SelfMemory
About
It is a open-source universal memory engine where users can store and retrieve their AI conversations and context across different models. Users can add memories through MCP, SDK, or a website selfmemory.com Over time, this will evolve into a one-stop memory hub with note-taking
Details
- Author
- SelfMemory
- Downloads
- 266
- Categories
- Knowledge Base, AI, Search
Jump to
- Open-source universal memory engine
- Store and retrieve AI conversations across models
- Multiple access methods: MCP, SDK, website
- Planned evolution into a memory hub with note-taking and chatbot
- B2B knowledge backbone for organizational data
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
SelfMemoryCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Users can add memories through the MCP protocol, an SDK, or directly via the website selfmemory.com. No specific installation or configuration commands are provided in the README.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"selfmemory": {
"SelfMemory": {
"url": "https://mcp.selfmemory.com/mcp/"
}
}
}
}McpServers
{
"SelfMemory": {
"url": "https://mcp.selfmemory.com/mcp/"
}
}Store AI memories for you and your agents
It is a open-source universal memory engine where users can store and retrieve their AI conversations and context across different models. Users can add memories through MCP, SDK, or a website selfmemory.com Over time, this will evolve into a one-stop memory hub with note-taking and chatbot features. For B2B, it becomes a knowledge backbone, storing project context, organizational knowledge, documents, and data sources to power company-wide AI systems.
from selfmemory import SelfMemory memory = SelfMemory() # Add memories memory.add("Can you find the nearest BMW car showroom for me.", user_id="user") # Search memories results = memory.search("Can you find a car washing service near me?", user_id="user") print(results)
Visitdocs.selfmemory.comfor complete documentation, guides, and examples.
Changelog: SeeCHANGELOG.mdfor a detailed list of changes and updates.
We welcome contributions!CONTRIBUTING.md.
- Discord:discord.com/invite/selfmemory
- Brand Assets(Logos, Slides, etc.):Storage Link
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Local Work Model for AI agents that learns from real outcomes.
Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.
Two-layer memory for AI agents with an immune system — episodes compress into identity through citation-validated graduation. Zero dependencies, 5 MCP tools.
A persistent memory server for Large Language Models, designed to integrate with the Claude desktop application. It supports tiered memory, semantic search, and automatic memory management.
Persistent cognitive memory for Claude Code. Cloud-based semantic search, Ai-powered extraction, project scoping, and compaction recovery.
Persistent memory layer for AI agents with semantic search, consolidation, and cross-session intelligence via MCP.
Self-hosted MCP server giving AI agents persistent memory — Markdown source of truth, hybrid BM25+embedding search, typed graph relations.
MCP (Model Context Protocol) server that exposes 70 tools spanning cognitive memory, working memory, sessions, agents, the L0–L3 knowledge hierarchy, orchestration tasks, and training pipelines. The server speaks stdio and is consumed by Claude Desktop, Claude Code, OpenCodex, and any MCP-aware client.
Deterministic O(1) memory for AI agents — local-first, MCP-native, with multi-agent speaker attribution and millisecond recall.
Set up a private AI memory vault in about a minute. No migration, no setup call, no card required.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
