AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Memory & Context/
neurostack
neurostack logo

neurostack

Active·★ 47·Apache-2.0·Updated 2026-10-22

NeuroStack is a self-hosted MCP server and CLI that indexes Markdown vaults by meaning, providing AI agents with persistent memory across sessions. It detects stale notes, supports semantic and keyword search, and uses tiered retrieval to minimize token usage. Fully local, it never modifies your files.

#ai-memory#knowledge-graph#local-ai#local-first#markdown#mcp#mcp-server
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#mcp-servers
$ Install
$ npm install -g neurostack && neurostack install && neurostack init
↗ Visit site★ GitHub
01

Features

01Hybrid semantic + keyword search across your Markdown vault
02Stale note detection to prevent AI from citing outdated information
03Agent write-back memory that persists across sessions
04Token-efficient tiered retrieval (triples → summaries → full content)
05Fully local, never modifies vault files
02

Compatibility

Linux
Linux
Verified via docs
macOS
macOS
Verified via docs
Claude Code
Claude Code
Verified via docs
Codex
Codex
Verified via docs
Gemini CLI
Gemini CLI
Verified via docs
Cursor
Cursor
Verified via docs
03

Quick start

1
$ npm install -g neurostack
2
$ neurostack install
3
$ neurostack init
04

Use cases

↳Give Claude Code or other AI assistants persistent memory across sessions
↳Search your personal knowledge base by meaning, not just keywords
↳Extract decisions, bugs, and learnings from session transcripts automatically
05

Alternatives

⚡Top VS:
VSopen-ontologies★1.2k→VSlocus★15→VSAgentRecall-MCP★371→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
ogham-mcp
★116
→
open-ontologies logo
open-ontologies★ 1.2k
AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL tableaux reasoner, SHACL validation, SPARQL, versioning. Single binary, no JVM.
VSCompare→
locus logo
locus★ 15
Persistent project-aware memory for AI coding tools. Built on MCP. Works with Codex, Claude Code, and other MCP-compatible clients.
VSCompare→
AgentRecall-MCP logo
AgentRecall-MCP★ 371
Persistent, correction-driven memory for AI agents. Cross-session, cross-platform (Claude Code, Codex, Gemini — any MCP client). Learns from mistakes, compresses context to save tokens, consolidates knowledge overnight. npm: agent-recall-mcp
VSCompare→
ogham-mcp logo
ogham-mcp★ 116
Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode
VSCompare→
agent-skill-memories-off logo
agent-skill-memories-off★ 48
把这些记住，帮我早点下班
VSCompare→
Ori-Mnemos logo
Ori-Mnemos★ 333
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
VSCompare→
LycheeMem logo
LycheeMem★ 1.1k
Compact, efficient, and extensible long-term memory for LLM agents.
VSCompare→
memtrace-public logo
memtrace-public★ 504
The missing memory layer for coding agents
VSCompare→
See all alternatives →
raphasouthall /
neurostack
↗

Your second brain, starting today. CLI + MCP server that helps you build, maintain, and search a knowledge vault that gets better every day. Works with any AI provider. Local-first, zero-prereq install.

47Apache-2.0
Last commit1d ago
StatusActive
CategoryMemory & Context
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit