Your agent's memory is a Git repo you own.
Every memory is a Markdown file you can read.
Every change is a commit you can audit.
Any MCP agent can connect to it.

# Install
npm install -g elefante-mcp

# Initialize vault (uses a private GitHub repo as storage)
elefante init git@github.com:yourname/my-memory.git

# Add your first memory
elefante add \
  --name "TypeScript strict mode" \
  --type user \
  --body "Always enable strict: true in tsconfig.json"

# Search
elefante search "typescript"

# Check status
elefante status

claude mcp add --scope user elefante -- npx -y elefante-mcp mcp

/mcp add --scope user elefante -- npx -y elefante-mcp mcp

{
  "mcpServers": {
    "elefante": {
      "command": "npx",
      "args": ["-y", "elefante-mcp", "mcp"]
    }
  }
}

~/Projects/acme-api/   →  git remote = github.com:you/acme-api.git
                       →  profile = "you/acme-api"
                       →  memories scoped to this project

~/Projects/my-cli/     →  git remote = github.com:you/my-cli.git
                       →  profile = "you/my-cli"
                       →  different project, different memories

Working in acme-api:
  ✓ "Uses Postgres 16"              (profile: you/acme-api)
  ✓ "Prefers Bun over npm"          (profile: null — global)
  ✗ "Uses SQLite"                   (profile: you/my-cli — different project)

Working in my-cli:
  ✓ "Uses SQLite"                   (profile: you/my-cli)
  ✓ "Prefers Bun over npm"          (profile: null — global)
  ✗ "Uses Postgres 16"             (profile: you/acme-api — different project)

---
id: mem_a1b2c3d4e5f6
type: feedback
name: No database mocking in tests
description: Integration tests must use real database connections
profile: you/acme-api
importance: 3
tags: [testing, database]
created_at: "2026-04-14T10:30:00Z"
updated_at: "2026-04-14T14:22:00Z"
---

Do not mock the database in integration tests — use a real connection
to a test database.

**Why:** Mocked tests passed but the production migration failed because
the mock didn't reflect actual schema constraints.

**How to apply:** Use the test database helper (`createTestDb()`)
instead of jest mocks.

$ git log --oneline
f4a2c1e remember: No database mocking in tests
b3d8e7a remember: TypeScript strict mode preference
a1c9f2b update: REST to GraphQL migration deadline
9e7d4c3 forget: Outdated staging URL
2f8a6b1 Initialize elefante vault

~/.elefante/vault/
├── .elefante/
│   └── config.yaml              # Vault settings
├── memories/
│   ├── user/                    # Who the user is
│   │   └── mem_*.md
│   ├── feedback/                # How the agent should behave
│   │   └── mem_*.md
│   ├── project/                 # Active work context
│   │   └── mem_*.md
│   └── reference/               # External resource pointers
│       └── mem_*.md
├── profiles/
│   └── *.yaml                   # Named scopes for partitioning
└── index/
    ├── manifest.json            # All memory metadata (generated)
    └── search.json              # Search index (generated)

elefante init <repo-url>       Clone vault repo to ~/.elefante/vault/
elefante status                Vault status, sync state, memory count
elefante list [--type TYPE]    List memories with filters
elefante search <query>        Search by keyword
elefante read <id>             Read a specific memory
elefante add                   Create a memory
elefante delete <id>           Delete a memory
elefante sync                  Pull and push changes
elefante reindex               Rebuild search index
elefante mcp                   Start MCP stdio server