Culprit SQL Studio is a desktop application, command-line tool and MCP server that finds the queries slowing down a database and explains what is slow, what it costs and how to fix it in one sentence. It supports SQL Server, PostgreSQL, TimescaleDB, YugabyteDB, MySQL, MariaDB and SQLite. It is aimed at developers and coding agents who need to diagnose database performance without installing anything on the server.
Culprit reads the statistics a database already keeps, such as catalog and statistics views, Query Store, plan cache, DMVs, Extended Events, pg_stat_statements and performance_schema, depending on the engine. Scans are read-only with short lock timeouts, and estimated plans never run anything. On a production connection, any statement that is not provably read-only asks for approval before running, and suggested fixes are shown but never applied automatically.
Findings rank slow queries, missing indexes, unsafe migrations, lock pile-ups and query regressions by their share of database time, each with supporting detail, a production-safe fix and a way to verify it. Execution plans are explained in plain words with a diagram of where the cost goes, and two plans can be compared or a virtual index tested with HypoPG before it is built. A "What changed" view compares two periods and lists what got slower or improved.
Culprit SQL Studio runs on macOS, Windows and Linux, with a separate command-line binary and an MCP server that gives Claude Code, Codex and Cursor 27 tools, including dashboard, findings, execution plans and migration linting. It is free and open source under the MIT license, with no account, cloud or telemetry; passwords are kept in the OS keychain. The Windows installer is not yet code-signed.
Adaptive Engine evaluates, tunes, and serves LLMs for enterprise AI, using reinforcement learning to optimize models and production feedback.
Prompt Octopus compares model responses side-by-side, with a VSCode extension and API key options for use in your codebase.
Antigma provides self-contained, self-organizing agents for developers, with Ante as an autonomous coding agent that runs locally or cloud-backed, in a terminal and via various interfaces.
Lingo.dev is a localization engineering platform for product teams to measure translation quality, choose translation providers, and manage localization…
Zipy provides AI-powered session replays, error tracking, performance monitoring, and product analytics for developers and product teams.
Miko is a self-hosted AI coding agent that connects Slack, Linear, GitHub, and GitLab to coding agents, enabling task assignment and pull-request reviews.