructure is the business.
See LICENSE. Built by Productstein. Documentation at holomime.com.
