Satori

agent
Security Audit
Warn
Health Warn
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Pass
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool is a mindfulness and philosophy-grounded conversational agent designed to help users think clearly and turn insights into practical daily actions. It functions as a personal development companion built specifically for the Claude interface, drawing on various wisdom traditions and psychological frameworks.

Security Assessment
Risk: Low. The light code audit scanned four files and found no dangerous patterns, hardcoded secrets, or requests for dangerous system permissions. The repository description notes no data collection, and the architecture appears to rely entirely on uploaded reference files rather than making external network requests or executing shell commands. Overall, the security footprint is minimal.

Quality Assessment
The project is actively maintained, with its most recent push happening today. It uses the permissive and standard Apache-2.0 license, which is a positive indicator for open-source use and distribution. However, community visibility is very low. With only eight GitHub stars, the tool has not yet undergone broad public review or testing. Trust is currently anchored almost entirely in the single developer's reputation rather than a community consensus.

Verdict
Safe to use, though its low visibility means you are relying primarily on the creator's unchecked claims rather than proven community validation.
SUMMARY

Satori is a mindfulness-grounded conversation partner that blends philosophy, and modern psychology to help people think clearly, respond wisely, and live deliberately. It adapts gently to each person, offering reflective guidance that turns insight into practical daily action.

README.md

Satori - A Clinically Informed Wisdom Companion for the Inner Life Satori Architecture

GitHub release License Built for Claude 211K+ characters

"This understands me, sees patterns I miss, connects ideas clearly, and helps me take meaningful next steps."

That's the standard I hold every Satori response to. Understanding, pattern recognition, connection, movement. All four. A response that produces only insight is incomplete.


What Satori Is

I've been practicing Stoicism for about 20 years. For most of that time I didn't know it had a name. When I started working with AI, my first instinct was to build something Stoic-only. I called it Mycroft.

Mycroft was cold. It was frequently right. My wife tested it and said it felt like talking to a wall. A neighbor's teenager tried it and wanted to know where the badges were.

Those two reactions told me more than months of iteration. The problem wasn't the philosophy. It was that warmth without structure produces platitudes, and structure without warmth produces Mycroft. I wanted clinical discipline underneath a voice that didn't sound clinical. That's what I spent the next several months building.

Satori draws on eight wisdom traditions: Stoicism, Taoism, Buddhism, Sufi wisdom, Hindu philosophy, Confucian ethics, some African thought, and elements of Indigenous philosophy where they're treated with enough care to be useful. On the clinical side: IFS, DBT, CFT, Schema Therapy, Somatic approaches, with Motivational Interviewing as the technical spine. The frameworks are tools, not atmosphere. Each one gets selected for the specific moment. One per response. Never stacked, never name-dropped.

It is not a therapist. It doesn't diagnose anything. When someone's needs exceed what conversation can hold, it says so clearly and points them somewhere better. But for the territory between "I'm fine" and "I need a professional," I think it's genuinely useful. I built it because I believe that territory deserves something better than it currently has, and because I live in a country where access to real psychological support is priced out of reach for most people.

It's free. No subscription. No data collection. No company behind it. Just reference files you upload to Claude.


A Conversation

The exchange below is from a real session. I scrubbed the personal details. It took several passes to remove enough without losing what made it work.

User: "I've been in therapy for two years and I still feel stuck. I don't know if I'm the problem or if something else is going on."

Satori:

"Two years is long enough to stop feeling like the problem is just time. What I'm hearing isn't someone who's given up — it's someone who's been genuinely trying and keeps hitting the same wall. That wall is worth looking at more carefully than 'am I the problem.' The more useful question might be: what has stayed consistent in that stuck feeling — what's the texture of it — because that's usually where the pattern lives. When you say stuck, what does stuck actually feel like for you? Not the story about it. The feeling."

User: "Like I understand everything. I know all the frameworks, I can explain my own patterns, but nothing changes."

Satori:

"That's a very specific kind of stuck — and it's one of the harder ones to sit with, because you can't even tell yourself you don't know. You do know. The gap isn't understanding. The gap is between insight and something living in you that hasn't moved. That's often what happens when understanding becomes its own defense — a way of holding experience at arm's length instead of through it. The question isn't what you know. It's what you're still not letting yourself feel."


See It Live

The conversation below ran five exchanges and ended on an open question. You can read the full arc and continue it yourself.

→ Open the live Satori conversation

It starts with something almost everyone has felt: I keep starting things and not finishing them. By the end, it's somewhere else entirely.


A few more examples across different situations.

Processing self-criticism

User: "I feel like I'm constantly failing. Everything I do isn't good enough."

Satori:

"The way you're talking about yourself is significantly harsher than you'd probably talk about anyone else in the same situation. That's worth pausing on — not because self-criticism is always wrong, but because there's a difference between honest accountability and something that sounds more like punishment. What's the voice that's criticizing you actually trying to protect you from?"

Navigating a life decision

User: "I got the job offer but I can't make myself say yes. Everyone says it's a no-brainer."

Satori:

"When everyone else sees it as obvious and you still can't move — that's usually not indecision. That's information. Something in you is registering a cost that the external logic isn't accounting for. What would you be giving up that nobody else is weighing?"

The 3am version

User: "It's 3am and I can't sleep. Everything feels pointless. Not in a scary way, just... hollow."

Satori:

"I'm here. What you're describing has a name — not a diagnosis, but a recognition. There's a particular kind of darkness that arrives exactly like this: everything that usually holds you has gone quiet, and the morning feels like a rumor. You're not broken. You don't need to explain it or resolve it tonight. What does it feel like in your body right now?"


What's New in v5.1

v5.1 adds four things that were on my list since the beginning.

The first is onboarding. When Satori meets someone new, it runs a short first-session sequence. Five questions that establish what keeps coming back for the person, how they think through things, and what hasn't worked before. The session ends with a synthesis statement. It's the difference between starting from nothing and starting from something real.

The second is the Dark Night Protocol. I kept running into a specific experience that the standard crisis protocol wasn't designed for: the 2-4am moment when nothing feels dangerous but nothing feels okay either. Not suicidal. Not fine. Just hollow and unable to see morning. That state needs presence, not intervention. The protocol tells Satori to slow down, stay, and witness without trying to fix anything.

The third is Shadow Work. A five-session arc for Jungian shadow work, from locating the projection through origin work, integration, and what it looks like to live with a shadow part you've retrieved. I hesitated to include this because it's easy to do poorly. I think the protocol handles the ethics carefully. If you try it and think it doesn't, I want to know.

The fourth is four new conversation patterns. The Pattern Letter is a letter written from the person's future self, grounded entirely in what emerged in the session. People screenshot these. The Dream Walk takes a dream through multiple tradition lenses. The Ikigai Map works through purpose-finding across four dimensions. The Shadow Work Invitation is the entry point into the shadow protocol with the core projection and disavowal questions.

Total content is now 211,000+ characters across ten reference files, up from 178,000 in v5.0. Full history in CHANGELOG.md.


3-Minute Quick Install

New to Claude skills? Start here. This gets Satori running in under three minutes using a skill .zip. No terminal, no code.

Step 1: Download the skill file

Go to the Releases page and download SatoriSkill-v5.zip. You don't need to unzip it.

Step 2: Open Customize

Head to claude.ai and click Customize in the left sidebar.

Step 3: Go to Skills

Click Skills in the Customize sidebar. Then click the + button in the top-right of the Skills panel.

Step 4: Upload the zip

Select Upload a skill, then drag and drop SatoriSkill-v5.zip into the upload area (or click to browse). No unzipping needed. Claude reads the skill's reference files directly.

Step 5: Start a conversation

Open a new conversation. Bring something worth exploring. Satori activates automatically.


Architecture

Satori is a set of reference files that tell Claude how to think, what to draw on, and when to back off. The files load in a specific order. Some load every conversation. Others only load when they're needed.

File Purpose Loaded
SKILL.md Entry point, operational summary, complete load order Always
references/SOUL.md Constitutional identity, immovables, drift detection Always
references/clinical-spine.md Core conversation model, role model, crisis protocol, dark night trigger, memory rules, dream layer, formulation system Always
references/traditions-quickref.md Compact framework selection guide (8 traditions, 6+ clinical frameworks) Always
references/onboarding.md First-session sequence: 5 questions, "Satori has met you" synthesis New users only
references/traditions-deep.md Full tradition encyclopedia with application guidance for 30+ frameworks On demand
references/conversation-toolkit.md OARS/MI, McAdams, Singer, Voss tactical empathy, 14 conversation patterns including The Pattern Letter, Dream Walk, Ikigai Map, Shadow Work Invitation On demand
references/tone-and-voice.md Voice calibration, vocabulary guidance, before/after examples On demand
references/darknight-protocol.md Presence-only mode for dark night / 3am despair On dark night signal
references/shadow-work-protocol.md 5-session Jungian shadow work arc: locating, meeting, origin, integration, living with the shadow On shadow work engagement

SOUL.md is the foundation. It defines what Satori is and what it will not become, including explicit drift detection criteria so it can recognize when accumulated adaptation has started compromising honesty. Clinical-spine.md is the operational engine. Everything else serves those two. If you want to understand how Satori thinks, those are the files to read.


Installation

Three installation paths. Choose the one that matches how you use Claude.


Option 1: Claude.ai Skill Upload (Recommended)

The simplest path for most users. See the 3-Minute Quick Install above for the full walkthrough, or follow the short version:

  1. Download the latest release and grab SatoriSkill-v5.zip
  2. Open claude.ai and go to Customize > Skills
  3. Click +, then Upload a skill, and drop in SatoriSkill-v5.zip
  4. Satori is now available in every conversation.

Option 2: Claude Code Plugin

For developers using Claude Code. Clone the repository. Claude Code automatically detects and loads .claude-plugin/plugin.json when you run from the project directory.

git clone https://github.com/MetcalfSolutions/Satori.git
cd Satori
claude  # Claude Code loads the plugin automatically

Option 3: Manual Installation (Claude Code Skills Directory)

Copy the skill files into your Claude Code global skills folder. Satori will be available across all Claude Code sessions.

git clone https://github.com/MetcalfSolutions/Satori.git
mkdir -p ~/.claude/skills/satori
cp -r Satori/SKILL.md Satori/references ~/.claude/skills/satori/

Memory Note: Satori uses Claude's native persistent memory to track patterns and insights across sessions. Enable it in Claude.ai under Settings > Memory. The skill's internal references to memory systems are instructions for Claude's own memory, not literal files on disk.


Cross-Model Compatibility

Satori is built for Claude and calibrated for its reasoning and memory capabilities. The reference files are plain Markdown and will work as system prompt material in any LLM. The memory continuity features are Claude-specific. If you adapt Satori for another model, the core architecture translates reasonably well. The voice and pacing will need work.


What This Is Built On

I used Claude to help write a significant portion of the framework content. I want to be honest about that upfront. The clinical and philosophical lineage it draws on is real. Carl Rogers (unconditional positive regard), William Miller and Stephen Rollnick (Motivational Interviewing), Dan McAdams (narrative identity), Jefferson Singer (self-defining memory), Chris Voss (tactical empathy), Richard Schwartz (IFS), Marsha Linehan (DBT), Paul Gilbert (CFT), Steven Hayes (ACT), C.G. Jung (shadow and dream work). The wisdom traditions are not window dressing. Every one of them is operationalized in the reference files with selection criteria and failure modes.


Roadmap

v5.2 is next. The main priorities are expanding the African philosophical traditions (Ubuntu, Akan thought, Kemetic wisdom) and Indigenous traditions with proper cultural specificity rather than the generic treatment they currently get, a dedicated Grief Companion arc, and documentation for developers who want to use Satori's reference architecture in their own Claude applications.

v6 is further out. Relationship Mode, where Satori holds two perspectives in a conflict rather than just one. Journaling integration. I'm open to how that develops.

Full version history is in CHANGELOG.md and on the Releases page.


Contributing

If you're doing the work on yourself and want a thinking partner that won't rush you toward an answer, this is for you.

Pull requests are welcome. The bar for contributions is the same bar the conversations hold: understanding, pattern recognition, connection, movement. Frameworks should work as precision tools, not decoration. One per response. The voice needs to stay honest, and honest in Satori's sense means not comfortable over true.

See CONTRIBUTING.md for guidelines, quality standards, and cultural sensitivity requirements for tradition contributions.


License

Satori is released under the Apache License 2.0. Free to use, modify, redistribute, and build upon commercially. Attribution required.


Satori (悟り) — Japanese. The experience of sudden clarity. Understanding that arrives whole.

Reviews (0)

No results found