The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Download the installer from the Releases page and run it:
tabularis_x.x.x_x64-setup.exe
Follow the on-screen instructions to complete the installation.
macOS
Homebrew (Recommended)
To add our tap, run:
brew tap TabularisDB/tabularis
Then install:
brew install --cask tabularis
Direct Download
Builds from v0.13.1 onward are signed and notarized by Apple, so they open without any extra steps.
The notes below only apply to older releases (before v0.13.1) downloaded directly:
You need to allow accessibility access (Privacy & Security) to the tabularis app. If you are upgrading and already have tabularis on the allowed list, remove it manually before accessibility access can be granted to the new version.
You may need to run xattr -c /Applications/tabularis.app after copying the app to the Applications directory.
Tabularis is hackable with an external plugin system. Plugins are standalone executables that communicate with the app over JSON-RPC 2.0 via stdin/stdout, and can be written in any language.
Install Plugins: Browse and install community drivers from Settings → Available Plugins — no restart required.
Manage Drivers: View all registered drivers (built-in and plugins) in Settings → Installed Drivers and uninstall plugins with one click.
Any Database: Add support for DuckDB, MongoDB, or any other database by writing or installing a plugin.
Configuration is stored in ~/.config/tabularis/ (Linux), ~/Library/Application Support/tabularis/ (macOS), or %APPDATA%\tabularis\ (Windows): connection profiles, saved queries, app settings (config.json), custom themes, and per-connection editor preferences — tabs and queries are restored when you reopen a connection. The wiki covers the full file layout and every config.json option, including custom AI model overrides.
Optional Text-to-SQL and query explanation powered by OpenAI, Anthropic, MiniMax, OpenRouter, Ollama (local models, no API key, full privacy), and any OpenAI-compatible API (Groq, Perplexity, Azure OpenAI, LocalAI, ...). Model lists are fetched from your provider and cached locally; custom models can be configured per provider.
Tabularis includes a built-in MCP (Model Context Protocol) server that lets AI agents read your database schema and execute queries directly from their chat interface.
tabularis --mcp
One-click setup for Claude Desktop, Cursor, and Windsurf: open Settings → MCP Server Integration, click Install Config next to your client, and restart it. Manual configuration is covered in the wiki.
Available tools
Once connected, your AI agent can:
Tool
Description
list_connections
List all saved database connections
list_tables
List tables in a connection (with optional schema filter)
describe_table
Get full schema: columns, indexes, foreign keys
run_query
Execute any SQL query and return results
Example prompts
"Show me all tables in my production database and describe the orders table"
"Write and run a query to find the top 10 customers by total order value this month"
"Check if there are any missing indexes on the users table"