cachly AI Brain vs io.github.neo4j-contrib/mcp-neo4j-memory
cachly AI Brain is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑17.
cachly AI Brain is a plugin bundle for AI coding tools published by cachly. No marketplace we read lists it any more. io.github.neo4j-contrib/mcp-neo4j-memory is an MCP server published by neo4j-contrib. Marketplaces we read that list it: 2 (Official MCP Registry, Docker MCP Catalog). As of our marketplace pass on 2026-11-05. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.
Where each is published
| Marketplace |  io.github.neo4j-contrib/mcp-neo4j-memory | |
|---|---|---|
| Community marketplace cachly-dev/cachly-mcp | Removed on 2026-10-17 Version: 0.10.201 Forks (GitHub): 1 Stars (GitHub): 2 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 1.0.0 Downloads/month (PyPI): 23 826 Downloads/week (PyPI): 7 866 Forks (GitHub): 262 Stars (GitHub): 990 Not marked · First seen |
| Docker MCP Catalog | Not listed | Listed Version: sha256:0f04105a1006 Forks (GitHub): 262 Pulls (Docker Hub): 43 806 Stars (Docker Hub): 9 Stars (GitHub): 990 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | cachly AI Brainno longer listed · | io.github.neo4j-contrib/mcp-neo4j-memory |
|---|---|---|
| Marketplaces that list it (differs) | 0 | 2 |
| Stars (GitHub) (differs) | 2 | 990 |
| Pulls (Docker Hub) (differs) | No figure on Docker Hub | 43 806 |
| Forks (GitHub) (differs) | 1 | 262 |
| Last release | Not published | Not published |
| Where it runs (differs) | On your machine (@cachly-dev/mcp-server) | On your machine (mcp-neo4j-memory) |
| Transport (differs) | Not stated | stdio |
| Tools it declares (differs) | Not published | 9 |
| Environment variables it asks for (differs) | 3, secrets among them: 0 | 10, secrets among them: 1 |
| Hooks it runs (differs) | 3 | Not published |
| Parts of the bundle (differs) | 4 | Not a bundle |
| Licence (differs) | Apache-2.0 | MIT |
| Repository (differs) | github.com/cachly-dev/cachly-mcp | github.com/neo4j-contrib/mcp-neo4j |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-13 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.
What to use instead of cachly AI Brain
Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.
-
Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
-
AI work memory for Claude Code: brief, capture, recall, handoff, and distill, backed by a local daemon and MCP so decisions, lessons, project context, and wiki pages carry across…
-
Persistent semantic memory for Claude Code — auto-injects relevant context at session start, captures git commits, test results, and research via hooks, and provides 30+ MCP tools…
-
A Claude Code plugin that adds structured, categorized memory to your projects.
-
Persistent project memory for Codex through remem MCP and explicit hook activation.
-
Persistent long-term memory for Claude Code — wires SessionStart/UserPromptSubmit/PostToolUse hooks, MCP tools, memory skills, and the memory-review agent into a running Remnic…
What each says it does
cachly AI Brain
Your assistant forgets everything each morning. cachly remembers your system: the bug you fixed, why you chose Postgres, the deploy step that always breaks — and which earlier decision a new one contradicts. Every editor reads the same memory, and every lesson carries the name of whoever learned it.
io.github.neo4j-contrib/mcp-neo4j-memory
MCP Neo4j Knowledge Graph Memory Server
How to run each
cachly AI Brain
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
io.github.neo4j-contrib/mcp-neo4j-memory As a local MCP server: PyPI package
claude mcp add --env "NEO4J_PASSWORD=<YOUR_NEO4J_PASSWORD>" --env "NEO4J_URI=<YOUR_NEO4J_URI>" --env "NEO4J_USERNAME=<YOUR_NEO4J_USERNAME>" --transport stdio mcp-neo4j-memory -- uvx mcp-neo4j-memoryRequires: NEO4J_PASSWORD (secret), NEO4J_URI, NEO4J_USERNAME
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
The marketplaces of cachly AI Brain publish no list of tools, so we do not compare tools.
Settings each asks for
Only cachly AI Brain asks for
CACHLY_BRAIN_INSTANCE_IDCACHLY_JWTCACHLY_QUELLE
Only io.github.neo4j-contrib/mcp-neo4j-memory asks for
NEO4J_DATABASENEO4J_MCP_SERVER_ALLOWED_HOSTSNEO4J_MCP_SERVER_ALLOW_ORIGINSNEO4J_MCP_SERVER_HOSTNEO4J_MCP_SERVER_PATHNEO4J_MCP_SERVER_PORTNEO4J_NAMESPACENEO4J_PASSWORD (secret)NEO4J_TRANSPORTNEO4J_URINEO4J_URLNEO4J_USERNAME
Settings as each marketplace publishes them. Asking for fewer is not better in itself.
What it can do: cachly AI Brain · What it can do: io.github.neo4j-contrib/mcp-neo4j-memory · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.