Local-first shared memory layer for AI coding agents.
One project memory system for Claude Code, Codex, Cursor, Windsurf, Copilot, Gemini CLI, OpenCode, Pi, Kiro, Antigravity, Trae, and any MCP-capable agent.

Shared Project Memory | MCP | Git Memory | Reasoning Memory | Plugins | Orchestration

Chinese | Install | Agents | Quick Start | Memory Model | memcode | Docs

Memorix gives the AI coding agents you already use a shared, searchable project memory that survives new chats, IDE switches, terminal sessions, and handoffs. The memory lives under the Git project, not inside one chat window or one tool.

Use Claude Code today, Codex tomorrow, and Cursor in the afternoon. The agent can change; the project memory stays the same.

Reach for Memorix when you keep re-explaining the same project to a new agent session: the last session figured something out, another IDE cannot see it, or a design decision is buried in a chat you cannot find anymore.

Memorix is local-first. SQLite is the canonical store, Orama handles search, and LLM-backed formation/embedding is optional. Without model keys, Memorix still works with local full-text retrieval.

Memorix connects through the interfaces each agent already supports: plugin packages, MCP, project rules, hooks, skills, or the bundled terminal agent. memorix setup chooses the right setup for each agent and keeps stdio MCP as the default transport.

Claude Code official plugin + MCP + hooks + skills	Codex CLI official plugin + MCP + AGENTS.md	GitHub Copilot CLI plugin + MCP + hooks + skills	Cursor MCP + rules + skills	Windsurf MCP + rules + hooks	Gemini CLI extension + MCP + GEMINI.md
OpenCode local plugin + MCP + skills + AGENTS.md	pi coding agent package + extension + skill	Kiro MCP + steering + hooks	Antigravity MCP + GEMINI.md	Trae MCP + project rules	memcode bundled terminal agent	Any MCP Client stdio or HTTP MCP

_{Works with agents that speak MCP, expose hooks/rules, or support plugin/package entries. One local-first memory layer shared across all of them.}

Integration surfaces:

See Integration Surfaces for the current support matrix and what each generated file means.

Use the same setup command without --global only when you intentionally want repo-local guidance, rules, or hooks in the current Git project.

CLI, MCP, and HTTP are different entry points:

• memorix CLI is the direct command surface for setup, memory search/store, Git Memory, import/export, dashboard, orchestration, diagnostics, and automation.
• memorix serve is the stdio MCP bridge used by IDEs and coding agents.
• memorix background start / memorix serve-http run the HTTP service for a shared endpoint, dashboard, Docker, or multiple clients.

Requirements:

• Node.js >=22.19.0
• Git, because project identity is derived from the real Git root

Install and initialize:

npm install -g memorix
memorix init --global                   # optional defaults
memorix setup --agent claude --global   # or codex, copilot, cursor, pi, gemini-cli, opencode, windsurf, kiro, antigravity, trae

memorix init is optional. It creates or updates TOML configuration:

• ~/.memorix/config.toml for global defaults
• <git-root>/memorix.toml for optional project overrides

Legacy memorix.yml, .env, and ~/.memorix/config.json are still read for compatibility, but new setup flows use TOML.

If you want repo-local guidance or hooks for a specific repository, run the same setup command from inside that repo without --global.

Use the setup command first. The global form is the normal one-time install:

memorix setup --agent claude --global
memorix setup --agent codex --global
memorix setup --agent copilot --global
memorix setup --agent cursor --global
memorix setup --agent pi --global
memorix setup --agent gemini-cli --global
memorix setup --agent opencode --global

What it installs depends on the target agent, but the goal is the same: make Memorix available wherever you open that agent without asking you to wire every repo by hand.

• Claude Code: installs the Memorix plugin package, adds CLAUDE.md guidance, and enables hook capture when you do not pass --noHooks.
• Codex: installs the Memorix plugin package, adds AGENTS.md guidance, and enables hook capture when you do not pass --noHooks.
• GitHub Copilot CLI: installs the Copilot plugin package and official Memorix skills.
• Pi: installs the user-level Pi package and official skills.
• Cursor: writes Cursor MCP/rules/config entries in the chosen scope.
• Gemini CLI: installs the extension package and GEMINI.md context.
• OpenCode: installs the local plugin file, opencode.json, skills, and AGENTS.md guidance.
• Windsurf, Kiro, Antigravity, Trae: write the MCP/rules/hooks files the target supports.

Need a quieter install? Add --noHooks to keep MCP, skills, and guidance without automatic capture.

If you intentionally want repo-local guidance or hooks, run the same command inside that repository without --global.

If your agent only needs a manual MCP entry, use stdio:

{
  "mcpServers": {
    "memorix": {
      "command": "memorix",
      "args": ["serve"]
    }
  }
}

HTTP is not required for normal setup. Use it only when you intentionally want a shared background service, dashboard, Docker, or multiple clients using the same endpoint:

memorix background start

Then point the client at:

http://localhost:3211/mcp

In HTTP mode, agents should bind the active repo explicitly with memorix_session_start(projectRoot=...) when the client can provide the workspace path. Git remains the final source of truth for project identity.

Preview what will be removed:

memorix uninstall --dry-run

Stop the background service and remove hooks:

memorix uninstall --background --hooks

Full cleanup:

memorix uninstall --yes --background --hooks --purge-data
npm uninstall -g memorix

memorix uninstall reports MCP config entries for manual cleanup instead of silently editing every MCP file it finds.

memorix memory search --query "release blocker"
memorix reasoning search --query "why sqlite"
memorix git-hook --force
memorix ingest log --count 20
memorix dashboard

memorix
# or
memcode

This opens memcode, a terminal coding agent that uses the same Memorix project memory as your MCP-connected agents.

Search is project-scoped by default. scope="global" searches across projects. Retrieval boosts Git Memory for "what changed" questions and reasoning records for "why" questions.

memorix orchestrate uses the current checkout for single-worker runs. When running multiple workers, it creates task worktrees under .worktrees/ and merges successful task branches back. Use --isolated to force worktree isolation for one worker, --no-worktree to disable it, --allow-dirty to run with uncommitted changes, and --no-auto-merge to preserve task worktrees for manual review.

memcode is the terminal coding agent bundled with Memorix. It can read, edit, run commands, resume sessions, switch models, and use /memory commands while reading and writing the same project memory pool as your MCP-connected agents.

Use it when you want a terminal agent with memory already wired in.

one Git project -> one shared Memorix memory pool

See docs/MEMCODE.md for the memcode-specific guide.

Minimal ~/.memorix/config.toml:

[agent]
provider = "openai"
model = "gpt-4o"
api_key = "..."

[memory.llm]
provider = "openai"
model = "gpt-4o-mini"
api_key = "..."

[embedding]
provider = "auto"

[memory]
inject = "minimal"
formation = "active"

Use [memory.llm] and [embedding] for Memorix memory quality and retrieval. Use [agent] for the model memcode talks to while coding. Keep credentials in global config or environment variables, and do not commit secrets.

Docker is for the HTTP service, not stdio MCP:

docker compose up --build -d

Then open:

• dashboard: http://localhost:3211
• MCP: http://localhost:3211/mcp
• health: http://localhost:3211/health

The container must be able to see the repository path passed as projectRoot for project-scoped Git/config behavior.

Use Memorix directly from TypeScript:

import { createMemoryClient } from 'memorix/sdk';

const client = await createMemoryClient({ projectRoot: '/path/to/repo' });

await client.store({
  entityName: 'auth-module',
  type: 'decision',
  title: 'Use JWT for API auth',
  narrative: 'Chose JWT because the API is stateless and used by multiple clients.',
});

const results = await client.search({ query: 'auth decision' });
await client.close();

LLM-friendly summaries: llms.txt and llms-full.txt.

git clone https://github.com/AVIDS2/memorix.git
cd memorix
npm install
npm run lint
npm test
npm run build

Memorix builds on ideas from the MCP ecosystem and prior memory projects such as mcp-memory-service, MemCP, claude-mem, and Mem0. memcode is based on the Pi coding-agent codebase and adapts its terminal-agent model for the Memorix ecosystem.

Apache 2.0