A local memory system for AI coding agents that stores information in SQLite and supports vector search through MCP tools.

It is for saving project context, decisions, and other notes, then retrieving related information during later coding work.

It helps an agent retain and find useful information across conversations without sending the memory to a remote service. It requires one environment variable to run.

same — MCP server by sgx-labs

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/sgx-labs/statelessagent/same

Clone the repo

git clone --depth 1 https://github.com/sgx-labs/statelessagent

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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

same 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 · 12 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 · 12 lines scan A ab28050e162e

Subscribe to this mod's changes

same is an MCP server published in the GitHub repository sgx-labs/statelessagent (23 stars, last pushed 18d 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 2026-08-30.

Data and AI Databases Memory and context ai-agent claude-code cursor golang llm-memory mcp-server

agent-tool

MCP server "agent-tool" as configured in knewstimek/agent-tool. Launched with https://github.com/knewstimek/agent-tool/releases/download/v0.4.2/agent-tool.mcp.

knewstimek/agent-tool · not measured

smolanalytics

MCP server "smolanalytics" as configured in Arjun0606/smolanalytics. Runs in Docker (ghcr.io/arjun0606/smolanalytics:v0.90.0).

Arjun0606/smolanalytics · not measured

memex

MCP server "memex" as configured in kioie/memex. Runs in Docker (ghcr.io/kioie/memex:0.6.0). Needs 3 environment variables to run.

kioie/memex · not measured

tiny-go-mcp

MCP server "tiny-go-mcp" as configured in kioie/tiny-go-mcp-server. Runs in Docker (ghcr.io/kioie/tiny-go-mcp:1.1.2).

kioie/tiny-go-mcp-server · not measured

kireo

Long-term memory for Claude Code, Cursor and any MCP client, with a searchable web dashboard. Runs locally from the @kireo/mcp-server npm package. Needs 1 environment variable to run.

wang1051992187/kireo-mcp-server · not measured

mcp-guard

Security MCP server with 20 tools — 12 require local hardware. Wi-Fi/Bluetooth/USB enumeration, ARP LAN discovery, kernel FS events, process introspection, secret scanning, port scanning, TLS inspection, CVE checking. Runs locally from the @zent7x/mcp-guard npm package.

zent7x/mcp-guard · not measured