ReMe is a local-first memory management system that turns conversations and other resources into searchable, editable Markdown knowledge shared across AI agents. It is for users and agent runtimes that need durable, interconnected knowledge they can inspect and maintain. The catalogue add-ons connect coding agents and other agents to ReMe through skills, hooks, plugins, MCP, and related interfaces.
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.
git clone --depth 1 https://github.com/agentscope-ai/ReMeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/agentscope-ai/reme/reme-reme)<a href="https://agentmods.dev/mcp/agentscope-ai/reme/reme-reme"><img src="https://agentmods.dev/badge/mcp/agentscope-ai/reme/reme-reme.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
reme 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 7d ago.
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.
What it actually says
{
"reme": {
"type": "http",
"url": "http://127.0.0.1:2333/mcp"
}
}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.
- 7d ago First seen · 6 lines scan A 0075f0b85a72
reme is an MCP server published in the GitHub repository agentscope-ai/ReMe (3,416 stars, last pushed 2d ago), licensed Apache-2.0. 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 2026-08-30.
Other mcp servers, from other repositories
cortxai
A self-hosted brain for your home, your company, or any activity: pluggable local or cloud LLMs, hybrid memory, and an expandable plugin surface. Runs locally from the cortxai Python package.
telemem
Long-term & multimodal memory for AI agents — character isolation, video pipeline, MCP server, mem0-compatible. Runs locally from the telemem Python package. Needs 3 environment variables to run.
rag-rat
CLI and MCP entrypoint for indexing repositories into local source, graph, history, and memory evidence. Runs locally from the @rag-rat/bin npm package.
coalent
A real-time, provenance-invalidated cognitive cache layer for AI agents and RAG. Runs locally from the coalent Python package. Needs 2 environment variables to run.
akb
AKB MCP stdio client — connect any AI agent to AKB knowledge base. Zero dependencies, auto-reconnect. Runs locally from the akb-mcp npm package. Needs 2 environment variables to run.
origin-memorycore
MCP server "origin-memorycore" as configured in moonandecho/origin-memorycore. Runs locally from the origin-memorycore Python package.