Find the open-source solution that fits.

Project overview

Cognee turns ingested data into a self-hosted knowledge graph that agents can remember and query across sessions. Developers use its Python API or CLI to remember, recall, forget, and improve information, combining semantic retrieval with graph relationships. It can run locally, in Docker, through Cognee Cloud, or on a consolidated PostgreSQL memory layer; an LLM provider key is normally required for local setup.

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

Nuclear is an open-source music player for Windows, macOS, and Linux that searches for songs and artists, manages queues, and builds playlists without ads or tracking. Plugins can add streaming sources, metadata, and playlist integrations, while its optional MCP server lets compatible AI clients control playback.

Project overview

Desktop Commander MCP equips clients such as Claude with local terminal execution, filesystem search and editing, process sessions, long-running commands, and support for formats including Excel, PDF, and DOCX. It can be installed through npx or run in Docker. The server is not itself a security sandbox: allowed-directory settings restrict file tools but do not fully contain terminal commands. Docker isolation and narrowly mounted folders are therefore important when working with untrusted tasks.

Project overview

tradingview-mcp exposes market quotes, screeners, technical indicators, sentiment, and strategy backtests for stocks, crypto, forex, and futures through MCP. It can be self-hosted for free or used through a managed connector. The server does not sign in to TradingView or place trades, and it is an independent project using third-party data that may be delayed or incomplete; its outputs are informational rather than financial advice.

Project overview

tradingview-mcp bridges Claude Code or a terminal CLI to a local TradingView Desktop session through Chrome DevTools Protocol. It supports Pine Script iteration, symbol and timeframe navigation, indicator reading, chart drawing, alerts, replay practice, screenshots, and JSONL monitoring. A valid TradingView subscription is required, and the desktop app must be launched with its debugging port enabled. The project is an interface for personal, educational, and research workflows rather than an autonomous trading bot, and users remain responsible for complying with TradingView's terms.

Project overview

SurfSense gives competitive-intelligence agents live connectors for social platforms, search, maps, and the open web through REST APIs or MCP. Scheduled and event-triggered agents can combine sources into cited briefs and alerts, then keep findings in a searchable knowledge base. The platform, including connectors, automations, and the MCP server, can be self-hosted with Docker, but the project states that it is still under active development and not yet production-ready.

Project overview

Work Review runs in the background to record foreground applications, visited pages, window titles, and time spent, with optional screenshots and OCR text. The same local records feed a timeline, statistics, questions about the day, and structured reports that can be edited or exported as Markdown. Data is stored in local SQLite by default, and AI features are optional and use the user's configured model credentials. On macOS, screenshots and some context-linking features require Screen Recording and Accessibility-related permissions.

Project overview

Install one Python package to get both a command-line client and an MCP server for NotebookLM. You can create notebooks, add URL, text, Drive, or file sources, run queries, start web or Drive research, generate Studio content, and download resulting artifacts. Batch operations, cross-notebook queries, sharing, and Drive-source synchronization make it useful for scripts and AI assistants that need more than the web interface.

Project overview

Koharu combines text and speech-bubble detection, OCR, inpainting, translation, and typesetting into a manga translation workflow. It handles vertical CJK and right-to-left text and can export layered PSD files with editable lettering. The app runs with a GUI, headless server, or MCP interface, using either local llama.cpp models or remote providers on Windows, macOS, and Linux.

Project overview

Education Agent Skills Library contains 165 pedagogical skills across 20 domains. The first 19 support teachers and learning designers, while the twentieth defines live interaction patterns for how an AI should respond to learners during study sessions. It works with Claude, Codex, Hermes, and compatible tools; local or plugin installation is the recommended free path, while the hosted MCP endpoint requires an access token.

Project overview

Windows-MCP exposes Windows computer-use capabilities to MCP-compatible agents. Its tools cover clicking, typing, scrolling, dragging, shortcuts, screenshots, UI and display state, application and window control, and other system actions without requiring a particular vision model. It can run through uvx over stdio or an explicitly bound HTTP transport. Because the server operates with full system access and can perform irreversible actions, deployments should use authentication, IP and tool allowlists, and other restrictions; anonymized telemetry can be disabled.

Project overview

Hercules converts readable Gherkin feature files into automated end-to-end browser tests, using Playwright to interact with web applications and producing JUnit XML and HTML reports. It is useful for QA or business teams that want to describe behavior without writing test code. The agent can consume tools from external MCP servers or run as an MCP server that exposes test generation, execution, and result retrieval.

Project overview

LichtFeld Studio combines 3D Gaussian Splatting training, real-time inspection, selection editing, and export in one native workstation. Users can train from COLMAP datasets, resume checkpoints, transform Gaussian subsets with history support, and deliver PLY, SOG, SPZ, or a standalone HTML viewer. Python plugins, embedded scripts, and MCP tools support extension and automation. Prebuilt distribution focuses on Windows and NVIDIA GPUs. Source builds use C++23 and CUDA 12.8 or newer, while current Windows builds also require a recent NVIDIA driver.

Project overview

Automatically chunk, embed, tag, and connect Markdown notes by semantic similarity, then search them by meaning, explore them on a graph canvas, or synthesize cited wiki articles and recurring reports. Atomic runs as a desktop app or self-hosted server and exposes MCP tools for other assistants; semantic and generative features require Ollama, OpenRouter, or another OpenAI-compatible provider.

Project overview

Browserbase MCP Server gives compatible assistants a small set of tools for starting cloud browser sessions, navigating pages, performing actions, observing interactive elements, and extracting information. The hosted HTTP endpoint is the easiest setup, while self-hosted deployments can run through NPM or Docker. These deployments still require a Browserbase API key and project ID, and choosing a model other than the default also requires that provider's API key.

Project overview

ByteChef combines AI-agent orchestration, application connectors, and workflow automation in a visual environment. Users configure models and tools, then connect them with conditions, loops, parallel branches, schedules, webhooks, and other triggers; connectors can also serve as agent or MCP tools. Docker Compose runs the application with PostgreSQL for self-hosting. The community edition includes the core editor, agents, workflows, and connectors, while workflows exposed as APIs and Git-native management are reserved for the enterprise edition.

Project overview

Google Calendar MCP Server lets an AI assistant query multiple accounts and calendars together, detect conflicts, check free or busy time, and create, update, delete, search, or respond to events, including recurring ones. It can also derive events from images, PDFs, or web links, and administrators may expose only selected tools. Setup requires a Google Cloud project with the Calendar API enabled, desktop OAuth credentials, and an initial browser authorization; test-mode tokens normally expire after seven days.