DojoGenesis

io.github.DojoGenesisPublished by GitHub account DojoGenesisv3.2.1Updated Oct 28, 2026

Practice library for coding agents: skill search/invoke, seed patches, scout, reflect, ADR writer

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

A local methodology library for coding agents: search and invoke 99 development skills, apply seed thinking patterns, reflect, and write ADR decision records.

What you can do
  • Search, list and invoke methodology skills, run scouting and reflection scaffolds, and apply reusable seed patterns
  • Write architecture decision records as markdown files to a configured directory
  • Store, list and search gateway session memory, plus read-only queries against a Postgres memory mirror
  • Fetch across memory, skills, ADRs and seeds with one unified lookup
  • Create and search seeds, list agents, and dispatch prompts to an LLM through a gateway
  • Track project status and decisions, set dispositions, and run convergence and health checks
When to use it
Useful when you want a coding assistant to follow structured, named development methods rather than just retrieve more information, and to keep decision records and reusable patterns alongside a project. The README itself states it has not measured whether these scaffolds improve decisions.
Requirements
Runs as a local process over stdio, from a container image or a Go build (Go 1.23 or later). Works with zero configuration using bundled skills. Optional settings: DOJO_SKILLS_PATH for the full skill library, DOJO_ADR_PATH for where decision records are written, DOJO_GATEWAY_URL and DOJO_GATEWAY_TOKEN for the gateway, and DOJO_MEMORY_DB_URL for the memory hub tools.
Before you install
Dispatch-class tools spend LLM provider budget through the gateway and are rate limited. The decision writer creates files in DOJO_ADR_PATH. DOJO_GATEWAY_TOKEN and DOJO_MEMORY_DB_URL are credentials; the README advises a SELECT-only database role. HTTP mode requires DOJO_MCP_API_KEYS and refuses to start without it.

Installation

In SourceWeft

  1. Open DojoGenesis in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Dojo Genesis MCP Server

The methodology layer for Claude Code. It encodes 99 first-party working methods across 10 behavioral plugins as active cognitive scaffolds: instead of giving Claude more data, it gives Claude structured methods for software development decisions.

We have not yet measured whether these scaffolds improve Claude's decisions, so this README makes no claim that they do.

[CI] [Go] [License: MIT] [MCP] [LobeHub]


Quick Install

Claude Code

Add to your project's .claude/settings.json:

json
{  "mcpServers": {    "dojo": {      "command": "/path/to/dojo-mcp-server",      "env": {        "DOJO_SKILLS_PATH": "/path/to/CoworkPluginsByDojoGenesis",        "DOJO_ADR_PATH": "./decisions"      }    }  }}

Or using Docker:

json
{  "mcpServers": {    "dojo": {      "command": "docker",      "args": ["run", "-i", "--rm", "ghcr.io/dojogenesis/mcp-server:latest"]    }  }}

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json
{  "mcpServers": {    "dojo": {      "command": "/path/to/dojo-mcp-server",      "env": {        "DOJO_SKILLS_PATH": "/path/to/CoworkPluginsByDojoGenesis",        "DOJO_ADR_PATH": "./decisions"      }    }  }}

What's Included

Tools (28)

GroupTools
Methodologydojo_scout, dojo_invoke_skill, dojo_search_skills, dojo_list_skills, dojo_apply_seed, dojo_reflect
Decisionsdojo_log_decision (writes ADR markdown to DOJO_ADR_PATH)
Gateway memorydojo_memory_list, dojo_memory_store, dojo_memory_search (gateway session memory)
Memory Hubdojo_search_memory, dojo_get_memory, dojo_recent_memories — read-only Postgres mirror of the institutional memory (DOJO_MEMORY_DB_URL)
Unified fetchdojo_fetch — one tool to search AND fetch across memory hub + skills + ADRs + seeds (typed ids: memory:slug, skill:name, adr:file.md, seed:name)
Seedsdojo_seed_list, dojo_seed_create, dojo_seed_search
Agents²dojo_agent_list, dojo_agent_dispatch², dojo_agent_chat²
Dispatch²dojo_dispatch² — prompt → LLM through the gateway
Projectdojo_project_status, dojo_project_track, dojo_project_decision
Dispositiondojo_disposition_list, dojo_disposition_set
Craftdojo_converge, dojo_health

² Dispatch-class — spends LLM provider budget through the gateway. In HTTP mode these require a dispatch-enabled API key and are rate limited per key; dojo_scout's LLM path degrades to its offline scaffold for non-dispatch keys.

Skills (99 from CoworkPlugins, 43 bundled)

Skills are complete, battle-tested methodology workflows loaded from SKILL.md files at startup. When DOJO_SKILLS_PATH is set, all 99 first-party CoworkPlugins skills are available. Without it, 43 key skills across 8 plugins are embedded in the binary via go:embed.

Bundled plugins and skills:

PluginSkills
agent-orchestrationagent-teaching, decision-propagation, handoff-protocol, workflow-router, workspace-navigation
continuous-learningdebugging, project-exploration, research-modes, research-synthesis, retrospective, web-research-external
skill-forgemcp-cloudflare-builder, mcp-server-builder, process-extraction, skill-audit, skill-creation, skill-maintenance
specification-driven-developmentcontext-ingestion, frontend-from-backend, implementation-prompt, parallel-tracks, pre-implementation-checklist, release-specification
strategic-thinkingiterative-scouting, multi-surface-strategy, product-positioning, strategic-scout
system-healthdocumentation-audit, health-audit, semantic-clusters, status-writing
wisdom-gardencompression-ritual, memory-garden, seed-extraction, seed-library

Seed Patches (20)

Seeds are reusable thinking patterns drawn from across the Dojo ecosystem.

Dojo Genesis (Core)

SeedDescription
three_tiered_governanceThree-tiered governance framework: Strategic, Tactical, Operational.
harness_traceNested JSON trace log for complete agent session traceability.
context_iceberg4-tier context management system (hot/warm/cold/pruned).
agent_connectRouting-first agent architecture with a single supervisor.
go_live_bundlesLightweight deployment packages pairing artifacts with approval evidence.
cost_guardBudget for the full 5-10x context iceberg multiplier.
safety_switchUsers must remain in control -- no autopilot on sensitive operations.
implicit_perspective_extractionExtract implicit perspectives from user queries without enumeration.
mode_based_complexity_gatingRoute to local or cloud models based on mode complexity.
shared_infrastructureBuild once, reuse everywhere -- central implementations.

AROMA & Serenity Valley

SeedDescription
sanctuary_architectureDesign digital spaces for being, not just doing.
pace_of_understandingMove slow to move fast; learn without extraction.
lineage_transmissionHonor sources, trace influence, celebrate collaboration.
graceful_failurePermission to not know, change your mind, and ask for help.
local_first_liberationLocal-first architecture for agent autonomy and user sovereignty.
the_onsen_patternRest as critical practice for sustainable performance.
collaborative_calibrationNorms for peer-to-peer learning and explicit teaching.
transparent_intelligenceReveal internal state, admit uncertainty, make learning visible.
inter_acceptanceAccept yourself through the compassionate eyes of another.
radical_freedomAgency and the power to choose your response within constraints.

Resources

Documentation resources accessible via MCP resource URIs:

  • dojo://resources/{name} -- 8 documentation resources (AROMA philosophy, EIT principles, etc.)
  • dojo://seeds/{name} -- 20 seed patches
  • dojo://skills/{plugin}/{name} -- All loaded skills

Configuration

Env VarDefaultDescription
DOJO_SKILLS_PATH(bundled fallback)Path to CoworkPlugins root directory containing plugins/
DOJO_ADR_PATH./decisionsDirectory where dojo_log_decision writes ADR files
DOJO_GATEWAY_URLhttp://localhost:7340Dojo AgenticGateway base URL
DOJO_GATEWAY_TOKEN(unset)Bearer token for the gateway, if it requires one
DOJO_MEMORY_DB_URL(unset → hub tools disabled)Postgres DSN for the Memory Hub (URL or keyword form; use the SELECT-only role)
DOJO_HTTP_ADDR(unset → stdio)Opt into HTTP mode, e.g. :8091
DOJO_MCP_API_KEYS(unset)HTTP mode only: comma-separated label:key pairs (individually revocable)
DOJO_DISPATCH_ALLOWED_LABELS(unset → none)Key labels allowed to run dispatch-class tools
DOJO_DISPATCH_RATE_PER_MIN6Per-label rate limit for dispatch-class tools

The server works out of the box with zero configuration (bundled skills, default ADR path, stdio).


HTTP Mode (public endpoint)

Setting DOJO_HTTP_ADDR serves MCP streamable-HTTP instead of stdio:

  • POST/GET /mcp — the MCP endpoint, Bearer-key required (Authorization: Bearer <key>). Keyless or wrong-key requests get 401.
  • /mcp/k/<key> — same endpoint for clients that cannot send custom headers; the key is redacted in logs.
  • GET /health — unauthenticated liveness (status + version only).

The server refuses to start in HTTP mode without a valid, non-empty DOJO_MCP_API_KEYS. Every tool call is logged as tool_call tool=… key=<label> dur_ms=… outcome=… — labels only, never key material, never payloads.

bash
DOJO_HTTP_ADDR=:8091 \DOJO_MCP_API_KEYS="win:$(openssl rand -hex 32)" \./dojo-mcp-server
curl -s localhost:8091/healthcurl -s -X POST localhost:8091/mcp \  -H "Authorization: Bearer <key>" \  -H "Content-Type: application/json" \  -H "Accept: application/json, text/event-stream" \  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"curl","version":"0"}}}'

Client wiring (Claude Code): claude mcp add --transport http dojo-remote https://<host>/mcp --header "Authorization: Bearer <key>".

Deployment notes: ingress is expected to be a Cloudflare tunnel (no host ports); pin the container image by digest so auto-pull never surprise-deploys a new public surface. Image publishing: .github/workflows/docker-publish.yml → ghcr.io/dojogenesis/mcp (supersedes the old manually-pushed mcpbydojogenesis image).


Building from Source

bash
git clone https://github.com/DojoGenesis/mcp.gitcd mcp
# Buildgo build -o dojo-mcp-server ./cmd/server
# Run./dojo-mcp-server
# Testgo test -race -v ./...

Requires Go 1.23 or later.

Docker

bash
# Build the imagedocker build -t dojo-mcp-server .
# Run via stdio (for MCP hosts)docker run -i --rm dojo-mcp-server
# Run with skills path mounteddocker run -i --rm -v /path/to/CoworkPlugins:/skills -e DOJO_SKILLS_PATH=/skills dojo-mcp-server

Project Structure

mcp-server/  cmd/server/main.go           Server entry point, env vars  internal/    dojo/      handler.go                7 MCP tool handlers      scaffolds.go              Scout and reflect methodology templates    skills/      loader.go                 Filesystem SKILL.md loader      search.go                 Keyword + trigger search      bundled.go                go:embed fallback (15 key skills)      bundled/                  Embedded SKILL.md files    decisions/      writer.go                 ADR file writer    wisdom/      base.go                   Wisdom base, search, helpers      seeds.go                  20 seed patches      resources.go              8 documentation resources  Dockerfile                    Multi-stage container build  .github/workflows/ci.yml     CI pipeline  .goreleaser.yml               Cross-platform release config

Philosophy

Dojo Genesis is built on three core principles:

  1. Beginner's Mind -- Approach every interaction fresh, free from accumulated expertise.
  2. Self-Definition -- Help users see their own thinking, not impose external frameworks.
  3. Understanding is Love -- Deep, non-judgmental understanding is the highest service.

License

MIT License -- see LICENSE for details.

Copyright (c) 2026 Dojo Genesis

Contributing

Contributions are welcome. Please see github.com/DojoGenesis for organization-level guidelines.

Source: README.md at commit 61b731a

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v3.2.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts