A local framework for giving an AI agent persistent memory, an identity, and changing emotional state. It runs from the substrate-mcp npm package.

Building or experimenting with locally run AI agents that use causal memory, identity, and emotional state.

It is intended for agents that need to retain context and behave as a continuing entity across interactions.

substrate — MCP server by PKaldone

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add mcp/pkaldone/substrate-mcp/substrate

Clone the repo

git clone --depth 1 https://github.com/PKaldone/substrate-mcp

Made for: Claude Code, Codex, Cursor.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin unknown No closer match found in the catalogue.

Security

Grade A, and why

substrate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 10 lines

The source is not reproduced here

No licence file

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 10 lines scan A a0d88705e00e

Subscribe to this mod's changes

substrate is an MCP server published in the GitHub repository PKaldone/substrate-mcp (0 stars, last pushed 5mo ago), with no licence file. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Memory and context ai-memory cognitive-framework garmo-labs mcp mcp-server model-context-protocol

xmemo

Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST. Runs locally from the @xmemo/client npm package. Needs 2 environment variables to run.

yonro/memory-os-cli · not measured

weasley-deepmind

Secure, fragment-based long-term memory for MCP-compatible AI agents. Runs locally from the weasley-deepmind npm package. Needs 3 environment variables to run.

potatohoney-p/weasley-deepmind · not measured

persistent-memory-mcp

MCP server "persistent-memory-mcp" as configured in dannymaaz/memory-mcp. Runs locally from the persistent-memory-mcp Python package.

dannymaaz/memory-mcp · not measured

sharpwave

Long-term memory for OpenClaw agents. An MCP server that remembers across sessions, forgets what stops mattering, and consolidates the rest — modeled on how the hippocampus actually works. Works with any MCP client. Runs locally from the sharpwave npm package.

Enlightened-Republic/sharpwave · not measured

mcp

Owned, portable working memory: a plain-files markdown brain any model can read and cite. Runs locally from the @br8n/mcp npm package.

Branded-Mayhem-Collective-LLC/br8n · not measured

mcp-server

MCP server for MemoryPlugin API integration. Runs locally from the @memoryplugin/mcp-server npm package.

memoryplugin/mcp-server · not measured