Amnesic

Created By
SurajKGoyal4 days ago
Persistent semantic memory for SQL databases (Postgres, MySQL, MSSQL, SQLite). Annotate once, remember forever.
Overview

amnesic

Persistent semantic memory for your SQL databases. The name is ironic — it remembers everything.

Every session with an AI starts cold: you re-explain what tables exist, what a status value of 3 means, which foreign key connects orders to users. amnesic fixes this with a local SQLite knowledge store — one per database — that survives across sessions. Annotate an enum once; every future session sees those labels automatically.

🔒 Read-only by design

Safe to point at production. Two independent layers: static SQL analysis rejects any write/DDL statement before connecting, and every query runs inside a transaction that is immediately rolled back. Credentials never appear in tool responses.

Supported databases

PostgreSQL · MySQL / MariaDB · Microsoft SQL Server · SQLite

Tools

ToolDescription
db_list_connectionsList configured connections (no secrets)
db_list_tablesAll known tables with descriptions
db_searchBM25 search over table/column knowledge
db_get_schemaColumn schema merged with saved annotations
db_queryExecute a read-only SELECT
db_annotatePersist semantic annotations (enum meanings, FKs)
db_sync_knowledgeCopy annotations between connections (staging → prod)
db_discover_relationshipsDiscover all FK relationships from the live DB
db_get_relationshipsNavigate the FK graph for JOIN planning

Install

pipx install amnesic
amnesic init        # interactive setup wizard

Server Config

{
  "mcpServers": {
    "amnesic": {
      "command": "amnesic"
    }
  }
}
Project Info
Created At
4 days ago
Updated At
4 days ago
Author Name
SurajKGoyal
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Gpt Scrambler

2 days ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago