Memorix Documentation

July 2, 2026 · View on GitHub

Use this page as the fastest path to the right Memorix document.

The public docs are organized by user intent:

  • Start: install Memorix and run memorix setup for an agent
  • Use: memory search, Git Memory, dashboard, and the optional bundled terminal agent
  • Operate: configuration, Docker, performance, troubleshooting
  • Integrate: MCP tools, CLI, SDK, agent rules, hooks, plugins, skills
  • Understand: architecture and deeper implementation notes
  • Develop: contributor workflow and release checks

Start

You want to...Read this
Install Memorix and run one-command agent setupSETUP.md
Configure provider keys, model lanes, and project overridesCONFIGURATION.md
Connect an IDE or AI coding agent manually over MCPSETUP.md
Understand plugin, rules, hooks, skills, and MCP supportINTEGRATIONS.md
Run the HTTP service in DockerDOCKER.md
Try the bundled terminal agentMEMCODE.md

Use

TopicDocument
CLI commands and MCP toolsAPI_REFERENCE.md
Memory Autopilot, CodeGraph Memory, and context packsAPI_REFERENCE.md § Memory Autopilot, CodeGraph Memory, and Context Packs, context fabric design, and auto context design
Git-derived engineering memoryGIT_MEMORY.md
Memory formation and quality pipelineMEMORY_FORMATION_PIPELINE.md
Performance and resource profilePERFORMANCE.md
Orchestrated subagent tasks, messages, locks, handoffsAPI_REFERENCE.md § Orchestration Coordination
Subagent orchestrationAPI_REFERENCE.md and memorix orchestrate --help
Bundled terminal agentMEMCODE.md

Operate

TopicDocument
Runtime selection: setup packages, stdio MCP, HTTP MCP, dashboard, CLI, memcodeSETUP.md
TOML-first configurationCONFIGURATION.md
Docker/compose deploymentDOCKER.md
Resource and timeout tuningPERFORMANCE.md
AI-facing install and troubleshooting playbookAgent Playbook

Integrate

TopicDocument
MCP / CLI commandsAPI_REFERENCE.md
Plugin, rules, hooks, skills, and MCP support matrixINTEGRATIONS.md
TypeScript SDK../README.md#sdk
Workspace and rules syncAPI_REFERENCE.md § Workspace and Rules
Project skills and mini-skill promotionAPI_REFERENCE.md § Skills
Hook architecturehooks-architecture.md

Understand

TopicDocument
System shape, data flows, memory layersARCHITECTURE.md
Design decisions and rationaleDESIGN_DECISIONS.md
Module-by-module notesMODULES.md
CodeGraph Memory / Context Fabric design2026-06-29-codegraph-memory-context-fabric-design.md
Auto Context Layer design2026-06-29-auto-context-layer-design.md
Historical cloud sync and multi-agent researchCLOUD_SYNC_AND_MULTI_AGENT_RESEARCH.md
Known issues and old roadmap notesKNOWN_ISSUES_AND_ROADMAP.md

Historical/deep-reference documents may describe older designs. If they conflict with the current product docs, prefer:

  1. README.md
  2. SETUP.md
  3. CONFIGURATION.md
  4. MEMCODE.md
  5. API_REFERENCE.md
  6. Agent Playbook

Develop

TopicDocument
Contributor workflow, tests, build, release checksDEVELOPMENT.md
AI-facing project context noteAI_CONTEXT.md
LLM-friendly short summary../llms.txt
LLM-friendly full summary../llms-full.txt

Current Product Line

These docs target the 1.1 release line, where:

  • memorix setup --agent <agent> --global is the default agent integration command
  • memorix serve is the manual stdio MCP server for external agents
  • memorix background start runs the shared HTTP MCP service and dashboard
  • memorix integrate --agent <agent> and memorix hooks install --agent <agent> remain manual/fallback generation commands
  • memorix / memcode open memcode, the bundled terminal agent that uses the same Memorix memory pool
  • ~/.memorix/config.toml and project memorix.toml are the user-facing configuration model
  • legacy memorix.yml, .env, and config.json files are still read for compatibility, but new setups should use TOML