Software Engineering Tools

QApilot MCP automates tests on real Android devices and emulators by talking to Claude, Cursor or Codex. Describe a test flow in plain English, no Appium code required. Your agent lays out the steps. QApilot runs the steps. It finds the elements, waits for the screen to settle, retries when something moves, and caches what it learns so repeat runs are faster. Every pass saves a Gherkin feature file and becomes a replayable test case. Needs Node, Java and the Android SDK.

Cline Desktop gives you an open-source workspace to put your favourite model to work - run multiple agent sessions, automate recurring tasks, extend their capabilities through Cline’s Marketplace, and continue work from agents like Claude Code and Codex. Choose the models and providers that work best for you, while Cline’s agent harness, optimized for open-weight models, powers the work behind them. All without being tied to a closed ecosystem.

Open-source AI gateway in Go. One OpenAI-compatible API for every provider, with budgets, caching, guardrails, load balancing, and failover. Single binary, ~20MB docker image MIT, bring your own keys. A self-hosted alternative to OpenRouter and LiteLLM.

Airuncode is a local-first agent runtime for serious software work. Run multiple coding agents on your machine, bring your own API keys, switch between cloud and local models, and pay providers directly with zero token markup. It scans your codebase, debates solutions across agents, edits files, runs tests and self-heals failures. It also ships with V-CORE, a native Vulkan 3D runtime for AI-assisted game development. Available on Windows, macOS and Linux.

PR Lens is a new way to look at code. It draws animated architecture and data flow diagrams of any codebase and every pull request, so you see the change before you read a single line of code. It runs as a GitHub Action, on the CLI, or as a skill for your coding agent. Open source under MIT.

Kit is a coding agent runtime. It gives the model one tool for writing and running programs. Kit provides a terminal client, an Agent Client Protocol (ACP) server, an A2A endpoint, and a subagent orchestrator in one static binary. ACP separates agent clients from agent runtimes, so Kit works in compatible editors and can orchestrate other harnesses without custom integrations.

Tadata is the AI employee that lives in your Slack. It connects to your tools, learns your company and your preferences, and does work for your team.

Porte is an open-source phone remote control built specifically for Grok Build. Pair your phone with your machine, then read live transcripts, send prompts and files, run slash commands, stop turns, and answer permission requests.

VaultBob brings true user sovereignty to your dev workflow. We teamed up with Amazon Web Services (AWS) to build a NEW end-to-end Zero-Knowledge Architecture for code repositories.  Unlike GitHub or other platforms that hold your keys, VaultBob encrypts your source code, configuration files, and deep local AI context directly on your machine before upload. Your encryption key never leaves your device. Secure, versioned snapshots with zero third-party risk. #PowerToTheUser 🌲

Kilo Code for JetBrains is a fully native, open-source coding agent for IntelliJ IDEA, WebStorm, PyCharm, GoLand, Rider, PhpStorm, CLion, RubyMine — any JetBrains IDE. Designed for both local and remote dev, with parallel agents in isolated worktrees, GitHub PRs and diffs inline, and 500+ models.

Different work needs different AI oversight, and Revolte gives you both. Our Interactive Sessions let you drive the full lifecycle with the agents, step by step: architecture, code, tests, staging, deploy. You approve every step. Autopilot mode hands off a Jira ticket end-to-end, with agents planning, coding, opening the PR, and deploying. Same workspace, same governance: plan approval, inline diffs, cost caps, and audit trails, built in. Hands-on when you want control, hands-off when you don't.

Coding agent can create huge code diffs. Someone still has to read it. seendiff is a local diff tool for large changes. Track what you've seen, review in chunks, and pull the coding agent in to explain its own work.

Introducing OpenComputer Deploy your agent as a function. Get a computer for it. - a real Linux machine per session - ffmpeg, chromium, git, install anything - durable: hibernate + resume - your keys never enter the runtime The cloud of the last decade was built for apps. The next one is for trillions of always on agents. OpenComputer is their home.

Alchemize is an AI code review platform that helps teams understand and test code. Agentic coding has 10x’d code output, creating larger PRs more frequently, but existing review workflows haven’t kept up. Alchemize breaks large changes into smaller, dependency-ordered PRs and guided reviews. It surfaces the prompts, intent, and assumptions behind agent-written code, then uses browser agents to test affected workflows.

Not only can AI agents build your UI, they can now test what it actually looks like. Buddy Visual Tests captures every UI change, compares it pixel by pixel with an approved baseline, and brings visual regression testing straight into your delivery flow. With CLI, MCP and Skills support, agents can spot visual bugs, fix them, rerun tests, and hand over intentional changes for human approval.

Lucid Train generates architecture diagrams from your codebase, then hands the diagram to a coding agent as a specification. Local models, fully offline.

Decawork is how IT teams take employee-built AI agents live and control every one of them from one place. An employee builds an agent on Claude Code, Codex, or any vibecoding tool; we take it in, put it on company accounts, and run it as a company asset. From there, IT team manages the agent like an employee: access, oversight, retirement.

Docker manager for one host or a whole fleet. - Manage local, remote TLS, and NAT'd/VPS hosts from one UI - Deploy & update Compose stacks, incl. from Git with auto-sync - Live logs, metrics, and an in-browser container shell - Scan every image for CVEs (Grype/Trivy) before it ships - Inject secrets from 1Password, Vault, Infisical, Doppler - Encrypted backups to local, S3, or GCS - Semver update badges with release notes - SSO, LDAP, and role-based access Hardened and free.

Antigravity IDE Extensions bring Google’s agentic coding platform into VS Code, Visual Studio, JetBrains, and Zed. Keep your agent conversations and shared context while reviewing inline diffs, inspecting plans, debugging code, and handing off multi-step tasks without leaving your editor.

bitdrift AI is the world’s first agentic mobile observability platform: a real-time, full-fidelity observability system that lets AI agents query mobile user behavior and act on it autonomously. It's built on the bitdrift Public API and bd skills. User journeys, performance metrics, and behavioral changes are all available when your agent needs them, not ten days later waiting for an app release. Early users of bitdrift AI report faster investigations and a 10x improvement in MTTR.

Cronloop lets you create AI agents that run in a loop, from every five minutes to once a week. Just describe the job in plain Markdown, pick Codex or Claude Code, connect your tools, and you're done. Every agent has a durable memory system and can self-improve each run. Create your first agent for free today.