Upvoted Tools

GitLab's agentic AI layer that orchestrates specialized agents and flows across planning, coding, review, security, and CI/CD.

A macOS security layer that checks AI agent actions, tool calls, skills and file access against a policy and returns allowed, flagged or blocked verdicts.

An open, reproducible benchmark and leaderboard for evaluating AI code review agents on real-world pull requests.

Open-source multi-agent harness that lets Claude Code, Codex, and Pi work together as a persistent, coordinated team on long-running software projects.

A desktop UI for coding agents that lets you run Claude Code, Codex, Cursor, OpenCode, and more from a single tabbed interface.

Open-source agent harness from DeepSeek with a plugin-based architecture, available as a desktop app and local web UI.

A desktop workspace for building software with AI coding agents like Claude Code, Codex, Grok Build, Antigravity, and OpenCode.

A Claude Code skill that generates 27 types of editorial-quality, brand-matched diagrams as self-contained HTML/SVG files — no Figma, no generic templates.

A compact 144.3M-parameter multilingual decision model from Supersonic Labs that classifies, ranks, and answers yes/no questions by choosing among supplied options, running on CPU.

An open-source library for efficient, flexible, and portable structured generation for LLMs, enabling near-zero overhead constrained decoding with support for JSON, regex, and custom context-free grammars.