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 setupfor 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 setup | SETUP.md |
| Configure provider keys, model lanes, and project overrides | CONFIGURATION.md |
| Connect an IDE or AI coding agent manually over MCP | SETUP.md |
| Understand plugin, rules, hooks, skills, and MCP support | INTEGRATIONS.md |
| Run the HTTP service in Docker | DOCKER.md |
| Try the bundled terminal agent | MEMCODE.md |
Use
| Topic | Document |
|---|---|
| CLI commands and MCP tools | API_REFERENCE.md |
| Memory Autopilot, CodeGraph Memory, and context packs | API_REFERENCE.md § Memory Autopilot, CodeGraph Memory, and Context Packs, context fabric design, and auto context design |
| Git-derived engineering memory | GIT_MEMORY.md |
| Memory formation and quality pipeline | MEMORY_FORMATION_PIPELINE.md |
| Performance and resource profile | PERFORMANCE.md |
| Orchestrated subagent tasks, messages, locks, handoffs | API_REFERENCE.md § Orchestration Coordination |
| Subagent orchestration | API_REFERENCE.md and memorix orchestrate --help |
| Bundled terminal agent | MEMCODE.md |
Operate
| Topic | Document |
|---|---|
| Runtime selection: setup packages, stdio MCP, HTTP MCP, dashboard, CLI, memcode | SETUP.md |
| TOML-first configuration | CONFIGURATION.md |
| Docker/compose deployment | DOCKER.md |
| Resource and timeout tuning | PERFORMANCE.md |
| AI-facing install and troubleshooting playbook | Agent Playbook |
Integrate
| Topic | Document |
|---|---|
| MCP / CLI commands | API_REFERENCE.md |
| Plugin, rules, hooks, skills, and MCP support matrix | INTEGRATIONS.md |
| TypeScript SDK | ../README.md#sdk |
| Workspace and rules sync | API_REFERENCE.md § Workspace and Rules |
| Project skills and mini-skill promotion | API_REFERENCE.md § Skills |
| Hook architecture | hooks-architecture.md |
Understand
| Topic | Document |
|---|---|
| System shape, data flows, memory layers | ARCHITECTURE.md |
| Design decisions and rationale | DESIGN_DECISIONS.md |
| Module-by-module notes | MODULES.md |
| CodeGraph Memory / Context Fabric design | 2026-06-29-codegraph-memory-context-fabric-design.md |
| Auto Context Layer design | 2026-06-29-auto-context-layer-design.md |
| Historical cloud sync and multi-agent research | CLOUD_SYNC_AND_MULTI_AGENT_RESEARCH.md |
| Known issues and old roadmap notes | KNOWN_ISSUES_AND_ROADMAP.md |
Historical/deep-reference documents may describe older designs. If they conflict with the current product docs, prefer:
Develop
| Topic | Document |
|---|---|
| Contributor workflow, tests, build, release checks | DEVELOPMENT.md |
| AI-facing project context note | AI_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> --globalis the default agent integration commandmemorix serveis the manual stdio MCP server for external agentsmemorix background startruns the shared HTTP MCP service and dashboardmemorix integrate --agent <agent>andmemorix hooks install --agent <agent>remain manual/fallback generation commandsmemorix/memcodeopen memcode, the bundled terminal agent that uses the same Memorix memory pool~/.memorix/config.tomland projectmemorix.tomlare the user-facing configuration model- legacy
memorix.yml,.env, andconfig.jsonfiles are still read for compatibility, but new setups should use TOML