io.github.AINative-Studio/ainative-memory-mcp
Cloud-persistent, semantic-search memory MCP — drop-in for server-memory, backed
Before you connect
Config example (to connect)
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "ainative-memory-mcp"],
"env": {
"ZERODB_API_KEY": "ak_your_key"
}
}
}
}Works with these clients
- Claude Desktopnpx
- Claude Codenpx
- Cursornpx
- VS Codenpx
- Windsurfnpx
Derived from the registry manifest (package type and transport) — we have not installed it ourselves. Check the official README before relying on it.
Install / Connect
claude mcp add ainative-memory-mcp -- npx -y ainative-memory-mcp@1.0.1Follow the official README; env and args vary per server.
🛠️ Maintenance weight 30% · 56 pts
📊 Adoption weight 25% · 2 pts
✅ Usability weight 20% · 100 pts
❤️ Health & community weight 25% · 51 pts
Sources: GitHub API · npm registry · Official registry · updated 2026-08-11
90-day trend
⭐ stars
📦 weekly downloads +942%
Similar / alternative servers
How to choose among these
Search servers all give web access; they differ between semantic retrieval and cited Q&A.
- Semantic web search + content (research / competitors)→Pick Exa — semantic search plus retrieval
- Distilled Q&A-style answers, fact-checking→Pick Tavily / Perplexity — AI-optimized answers
- Privacy-focused, general web/news search→Pick Brave Search
io.github.jyswee/agenticmemory
Persistent memory for AI agents — history, context, semantic search, queues. 17
io.github.vnbochkarev-netizen/vibo-memory
Memory for AI agents: persistent L1/L2/L3, web-search savings, thread memory.
io.github.Lyellr88/marm-mcp-server
Universal MCP Server with advanced AI memory capabilities and semantic search.
io.github.fulminate-io/knowledge-mcp
Persistent memory graph for coding agents: hypotheses, evidence, and decisions s
One email a week, 5 minutes to see what happened in the MCP ecosystem
New servers, breakout trends, abandonment alerts — tracked automatically, curated by hand, sent to your inbox.
One email a week · unsubscribe anytime · no data selling