Ainative Memory Mcp

io.github.AINative-StudioPublished by GitHub account AINative-Studiov1.0.1Updated Oct 24, 2026

Cloud-persistent, semantic-search memory MCP — drop-in for server-memory, backed by ZeroDB.

The publisher's own server: Memory.fit

VerifiedSTDIODesktop onlyDatabasesKnowledge & Memory

Overview

AI-generated overview

A local MCP memory server that stores a knowledge graph in the ZeroDB cloud and adds vector-based semantic search to the standard server-memory tools.

What you can do
Create, read and delete entities, observations and directed relations in a knowledge graph, including cascading relation removal on entity delete and fetching named entities with their relations. Search nodes by text match or by vector similarity to find entities by meaning. Read the whole graph at once. Data is stored in ZeroDB cloud tables with embeddings generated per entity, so the same graph is reachable from any device using the same key.
When to use it
Use it when you want an assistant to keep persistent memory across sessions and machines, and you would rather have cloud storage plus semantic recall than a local JSONL file. It is a drop-in swap for the reference server-memory server.
Requirements
Runs locally over stdio, typically launched with npx, so Node.js is needed. Optional environment variables ZERODB_API_KEY, ZERODB_PROJECT_ID and ZERODB_API_URL; if no key is given, a free ZeroDB instance is auto-provisioned on first run and credentials are written to .env and .mcp.json in the project. Network access to the ZeroDB API is required.
Before you install
All memory content is sent to and stored in a third-party cloud service, not on your machine. Auto-provisioning writes credentials into project files and prints a claim link; the free instance lasts 72 hours unless claimed. Anyone holding the same API key can read and change the same graph, so treat the key as a secret. Delete tools remove entities, observations and relations, and deleting an entity also removes its relations.

Installation

In SourceWeft

  1. Open Ainative Memory Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

ainative-memory-mcp

Enhanced MCP knowledge graph memory server with cloud persistence and semantic search. Drop-in replacement for @modelcontextprotocol/server-memory.

Why this instead of server-memory?

Featureserver-memoryainative-memory-mcp
StorageLocal JSONL fileZeroDB cloud
PersistenceLost on machine wipeSurvives forever
Cross-deviceNoYes (same API key = same graph)
Semantic searchNo (text match only)Yes (vector similarity)
SetupManual file pathAuto-provisions on first run
SharingCopy files aroundShare API key

Quick Start

Claude Desktop / Claude Code

json
{  "mcpServers": {    "memory": {      "command": "npx",      "args": ["-y", "ainative-memory-mcp"],      "env": {        "ZERODB_API_KEY": "ak_your_key"      }    }  }}

No API key? Just omit it — a free ZeroDB instance is auto-provisioned on first run.

Cursor / Windsurf / VS Code

Same config in your .mcp.json:

json
{  "mcpServers": {    "memory": {      "command": "npx",      "args": ["-y", "ainative-memory-mcp"],      "env": {        "ZERODB_API_KEY": "ak_your_key"      }    }  }}

Get an API Key

bash
npx zerodb-cli init

Or sign up at ainative.studio.

Tools (10)

All 9 original server-memory tools plus semantic search:

Original Tools

ToolDescription
create_entitiesCreate new entities with name, type, and observations
create_relationsCreate directed relations between entities
add_observationsAdd observations to existing entities
delete_entitiesDelete entities and their cascading relations
delete_observationsRemove specific observations from entities
delete_relationsDelete specific relations
read_graphRead the entire knowledge graph
search_nodesSearch by text match (name, type, observations)
open_nodesFetch specific entities by name with their relations

New Tool

ToolDescription
search_nodes_semanticVector similarity search — find entities by meaning, not just exact text
Semantic Search Example

The original search_nodes only finds exact text matches. search_nodes_semantic understands meaning:

search_nodes("ML frameworks")        -> might find nothingsearch_nodes_semantic("ML frameworks") -> finds "PyTorch", "TensorFlow", "JAX"

Environment Variables

VariableRequiredDescription
ZERODB_API_KEYNo*ZeroDB API key (auto-provisions if missing)
ZERODB_PROJECT_IDNoZeroDB project ID
ZERODB_API_URLNoAPI URL (default: https://api.ainative.studio)

*If no credentials are provided, a free instance is automatically provisioned on first run.

Auto-Provisioning

On first run without credentials:

  1. A free ZeroDB instance is provisioned automatically
  2. Credentials are saved to .mcp.json and .env in your project
  3. A claim URL is printed so you can take ownership of the instance
  4. Everything works immediately — no signup required

How It Works

Instead of writing to a local memory.jsonl file, this server:

  1. Entities are stored as rows in a ZeroDB NoSQL table (kg_entities)
  2. Relations are stored in a separate table (kg_relations)
  3. Vector embeddings are automatically generated for each entity via ZeroMemory, enabling semantic search
  4. All data persists in the cloud and is accessible from any device with the same API key

Migration from server-memory

  1. Replace @modelcontextprotocol/server-memory with ainative-memory-mcp in your MCP config
  2. Add ZERODB_API_KEY to your env (or let it auto-provision)
  3. Re-create your entities (one-time migration — your old JSONL data stays on disk)

License

MIT

Powered by ZeroDB + AINative

This package is part of the AINative ecosystem — the AI-native developer platform.

Why ZeroDB?

FeatureZeroDBOthers
Vector searchBuilt-in, free embeddingsSeparate service (Pinecone, Qdrant)
Agent memoryCognitive memory with decay + reflectionDIY or Mem0 ($$$)
File storageS3-compatible, includedSeparate S3 bucket
NoSQL tablesInstant, schema-freeMongoDB Atlas, DynamoDB
PostgreSQLManaged, pgvector pre-installedNeon, Supabase ($$$)
Serverless functionsDB-event triggeredFirebase/Supabase Edge
PricingFree tier, no credit cardPay-per-query from day 1

Get Started Free

bash
npx zerodb-cli init    # Auto-configures your IDE

Or sign up at ainative.studio — free tier, no credit card required.

View all ZeroDB packages →

Zero-Config Auto-Provisioning

No account needed to start. On first run, this package automatically:

  1. Provisions a free ZeroDB instance (~800ms)
  2. Saves credentials locally (.env, .mcp.json)
  3. Prints a claim link in your terminal

The 72-Hour Window

Your auto-provisioned instance is free for 72 hours. To keep your data permanently, visit the claim URL printed in your terminal.

For AI Agents

If a coding agent (Claude Code, Cursor, Windsurf) installs this package:

  • Auto-provisions without human intervention
  • The claim URL appears in agent output — visit it to take ownership
  • .claude/CLAUDE.md instructs agents to surface the claim link to you
  • Check .env or ~/.ainative/config.json for your project ID if you miss it

Source: README.md at commit 0244800

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Memory integrations

Memory.fit

fit.memoryOfficial publisher

Hosted Memory.fit server that lets an AI read your training, sleep, recovery and nutrition data and write back weekly plans, targets and meal plans.

Streamable HTTPWeb executableAuth
Location & LifestyleCredential requiredOct 29, 2026

pg.ddx.io: the PostgreSQL community's memory

io.ddx.pgOfficial publisher

pg.ddx.io: the PostgreSQL community's memory's hosted MCP server, published by pg.ddx.io; no sign-in required; Streamable HTTP; 29 tools.

Streamable HTTPWeb executable
Databases29 toolsOct 24, 2026

var.gg Naming Memory

gg.varOfficial publisher

Remote MCP server that suggests and searches code identifier names from domain concepts in Korean, Japanese, Chinese, Vietnamese and English, and exposes ERD…

Streamable HTTPWeb executable
Databases7 toolsOct 27, 2026

Counterparts

ai.counterparts

Local-first long-term memory for Claude Code and Claude Desktop: the assistant writes notes about you and your projects and recalls them in later sessions.

STDIODesktop only
AI & MLNot validated yetNov 7, 2026

LAHZE - Persian AI Memory Platform

Published by GitHub account pedramgholizadeh

LAHZE - Persian AI Memory Platform's hosted MCP server; no sign-in required; Streamable HTTP; 13 tools.

Streamable HTTPWeb executable
Location & Lifestyle13 toolsNov 3, 2026