Manifest
Manifest by Omfang is an action layer for AI agents that turns any webpage into a structured map of what an agent can actually do. Developers send a URL to the Manifest API and receive clean JSON describing the page state, available buttons, forms, inputs, navigation links, required fields, and dependencies between actions. Manifest loads the page in a real Chromium browser after JavaScript runs, reads the accessibility tree used by screen readers, and cross-references it with the underlying DOM to capture details the accessibility layer can miss, including input types, placeholders, disabled states, and prerequisites for submission. Once actions are identified, their locators are resolved deterministically rather than generated by a model; ambiguous matches are marked uncertain instead of guessed. This gives agents a machine-readable interface for reasoning about what to click, fill, or submit without relying on screenshots, brittle CSS paths, etc.
Learn more
Action Agent
Action Agent is an autonomous AI with enterprise‑grade controls that reasons, runs code, and executes tasks across your data and systems without manual prompting. It lets you build custom agents with shared tools for IT and business teams, activate them via a unified interface, and supervise performance at scale with governance and monitoring features. By ingesting large data files, the agent can analyze complex datasets and generate charts, graphs, and presentations; draw insights from competitive landscapes and research; and create ready‑to‑use outputs based on high‑level instructions. Action Agent consistently ranks #1 on GAIA Level 3 and Computer Use benchmarks, demonstrating proficiency in web search and scraping, data analysis and visualization, browser and system navigation, task orchestration, file generation, and code execution. A forthcoming library of 80 + connectors will ground its autonomy in real workflows, integrating with core enterprise systems.
Learn more
Surfer H
Surfer H from H Company is an autonomous web-agent platform built to understand and navigate user interfaces like a human by combining three modular models; a policy model that plans tasks, a localizer model that identifies UI elements visually, and a validator model that checks outcomes. The agent works purely through the browser interface with no special API hooks, enabling it to scroll, click, type, and complete real-web tasks such as booking hotels, comparing product deals, or extracting structured information. When paired with H Company’s open-weight vision-language models, Surfer H achieved state-of-the-art performance on the WebVoyager benchmark (92.2% accuracy at around $0.13 per task) and supports deployment locally, via Docker, or on cloud infrastructure. Use cases span web automation, QA testing without brittle scripts, data harvesting, and intelligent workflow agents that interact with the web directly as a human would.
Learn more
Incredible
Incredible is a no-code automation platform powered by agentic AI models designed for real work across applications, letting users create AI “coworkers” that perform complex, multi-step workflows merely by describing tasks in plain English. These AI agents integrate with hundreds of productivity tools, CRMs, ERPs, email systems, Notion, HubSpot, OneDrive, Trello, Slack, and more to perform actions like content repurposing, CRM health checks, contract reviews, and content calendar updates without writing any code. Its architecture supports parallel execution of hundreds of actions with low latency and handles large datasets efficiently, dramatically reducing token limitations and hallucinations in data-critical tasks. The latest model, Incredible Small 1.0, is available in research preview and via API as a drop-in alternative to other LLM endpoints, offering high-precision data processing, near-zero hallucination, and enterprise-scale automation.
Learn more
