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.

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).

HIA (Health Insights Agent) is an open-source Streamlit app that lets users upload blood report PDFs and receive AI-generated, personalized health insights. It uses an agent-based architecture with a multi-model cascade via Groq for reliability, performs PDF validation and text extraction (up to 20MB), and supports secure user authentication plus session history for tracking past analyses. The project is built around a practical “report → extraction → analysis → insights” workflow and is designed to be deployable with Supabase (DB + Auth) and simple Streamlit configuration.

HIA (Health Insights Agent)

hia-health-insights-agent

Open-source AI agent that analyzes blood-report PDFs and returns personalized health insights, with authentication and analysis history.

Careery is a web-based AI job-search agent designed to run continuously in the background: it discovers roles that match your profile and applies for you, aiming to get you into the “first wave” of applicants. The platform emphasizes full-platform coverage beyond simple one-click applications, including submitting on job boards and directly on company career portals/ATS systems such as Workday, Greenhouse, Jobvite and others. Careery also includes email shortlisting so interview and recruiter messages don’t get lost in inbox clutter. The product is sold as time-limited credit bundles (one-time payment), where each completed application costs credits and there’s an ongoing per-agent monthly credit fee for maintaining agent features (search/matching, email shortlisting, and applied jobs management). By using the service, users explicitly authorize Careery to submit job applications on their behalf, with standard “no guarantee of results” terms.

Careery

careery

AI job-search agent that automatically finds matching roles and submits applications on your behalf (including company ATS portals).

Seedance15.ai is a web-based AI generation platform built around the “Seedance 1.5” model, focused on creating professional-looking videos with synchronized audio in a single generation flow. It supports text-to-video and image-to-video creation with options like resolution, aspect ratio, and duration, and highlights features such as precise lip-sync alignment, multilingual voice synthesis (including dialect/accents), cinematic camera movement control, and contextual ambient sound effects. Alongside video generation, the site also offers text-to-image generation and an AI image editor. The service uses paid plans with usage limits/credits, and also sells one-time credit packs; subscription credits reset monthly, while one-time credit packs are described as non-expiring. The Terms state users retain rights to their inputs and own the generated videos (including for commercial use), and the platform positions itself as independent (not affiliated with third parties).

Seedance 1.5 Pro

seedance-1-5-pro

AI creation platform for generating videos with synchronized audio (voice, lip-sync, SFX) from text or images, plus image generation and AI image editing tools.

Together Open Data Scientist is an open-source AI data analysis agent built around the ReAct (Reasoning + Acting) pattern. It automates common end-to-end data science workflows: loading and exploring datasets, running EDA, engineering features, training baseline models, creating plots, and writing a structured report. The agent can execute Python code either locally (via Docker/internal execution) or in the cloud using Together Code Interpreter (TCI), and it supports uploading a data directory for analysis. It’s positioned as experimental software—outputs should be reviewed and validated—making it most useful for exploration, learning, and fast first-pass analysis rather than unattended production analytics.

Together Open Data Scientist

together-open-data-scientist

Open-source data scientist agent that runs Python (locally or in the cloud) to explore datasets, build models, and generate detailed analysis reports using the ReAct framework.

CodeMender is a Google DeepMind research project focused on automatically improving software security by generating high-quality vulnerability patches. It’s designed to work both reactively (patching newly found vulnerabilities) and proactively (rewriting existing code to reduce or eliminate entire vulnerability classes). The agent leverages advanced “thinking” model capabilities plus a toolbox for reasoning and validation, including program analysis techniques (static and dynamic analysis, differential testing, fuzzing, SMT solvers) and multi-agent components for critique and regression checking. DeepMind reports that in the first six months of development it upstreamed dozens of security fixes to open-source projects, with all patches reviewed by humans before submission, and that broader availability is planned but not yet generally released.

CodeMender

codemender

Google DeepMind research AI agent that autonomously finds, patches, and validates fixes for software security vulnerabilities (human-reviewed before upstreaming).

PXZ AI is a web-based, all-in-one creative platform that bundles AI tools for image generation and editing, video generation and enhancement, voice creation, writing assistance, and chat in a single workspace. It brings multiple popular models together for text-to-image and text/image-to-video creation, letting users try different engines and styles without switching services. Beyond generation, PXZ AI includes practical production utilities such as image upscaling, background removal, photo colorization, video enhancing, trimming, compression, format conversion, and effects like multi-face-swap video. The service uses a credit-based model with a free tier for light use and paid plans that unlock more credits, higher quality outputs, faster generation, and broader usage rights.

PXZ AI

pxz-ai

All-in-one creative suite for generating and editing images, videos, voiceovers and written content using multiple AI models.

Orchids is an AI-powered coding IDE that acts as a full-stack engineer for building production-ready apps and websites. By chatting with the built-in Orchids Agent, users can describe what they want in natural language and have the system plan features, design UI, write frontend and backend code, wire databases, configure auth and payments, and deploy working projects. It runs as a desktop IDE where the agent can see your screen, interact with a built-in browser, and iteratively refine implementations. Orchids is aimed at founders, indie hackers, agencies, and engineering teams who want to move from idea to deployed software quickly without stitching together multiple tools or writing all boilerplate code themselves.

Orchids

orchids

AI full-stack engineer that lets you chat to design, code, and deploy production-ready apps and websites with no manual setup.

GLM-4.6V is a next-generation multimodal large language model series from Z.ai (Zhipu AI), designed for high-fidelity visual understanding and long-context reasoning across images, video, documents, and text. It comes in two main variants: the 106B-parameter GLM-4.6V foundation model for cloud and cluster deployment, and the lightweight GLM-4.6V-Flash (9B) optimized for local and low-latency applications. With a 128k token context window, GLM-4.6V can read large PDFs, slide decks, and multi-page mixed-media documents in a single pass. Native multimodal function calling lets it use tools directly from visual inputs, closing the loop from perception to executable actions and enabling powerful agent-style workflows. Typical use cases include visual document QA, chart and layout understanding, multimodal search and analysis, converting UI screenshots into production-ready code, and generating image-rich content. The models are released with open weights under a permissive open-source license, making them suitable for research, self-hosted deployments, and integration into production systems.

GLM-4.6V

glm-4-6v

Open-source multimodal GLM from Z.ai unifying vision, text, and tool calling for long-context reasoning, search, coding, and UI-to-code.

Google Antigravity is an AI-powered, agent-first development platform and IDE from Google, released alongside the Gemini 3 model family. Built as a fork of Visual Studio Code, it lets developers delegate complex software tasks to autonomous agents that can plan, code, test, and debug across an integrated editor, terminal, and browser. Antigravity’s Agent Manager view orchestrates multiple agents in parallel workspaces, while the Artifacts system surfaces verifiable plans, patches, logs, and screenshots so developers can inspect how work was done. The platform supports multiple models, including Gemini 3 Pro and other leading AI models, and is available as a free preview with generous usage limits on Windows, macOS, and Linux.

Google Antigravity

google-antigravity

Agent-first AI coding environment and IDE from Google where autonomous agents plan, write, test, and debug software across editor, terminal, and browser.

Calk AI is a no-code SaaS platform that lets teams build custom AI agents powered by their internal knowledge and business tools. By connecting sources like Notion, HubSpot, Slack, Google Analytics, and other systems, Calk enables agents to search, summarize, and write using real company context. The platform supports multi-model intelligence (e.g., GPT, Claude, Gemini, Mistral) so each task can use the best model for analysis, content creation, or reporting. Calk is designed for agencies, startups, and modern teams that want operational, sales, marketing, support, and analytics workflows automated by AI that understands their data while keeping security, privacy, and compliance in focus.

Calk AI

calk-ai

No-code platform to build custom AI agents that connect to your tools and internal data for search, insights, and workflow automation.

Explore AI Agents