Find the open-source solution that fits.

Project overview

Inbox Zero uses natural-language rules to organize an inbox and pre-draft replies in the user’s tone. It can track messages that need a response or are awaiting one, bulk-unsubscribe and archive unwanted mail, block cold email, prepare meeting briefs from email and calendar context, and file attachments to cloud storage. Users can also manage the inbox through Slack or Telegram. A hosted service is available; self-hosting uses the project’s setup CLI and requires Docker and Node.js 24 or newer.

Project overview

Onyx is a self-hosted AI workspace for teams that want to use different LLMs through one interface and ground answers in organizational knowledge. It can index application data through more than 50 connectors or connect agents to external systems through MCP, with additional support for research workflows and code execution. Lite mode keeps a smaller chat-and-agents stack, while the standard deployment adds vector and keyword indexes plus background synchronization workers for a fuller knowledge workflow.

Project overview

World Monitor combines hundreds of curated feeds with military, economic, disaster, escalation, and market signals in a map-based situational dashboard. Users can access it through the web, desktop app, CLI, REST API, or MCP server; the base app starts without environment variables, while some data sources need credentials, and local AI is available through Ollama.

Project overview

Readest opens EPUB, MOBI, AZW3, FB2, CBZ, TXT, and PDF files across macOS, Windows, Linux, Android, iOS, and the web. Readers can switch between scrolling and paginated layouts, search within books, add bookmarks, highlights, and notes, look up terms, or place two documents side by side. It is designed for people who want a consistent reading workflow across several device types.

Project overview

SigNoz gives engineering teams one place to investigate application and infrastructure problems through correlated logs, metrics, traces, alerts, exceptions, and dashboards. Its OpenTelemetry-based workflow also covers LLM applications, including prompts, tool calls, latency, token usage, and cost signals. Teams can use the managed cloud offering or self-host the community edition with Docker, Kubernetes, or Linux when they need control over the telemetry data plane.

Project overview

Dokploy is a self-hosted platform for deploying and operating applications, databases, and Docker Compose workloads from one control plane. Installed on a VPS, it can create common databases, automate external backups, monitor resource usage, and launch packaged open-source services from templates. Teams can extend deployments across multiple or remote servers with Docker Swarm, and automate operations through its CLI and API. It is aimed at users who want a Vercel- or Heroku-like workflow while retaining infrastructure control.

Project overview

Cachet is an open-source status-page system that organizations can host themselves to communicate service health and incidents. The documented requirements include PHP 8.3 or newer, Composer, and a supported MariaDB, MySQL, PostgreSQL, or SQLite database. The project is rebuilding its 3.x line, so operators should follow the matching installation documentation rather than assume older deployment instructions still apply.

Project overview

changedetection.io watches web pages, PDFs, and JSON endpoints for meaningful changes such as price drops, restocks, or new text, then sends alerts through email, Discord, Slack, Telegram, webhooks, and many other services. Visual selectors and browser steps help target dynamic or logged-in pages. Optional AI rules can suppress irrelevant diffs and summarize changes, but monitored content is sent to the model provider you configure.

Project overview

OpenKnowledge is a local-first Markdown and MDX editor for notes, specifications, wikis, codebases, and Obsidian-style vaults. It opens an existing folder and provides WYSIWYG editing, navigation, search, tabs, wiki-link graphs, and side-by-side work with Claude, Codex, and other agent harnesses. A native macOS app is available, while Linux, Windows, and Intel Mac users can run the local web interface through its CLI with Node.js 24 and Git. Git-based sync and team sharing are optional.

Project overview

ToolJet Community Edition is an open-source low-code platform for building internal applications with drag-and-drop tables, forms, charts, and other responsive components. Teams can connect databases, APIs, SaaS products, cloud storage, and a built-in database, then add JavaScript or Python where custom logic is needed. It supports hosted use and several self-hosted deployment paths, including Docker and Kubernetes. Natural-language app generation, AI query building and debugging, and the Agent Builder are part of the enterprise ToolJet AI offering rather than the default community edition.

Project overview

Next AI Draw.io turns natural-language requests into editable draw.io diagrams and can use images, PDFs, or text files as source material. It keeps diagram history, runs as a web or desktop app, and exposes an MCP server for agent workflows. You need to configure an AI provider and API key, and complex diagrams benefit from models that reliably produce long, strictly formatted draw.io XML.

Project overview

Open WebUI provides a self-hosted interface for Ollama, local models, and OpenAI-compatible APIs, with built-in retrieval, user and group permissions, and an extensible plugin system. It can connect tools through MCP or OpenAPI and deploy through pip, Docker, or Kubernetes. Docker users need to mount the persistent data volume, or the application database can be lost when the container is removed.

Project overview

Open Design connects a local-first desktop workspace to coding agents through skills, a CLI, and an MCP server. It can generate web, desktop, and mobile prototypes, live dashboards, slide decks, images, video, and motion graphics, then preview them in a sandbox and export HTML, PDF, PPTX, or MP4 files. The app supports macOS and Windows, uses bring-your-own model credentials, and can also run headlessly from a compatible agent.

Project overview

Paseo runs a local daemon that manages Claude Code, Codex, Copilot, OpenCode, and Pi agents, then exposes them through desktop, mobile, web, and command-line clients. You can run agents in parallel on your own machines and pair a phone by QR code or use the headless server path. At least one supported agent CLI must already be installed and authenticated.

Project overview

Memos offers a timeline-first space for quickly capturing Markdown notes without navigating a folder hierarchy. It can run as a single Go binary or a small Docker deployment backed by SQLite, MySQL, or PostgreSQL. Notes remain portable, the application reports no telemetry, and REST and gRPC APIs make it practical to connect other tools and automations.

Project overview

Karakeep gives you a self-hosted place to collect links, quick notes, images, and PDFs for later use. It fetches page metadata automatically, supports lists and collaboration, and makes stored content searchable through full-text search and OCR. Optional language-model features can tag and summarize items, including through locally hosted models with Ollama.

Project overview

Documenso is an electronic document-signing application that can be used as a hosted service or deployed on infrastructure you control. Teams can run and inspect the code instead of relying entirely on a closed signing provider, with documented options for Docker, Kubernetes, and several cloud platforms. The project remains open source, although external pull requests are currently limited to contributors invited by the maintainers; other proposals should be filed as detailed issues.

Project overview

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.