Skip to content
Agentmart
Submit a tool

Cortex Memory Engine

Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs.

Connector by gambletan · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 35
Write a review

Chalk Labs

Need help deploying Cortex Memory Engine?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/gambletan-cortex

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs.

Use cases: agent-memory

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Runs code on install

Its package runs an install script (such as npm postinstall or setup.py code) as soon as you install it, before any tool is called. Read the script first.

Tools
2 read · 5 write · 0 delete
Secrets
None asked for
Install scripts
Runs code on install
Runs as
Docker image

Tools by what they do 7

Read from the source code; the running server may list different tools.

Read 2 · Look things up without changing anything.

  • memory_get
  • memory_search

Write 5 · Create, change, send or run things.

  • belief_observe
  • fact_add
  • memory_store
  • person_resolve
  • preference_set

Network hosts it talks to 8

  • ::1 · found in code
  • agent.meta.ai · found in code
  • api.github.com · found in code
  • cortex.alvinsclub.ai · found in code
  • github.com · found in code
  • me.ts.net · found in code
  • raw.githubusercontent.com · found in code
  • rustup.rs · found in code

Files it touches

  • ~/.claude/settings.json
  • /tmp/cortex_verify.db
  • /Users/alvinclaw/work/cortex
  • /Users/alvinclaw/work/cortex/cortex-core/src/retrieval.rs
  • /Users/alvinclaw/work/cortex/cortex-core/src/storage/memory_index.rs
  • Your home directory (~)
  • ~/.cortex/memory.db
  • ~/.local/bin/cortex-mcp-server
  • ~/Library/CloudStorage/x

Tools (7)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • belief_observe

    Update a belief based on new evidence. Beliefs are probabilistic — supporting evidence increases confidence, contradicting evidence decreases it. Use to track things learned about the user over time.

  • fact_add

    Store a semantic fact as a subject-predicate-object triple. Use for structured knowledge like "User works_at Google" or "User speaks Chinese".

  • memory_get

    Get a comprehensive context summary from all memory tiers. Returns user profile, recent episodes, beliefs, and relationships — ready for injection into system prompts.

  • memory_search

    Search through persistent memories. Returns results ranked by similarity, recency, salience, and social context. Use when you need context about the user, their preferences, or past interactions.

  • memory_store

    Save important information to persistent memory. Use for preferences, facts, decisions, and anything worth remembering across sessions.

  • person_resolve

    Resolve or create a person identity. Links a channel-specific user ID to a cross-channel person profile.

  • preference_set

    Store a user preference. Use for language, communication style, timezone, favorite tools, etc.

Signals

Stars
35
Forks
4
Open issues
0
Contributors
9
Last commit
Oct 22, 2026 (8 days ago)
Last release
Oct 6, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.gambletan/cortex
Version
1.8.0
Auth
No auth
Packages
oci ghcr.io/gambletan/cortex:v1.8.0
License
MIT
Repository
github.com/gambletan/cortex
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get Cortex Memory Engine running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying Cortex Memory Engine?

CallGet help
Cite this page

Cortex Memory Engine MCP server. Agent Mart. https://agentmart.dev/connectors/gambletan-cortex (last updated 2026-10-24)