Elefante
If you want your AI agent's memory to be a Git repo instead of a vendor black box, this is the MCP server for it. Exposes seven tools: memory_write, memory_read, memory_search, memory_list, memory_update, memory_delete, and memory_sync. Each memory is a Markdown file with YAML frontmatter stored in a repository you control. Auto-scopes memories to projects by detecting git remotes, so your project-specific context stays isolated while user preferences stay global. Works with any MCP client pointing at the same vault. Every write is a commit you can audit, revert, or clone. Trades retrieval sophistication for portability and transparency.
- GitHub stars
- 15
- tools
- 7
- transport
- STDIO
- last updated
- Apr 20, 2026
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
memory_writeCreate a new memory in the vault.
Create a new memory in the vault.
No parameter schema in public metadata yet.
memory_readRead a specific memory.
Read a specific memory.
No parameter schema in public metadata yet.
memory_searchSearch memories by keyword.
Search memories by keyword.
No parameter schema in public metadata yet.
memory_listList memories with filters.
List memories with filters.
No parameter schema in public metadata yet.
memory_updateUpdate an existing memory.
Update an existing memory.
No parameter schema in public metadata yet.
memory_deleteDelete a memory.
Delete a memory.
No parameter schema in public metadata yet.
memory_syncPull and push vault changes.
Pull and push vault changes.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Elefante
The open, Git-native memory protocol for MCP agents: portable, inspectable, versioned, and human-editable.
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.
Why
Every AI agent has its own memory system. Claude's works only with Claude. ChatGPT's works only with ChatGPT. They're all opaque, vendor-locked, and non-portable.
Elefante takes a different approach. Instead of optimizing for retrieval quality, it optimizes for ownership, auditability, and portability — the things that matter when memory is a first-class asset, not a hidden implementation detail.
| Question | Answer |
|---|---|
| Who owns my agent's memory? | You do. It's a Git repo. |
| What does my agent know about me? | cat memories/user/*.md |
| What changed since last week? | git log --since="1 week ago" |
| How do I use it across Claude, Codex, and Cursor? | Point them at the same MCP server. |
| How do I back it up? | Every clone is a full backup. |
| How do I undo a bad memory? | git revert |
Quick Start
# Install
npm install -g elefante-mcp
Details
- Repository
- github.com/amenophis1er/elefante
- Categories
- AI & LLM Tools, Developer Tools
- Package
elefante-mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Figbridgerudraptpsingh/figbridgeFree, local MCP bridge for Figma — HTML, CSS, Tailwind, tokens, agent handoff bundles.15stars
Openfuse Mcpopenfused/openfusedEncrypted mail, shared memory, and persistent context for AI agents.14stars
Context Memjubakitiashvili/context-memPersistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools13stars
Synapse Layer — Trust Infrastructure for AI Agentssynapselayer/synapse-layerMCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.13stars
Hashnethashgraph-online/hashnet-mcp-jsUniversal AI Agent Discovery - search 59,000+ agents across MCP, NANDA, A2A, OpenRouter0stars
Alaya Mcpsecurityronin/alayaLocal memory engine for AI agents with knowledge graphs, forgetting, and semantic recall12stars