Start with the job, then find an open-source answer

Kilo Code works in VS Code, JetBrains, and the terminal to generate multi-file changes, autocomplete code, run commands, and automate browser tasks. You can switch models during a task and choose specialized agents for planning, debugging, questions, or review. Its autonomous CLI mode removes permission prompts, so it should be limited to trusted environments.

Qwen Code is an open-source coding agent for the terminal with Auto-Memory, Auto-Skills, subagents, agent teams, and MCP. It supports interactive and headless use, an experimental shared daemon, and providers using OpenAI, Anthropic, Gemini, Qwen, or local-model-compatible APIs. The project also ships IDE, desktop, SDK, and IM integrations; Node.js 22 or newer is required for the npm installation path.

Dashy gives homelab and self-hosting users a central homepage for launching services, checking their status, and viewing information through widgets. It supports multiple pages, search and keyboard shortcuts, extensive themes and icons, a UI editor, and optional multi-user authentication with configurable privileges. Docker is the common deployment path, while several cloud platforms are also supported. Persistent deployments need a user-data directory containing at least the main configuration file.

Zulip is an open-source team chat server and web application built around topic-based threads. Messages stay grouped by subject, helping teams combine real-time discussion with asynchronous work without losing the surrounding context. The project is used by remote teams and open-source communities, and organizations can try the public development chat or follow the documentation to run their own service.

AI SDK lets TypeScript developers call multiple model providers through a consistent API for text, structured output, agents, and generative interfaces. It works with frameworks such as Next.js, React, Svelte, and Vue, either through Vercel AI Gateway or direct provider packages. Local development requires Node.js 22 or newer.

Store task plans, findings, and progress in Markdown files so coding agents can recover after context loss, session clearing, crashes, or handoffs between workers. Optional lifecycle hooks remind the agent to reread and update the plan, while gated modes prevent it from stopping before explicit completion conditions are met. The skill works across many SKILL.md-compatible coding agents and supports shared state for multi-agent work.

Frontend Slides helps non-designers build web presentations by generating visual style previews first and letting the user choose a direction before the full deck is produced. It can also extract text, images, and notes from a PowerPoint file and rebuild them as a 16:9 HTML presentation with inline CSS and JavaScript. Optional scripts deploy the deck or export a static PDF; PowerPoint conversion requires Python and python-pptx.

Responsively App is an Electron-based browser for testing responsive layouts across several device profiles at once. It mirrors interactions between previews, provides a customizable arrangement and a shared element inspector, includes more than 30 built-in profiles plus custom devices, and captures screenshots across every preview in one click. Hot reloading is supported on Windows, macOS, and Linux.

NextAI Translator works as a browser extension and a desktop app for Windows, macOS, and Linux. It can translate selected text or screenshots, polish writing, summarize content, and organize vocabulary across many languages. The app relies on a supported LLM provider, so users need to supply a compatible OpenAI, Azure OpenAI, or other available API key.

Meetily records and transcribes meetings on your device, keeping recordings, transcripts, and transcription models local for privacy-sensitive work. Summaries can stay fully local through Ollama or use Claude, Groq, OpenRouter, or a custom OpenAI-compatible endpoint. Installers are available for macOS and Windows, while Linux users build from source.

cmux is a Ghostty-based native macOS terminal for organizing coding-agent work across vertical tabs, split panes, browser surfaces, and notifications. Its CLI and Unix socket can create workspaces, send keystrokes, inspect screens, and drive the built-in browser, while session restore keeps layouts and supported agent sessions available after relaunch. It is licensed under GPL-3.0-or-later and is currently a macOS application.

awesome-n8n-templates is a collection of more than 280 importable workflows organized across email, messaging, cloud storage, social media, DevOps, document processing, RAG, research, and AI-agent use cases. It helps users start from working examples and adapt nodes instead of building every automation from an empty canvas. The repository is not an automation runtime itself: users still need an n8n instance and must supply the accounts, credentials, databases, or model APIs required by each workflow.

Dockge manages compose.yaml-based stacks through a web interface for creating, editing, starting, stopping, restarting, and updating services, with live progress and terminal output. Compose files remain in a normal directory structure and can still be used with standard Docker Compose commands, while agents can connect multiple hosts. It targets Linux stack management and is not intended for standalone containers without compose.yaml.

Letta offers a CLI and TypeScript Agent SDK for running agents with advanced memory, either fully locally, in its cloud, or against a self-hosted App Server. This repository mainly retains the legacy Letta Server behind the V1 API and SDKs; active development has moved to the Letta Agent repository, and new projects are encouraged to use the newer Agent SDK.

The MCP Python SDK turns Python type annotations into tool schemas and offers both server and client APIs for in-memory, stdio, and remote HTTP connections. It supports the standard MCP transports and is suited to building or testing protocol integrations. The documented v2 line is a breaking-change-prone prerelease, so v1.x remains the stable production choice.

Beszel collects server and Docker or Podman metrics through a central web hub and a lightweight agent installed on each monitored system. Its dashboard records historical CPU, memory, disk, network, temperature, GPU, and container data, with configurable alerts for operational thresholds and outages. The self-hosted platform also supports multiple users, OAuth or OIDC authentication, and automatic backups to local disk or S3-compatible storage.

Open Generative AI combines image, video, audio, lip-sync, and workflow tools in a shared creative interface. Users can call hosted models or connect local inference engines, with desktop installers for macOS, Windows, and Linux as well as a hosted browser version. Cloud generation generally requires an account and API key, while local models require suitable hardware and additional runtime setup.

NocoBase is an open-source no-code platform for assembling business applications such as CRM, ERP, and internal operations tools. Teams can configure data models, pages, workflows, and permissions in a visual interface, while coding agents can assist with setup, development, and migration. AI actions follow the same role and audit boundaries as human users, and the platform can work with owned databases, external databases, APIs, and an extensible plugin model.