← Back to directory
M

Memorix

Community
Local-first shared memory layer for AI coding agents.
GitHub source repository ↗
★ 694 Stars Category · Dev Tools Very popular Source revision 064fef7d4cb3
66FMRS · C
Reliability
8/20
Security and permissions
15/20
Maintenance
14/20
Documentation
16/20
Setup experience
13/20

Memorix is a feature-rich, local-first MCP server designed for AI coding agents. It supports a wide range of agents and clients, offering multiple memory types and tools, making it suitable for teams needing persistent memory across sessions. Installation and configuration are relatively complex but well-documented. It is not officially maintained, but the open-source community is active.

Read the FMRS scoring method →

Memorix is an open-source, local-first, cross-agent memory layer for AI coding agents via MCP. It supports Claude Code, Codex, Cursor, Windsurf, Copilot, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, and any MCP-capable agent. The memory lives under the Git project, not inside a chat window or tool, enabling shared, searchable project memory across sessions, IDEs, and terminals. It provides Observation Memory, Reasoning Memory, Git Memory, Code Memory, Curated Long-term Memory, Compact Continuity, Memory Autopilot, orchestration, and a bundled terminal agent (memcode).

Tools

memorix_session_start
Starts or binds a session to a specified project root.
memorix_project_context
Gets a summary of the current project context, including relevant memories, files, and cautions.
memorix_search
Searches memory entries within the project or globally.
memorix_detail
Retrieves full details of a specific memory entry.
memorix_store
Stores new facts, fixes, gotchas, or notes into memory.
memorix_resolve
Resolves references to actual files, symbols, or memory entries.
memorix_media
Manages controlled media assets, such as import, attach, view, and list.
memorix_checkpoint
Views and manages native context compaction checkpoints.
memorix_long_term_memory
Manages curated long-term memory, including candidates, approval, and archiving.
memorix_reasoning
Searches and stores design decisions, rationale, and trade-offs.
memorix_git_memory
Extracts and stores engineering facts from Git commits.
memorix_code_memory
Gets code state and symbol information to help agents understand the codebase.
memorix_context
Builds a compact task-lensed brief (Memory Autopilot).
memorix_resume
Resumes a previous session, loading relevant summaries and anchors.
memorix_skills
Lists or retrieves reusable project skills.
memorix_promote
Promotes durable knowledge into project skills.
memorix_team
Manages team collaboration, such as task assignment and handoffs.
memorix_lock
Manages file locks to prevent concurrency conflicts.
memorix_task
Creates and manages tasks for orchestration.
memorix_workbench
Opens an interactive terminal memory control plane.

Setup

  1. Install Node.js >= 22.18.0 and ensure Git is available.
  2. Install Memorix globally: npm install -g memorix.
  3. Initialize configuration (optional): memorix init --global.
  4. Set up integration for your agent: memorix setup --agent <agent> --global, e.g., --agent claude, --agent codex, --agent cursor.
  5. For manual MCP configuration, add stdio config to your client: {"mcpServers":{"memorix":{"command":"memorix","args":["serve"]}}}.
  6. Optional: Start the background HTTP service: memorix background start, then point client to http://localhost:3211/mcp.
claude_desktop_config.json
{
  "mcpServers": {
    "memorix": {
      "command": "memorix",
      "args": [
        "serve"
      ]
    }
  }
}

Fit and risk

Best for

  • Development teams that want shared project memory across different AI coding tools.
  • Experienced developers who frequently start new sessions and lose context.
  • Projects that value preserving design decisions and reasoning.
  • Users who prefer local-first, privacy-friendly memory storage.
  • Users working with multiple MCP-compatible agents who want a unified memory layer.

Not for

  • Simple projects that only need single-session memory.
  • Users without Node.js or Git environments.
  • Teams needing cloud sync or centralized memory management (Memorix is local-first).
  • Users needing fully automatic, review-free long-term memory (long-term memory requires manual candidates and approval).
  • Beginners who are configuration-sensitive, as setup involves multiple steps.

Required permissions

  • Read and write local files (project root and memorix data directory).
  • Execute Git commands (e.g., commit history reading).
  • Start local HTTP services (if background mode is enabled).
  • Optional API keys for LLM generation and embeddings (e.g., OpenAI, OpenRouter).
  • Install agent plugins, rules, hooks, and skills (via setup command).

Risks and side effects

  • Local-first means memory is not synced to cloud; you must back it up yourself.
  • Misconfigured API keys may send data to third parties; ensure keys are secure.
  • Hooks may consume computational resources or impact performance.
  • Long-term memory requires human review, otherwise incorrect information may accumulate.
  • Orchestration may create multiple worktrees or branches, requiring careful merge conflict resolution.

Troubleshooting

  1. If MCP connection fails, check `memorix doctor agents --agent <agent>` and run `memorix repair agents --agent <agent>`.
  2. Ensure Node.js version >= 22.18.0.
  3. Verify that `memorix serve` runs without errors on the command line.
  4. Ensure the project is a Git repository, as memory is bound to the Git root.
  5. For HTTP mode, check if port 3211 is listening: `curl http://localhost:3211/health`.
  6. Check logs or run `memorix workbench` for diagnostics.

Use cases

Share project knowledge across multiple agent sessions to avoid re-explanation.
Maintain consistent memory across IDEs or terminals for tool switching.
Turn Git commits into searchable engineering facts for quick impact analysis.
Preserve design decisions and rationale for future sessions.
Coordinate multi-agent parallel work with orchestration for tasks, locks, and reviews.

Supported clients

Claude CodeFull support
Codex CLIFull support
CursorFull support
WindsurfFull support
Gemini CLIFull support
GitHub Copilot CLIFull support
AntigravityFull support
OpenClawFull support
Hermes AgentFull support
Oh-my-PiFull support
PiFull support
KiroFull support
OpenCodeFull support
TraeFull support
Any MCP ClientFull support