Open infrastructure

Dojo Genesis

Infrastructure for disciplined AI.

AI agents are intelligent enough — they lack method. DojoGenesis encodes discipline into self-hosted runtimes, methodology skills, and practitioner tools.

148K+ lines of Go
89 methodology skills
8 LLM providers
19 runtime modules
0 vendor lock-in

Four tools. One practice.

Every component is self-hosted, single-binary, and designed to run without sending data to third parties.

Gateway

Self-hosted agentic AI runtime

19 modules · 148K+ lines of Go · 8 LLM providers · Single binary
  • Multi-provider routing with intent classification
  • DAG orchestration for complex agent workflows
  • SSE observability — watch every token in real time
github.com/DojoGenesis/gateway

CLI

Your terminal. Your infrastructure.

Interactive REPL · 30+ slash commands · 8 named surfaces
  • Plugin system with hook runner and lifecycle gates
  • SSE streaming — low-latency response rendering
  • Skill search, package-all, and CAS bridge built in
github.com/DojoGenesis/cli

Plugins

The discipline. Encoded.

89 skills · 8 behavioral plugins · Every one rated A+
  • Strategic thinking — structured decision frameworks
  • Specification-driven development — spec before code
  • System health — audit, converge, and maintain quality
github.com/DojoGenesis/plugins

MCP Server

Better methods, not just more data

7 tools · 89 skills · 20 seed patches
  • Claude Code methodology layer — skills inside the model
  • Decision logging — structured reflection and audit trail
  • Seed patches — behavioral upgrades delivered as context
github.com/DojoGenesis/mcp

A real session.

The CLI is an interactive REPL that connects to the Gateway. Every slash command maps to a surface.

dojo

dojo ~ /strategic-scout

Tension: We need to choose between SQLite and Postgres for the new service.

Scout is analyzing 3 routes...


Route 1: SQLite embedded

Zero ops. Single binary. Limits: no concurrent writers, 281TB ceiling.

Route 2: Postgres managed

Full SQL. Connection pooling. Cost: $7/mo minimum, ops overhead.

Route 3: SQLite now, migrate later

Ship today. Abstract the storage interface. Migrate when metrics justify.


Recommendation: Route 3. Ship with SQLite, keep the interface clean.

dojo

dojo ~ /sensei


Green Belt — Practitioner


"Ship small, learn fast, correct course."


XP: 2,340 / 3,000 to Blue Belt

Streak: 12 days


dojo ~ /garden seeds


23 seeds planted. 8 cultivated this week.

Latest: "compilation-as-contract" — planted 2h ago

What a skill looks like.

A skill is a structured methodology — not a prompt template, not a chain, not a wrapper. It defines phases, outputs, quality gates, and decision points. The agent follows the method. The method encodes the discipline.

8 plugins Strategic thinking, spec-driven dev, system health, wisdom garden, agent orchestration, continuous learning, skill forge, pretext-pdf
89 skills Every one rated A+ by automated audit. Frontmatter validated on every write via PostToolUse hook.
20 seeds Reusable thinking patterns — applied to new situations with checklist output.
strategic-scout/SKILL.md

---

name: strategic-scout

description: Explore tensions, scout routes, decide

model: opus

category: strategic-thinking

inputs:

- A tension or decision to analyze

- Optional: constraints, stakeholders

outputs:

- Scout document with 3-5 routes

- Architecture Decision Record (ADR)

---


# Strategic Scout


Begin with a tension, not a solution.


## Phase 1: Identify the Tension

State the tension in one sentence...

Every surface, one practice.

Eight named surfaces — Home, Garden, Practice, Trail, Partnership, Projects, Pipelines, Piloting — each accessible from CLI or browser.

Gateway Chat UI Embedded Svelte 5 SPA — multi-provider routing, real-time streaming
Piloting Dashboard SSE observability — live agent events, tool calls, token usage
Workflow Builder DAG-based task orchestration with visual node editor

From install to practice.

No accounts. No API keys to configure. Self-hosted from the start.

1

Start the Gateway

A single Go binary. Bring your own API keys for any of the 8 supported providers — or connect Ollama for fully local inference. The Gateway handles routing, memory, and skill storage.

./gateway
2

Launch the CLI

Install via Homebrew and connect. The CLI streams responses in real-time, runs plugins, and surfaces your Garden, Trail, and Practice from the terminal.

brew install DojoGenesis/tap/dojo && dojo
3

Begin the practice

Use /strategic-scout to think through decisions. Use /practice for daily reflection. Seeds accumulate in your Garden. The methods compound over time — the practice continues.

/strategic-scout "Should we monorepo or multi-repo?"

What changes with discipline.

AI tools are useful out of the box. DojoGenesis adds the layer that makes them reliable.

AI tools alone With DojoGenesis
Context between sessions Starts fresh every time Garden persists seeds, trails, memory
Decision methodology Ad hoc, prompt-dependent 89 structured skills with phases and gates
Multi-provider routing Locked to one vendor 8 providers, explicit and rule-based routing
Verification discipline Trust the output Pre-flight checks, compilation gates, audits
Infrastructure ownership Cloud-hosted, data leaves your machine Self-hosted. Single binary. Your data stays local.
Observability Black box Real-time SSE events, tool call tracing, token tracking

The practice beneath the tools.

A workspace should feel like a sanctuary — calm, focused, intentional. Surface information when asked, not when available.

from the sanctuary architecture seed, planted on every first run

Discipline over intelligence

Raw capability without method produces noise. Structured prompting, convergence gates, and behavioral plugins encode the discipline that makes intelligence useful — reproducibly.

Own your infrastructure

The Gateway runs on your hardware. Your skills stay in your repos. Your routing logic is auditable. No vendor lock-in, no prompt data leaving your network without your knowledge.

The practice continues

A dojo is not built once. Skills compound. Memory persists. Each session leaves seeds for the next. The stack grows with the practitioner, not against them.

Two commands to start.

$ brew install DojoGenesis/tap/dojo

==> Installing dojo from DojoGenesis/tap

==> Downloading dojo binary...

✓ dojo installed


$ dojo

Welcome to the dojo.

Gateway: localhost:7340  connected

Type /help to see available commands.


dojo> _

The CLI connects to the Gateway at localhost:7340. Start the Gateway first, then launch the CLI.

1

Install the Homebrew tap and the dojo binary.

2

Start the Gateway: dojo gateway start. It binds to port 7340 and loads your configured LLM providers.

3

Run dojo to enter the interactive REPL. Type /skills to see installed methodology plugins.

4

Install the MCP server in your Claude Code .mcp.json to bring skills inside the model context.

Read the orchestration guide ↗ — a progressive curriculum for Claude Code mastery.

More tools in the stack.

Focused packages extracted from the core platform. Each one zero-dependency where possible.

Logwatcher

Zero-dependency Go log watcher with bounded fan-out. Multi-file tail, multiple subscribers, silent drop on slow clients. Extracted from AgenticOS.

github.com/DojoGenesis/logwatcher

git-for-strategy

Strategic thinking as installable Claude Code infrastructure. Installs as a plugin that encodes structured decision-making, competitive scouting, and planning frameworks.

github.com/DojoGenesis/git-for-strategy

SurfaceIntelligence

AI competitive surface analysis. Structured scouting of products, communities, and ecosystems — output as seeds and decision logs, not unstructured text.

github.com/DojoGenesis/SurfaceIntelligence

orchestration-guide

Progressive curriculum for Claude Code mastery. Covers parallel agent dispatch, convergence gates, hook lifecycle, and the full practitioner playbook from first session to production.

dojogenesis.github.io/orchestration-guide

Built by a practitioner.

DojoGenesis started as internal tooling — methods and runtimes built to ship software with autonomous agents. The discipline encoded in these skills comes from actually using them, daily, across 18+ repositories and 400+ hours of agent-assisted development.

Every skill exists because it was needed. And then needed again.

Cruz Morales / Tres Pies Design / Madison, Wisconsin

469 agent dispatches in 18 days
89 commits across 6 repos
432 hours of development sessions
11 open source repositories