Food Checker lets users take a photo of a food product’s ingredients list and get a safety score (1-100), risk flags (e.g. additives, high sodium), and explanations in plain language. Results adapt to the user’s allergies or health conditions. First few scans are free!

Food Checker: Ingredients Scan

food-checker-ingredients-scan

Scan food labels to get a safety score and alerts based on ingredients, allergies & health conditions.

Mastra is an all-in-one TypeScript framework for building AI-powered applications and agents. It supports core agent patterns like tools, workflows/orchestration, RAG, memory, MCP integration, and evals, designed to go from prototype to production inside your own codebase. Mastra also offers an optional Mastra Cloud/Platform experience with a Studio for testing agents and workflows plus AI-focused observability (structured logs, tracing, and eval dashboards) and deployment integrations.

Mastra

mastra

Open-source TypeScript framework for building AI agents, workflows, RAG, memory and MCP, with optional cloud studio and observability.

OpenCode is an open-source AI coding agent designed to help developers plan, implement, and refactor code from a terminal-first workflow, with options to use it as a desktop app or IDE extension. It can connect to multiple model providers (or use included free models), apply changes across a codebase, and support common developer flows like asking questions, adding features, making edits, and undoing changes. OpenCode also integrates with GitHub workflows: you can mention a command in issues or pull requests to have it execute tasks inside a GitHub Actions runner.

OpenCode

opencode

Open-source AI coding agent for terminal, desktop, and IDEs—plans changes, edits code, and can run tasks in GitHub via comments.

Agent S is an open-source framework for building and running “computer use” GUI agents that can autonomously operate a computer through an Agent-Computer Interface. It’s designed to let an LLM plan and execute multi-step tasks by observing the screen and taking actions (e.g., clicking, typing, navigating) on supported platforms (Linux, macOS, Windows). The project provides a CLI to run the agent, supports multiple model providers (including OpenAI, Anthropic, Gemini, OpenRouter, and vLLM), and recommends pairing a main LLM with a separate grounding model for UI understanding. Agent S also includes evaluation assets and reports results on established computer-use benchmarks such as OSWorld.

Agent S

agent-s

Open-source GUI agent framework that lets an LLM use your computer like a human via an Agent-Computer Interface.

PubNub MCP Server is a CLI-based Model Context Protocol (MCP) server that connects MCP-compatible AI assistants (like Cursor, VS Code, Claude Code, Codex, and others) to PubNub’s SDK documentation and PubNub account/API resources. It helps agents retrieve SDK and Chat SDK documentation across many languages, manage PubNub apps and keysets (including enabling features like persistence, files, presence, and app context), and perform real-time operations such as publish/subscribe, signals, presence, and user/channel objects. The server supports dynamic mode (keys provided per tool call) and fixed mode (publish/subscribe keys set via environment variables) and can be installed via npm or run via Docker, with authentication typically provided using a PubNub API key.

PubNub MCP Server

pubnub-mcp-server

MCP server that lets AI coding assistants access PubNub docs and manage apps/keysets, plus messaging, presence, and channel/user objects.

Desktop Commander MCP is an open-source Model Context Protocol (MCP) server that gives AI clients controlled access to your local development environment. It enables running terminal commands with streaming output and interactive process/session management, plus full filesystem operations like reading/writing files, creating directories, and recursive search. It includes diff-based “surgical” edits and pattern-based replacements, powered by ripgrep for fast repo-wide search. The tool also adds native Excel support (read/write/edit/search) and PDF tooling (extract text, create PDFs from markdown, and modify PDFs), along with comprehensive audit logging of tool calls for traceability.

Desktop Commander MCP

desktop-commander-mcp

MCP server that lets AI run terminal commands, manage processes, and search/edit files (diff-based) with Excel/PDF support and audit logs.

FLAMEHAVEN FileSearch is an open-source, self-hosted RAG document search engine you can run locally (Docker or Python). It supports multi-format ingestion (PDF, DOCX, TXT, MD) and provides keyword, semantic, and hybrid search modes (with typo correction). Results include source attribution, and the API includes production features like API-key authentication with permissions, rate limiting, audit logging, batch search, and an admin dashboard. It integrates with Google Gemini (via GEMINI_API_KEY) and supports a lightweight local store plus optional components such as Redis caching and Postgres/pgvector for higher-performance deployments.

FLAMEHAVEN FileSearch

flamehaven-filesearch

Self-hosted RAG file search engine (FastAPI) with keyword/semantic/hybrid modes, citations, API keys, and Docker quickstart.

Gobii is a platform for creating “digital workers” (always-on browser agents) that can perform repetitive web-based tasks automatically. You can create custom workers or spawn pretrained ones, run them on schedules, and connect them to workflows through triggers and APIs. For developers, Gobii provides a cloud browser automation stack (persistent agents/sessions, webhooks, and integrations) and also supports self-hosting through its open-source codebase for teams that want more control over infrastructure and data residency.

Gobii

gobii

Always-on browser workers that automate web tasks via schedules, triggers, and API—run in the cloud or self-host open source.

Nano Banana (nanobananaimg.com) is a web platform for AI-powered image creation and editing using natural-language prompts. It offers text-to-image generation and text-based image editing, highlighting capabilities like multi-image fusion, character consistency, and targeted transformations. The platform also includes AI video features such as image-to-video generation with model choices and controls like start/end frame inputs, plus additional creative utilities (e.g., image enhancement and background removal) to streamline content creation workflows.

Nano Banana

nano-banana

AI image generation and editing with text prompts, plus image-to-video tools using multiple video models in one web studio.

AniFun AI is a web-based anime creation platform that helps users generate anime-style images, manga pages, and short anime-style videos using AI. It offers tools like text-to-anime image generation, photo-to-anime conversion, anime-to-real transformations, manga page generation with layouts, and image-to-video workflows. The product emphasizes fast creation with no complicated setup, plus a broad suite of creator-focused utilities (filters, sketch tools, upscalers, extenders, and more) to move from an idea to shareable anime content quickly.

AniFun AI

anifun-ai

Free anime creation platform for generating anime art, manga pages, and anime-style videos from text or images—no setup required.

APIx420 is a production-ready API gateway designed for AI agents, exposing 100+ real-time data endpoints via an MCP server interface and standard HTTP APIs. It focuses on agent-friendly utilities and live data across crypto and Web3 (prices, gas, balances, DeFi stats, NFTs), plus general-purpose tools like weather/air quality, news, domain/DNS/WHOIS, network utilities, geography, conversions, text analysis, and reference lookups. The service is pay-per-call and mentions USDC micropayments, with an MCP endpoint that advertises 100+ available tools and a broad set of categories for programmatic discovery.

APIx420

apix420

Pay-per-call API gateway with 100+ real-time data endpoints for AI agents, available as an MCP server (USDC micropayments).

Playwright MCP is an open-source Model Context Protocol (MCP) server from Microsoft that exposes Playwright-powered browser automation as callable tools for AI agents. Instead of relying on screenshots or visually-tuned models, it provides structured page state (including accessibility snapshots) so an LLM can reliably understand and interact with live web pages—clicking, typing, waiting for selectors, navigating, and validating outcomes. It’s useful for AI-assisted web testing, agent-driven site exploration, and automations that need a real browser environment with deterministic, tool-based control.

Playwright MCP

playwright-mcp

An open-source MCP server that lets LLMs automate real browsers with Playwright using structured accessibility snapshots (no screenshots needed).

Explore AI Agents