SAPI

Agent S is an open-source computer-use agent framework from Simular. It accepts natural-language tasks, observes a real desktop through screen and accessibility signals, and operates ordinary applications by clicking, typing, scrolling, and executing optional local code rather than relying on per-application APIs or scripts. The project has progressed through three generations: accessibility-tree grounding with an LLM, a vision-based manager-worker architecture using multiple foundation models, and Agent S3, which scales computer-use attempts through parallel rollouts and selection. Its workflow can combine model-driven exploration with reusable automation code, replay saved skills, and recover when the interface changes. The framework supports macOS, Windows, and Linux, works with models from OpenAI, Anthropic, Gemini, OpenRouter, vLLM, and open-weight providers, and is distributed through the `gui-agents` Python package. An optional local coding environment can execute Python and Bash with the current user's permissions, so the repository warns that this capability should be used only in trusted environments.

Simulan is an open-source, JavaScript-based language from Simular for writing deterministic, replayable computer-automation workflows. It provides a symbolic automation layer for computer use, analogous to Playwright for browser automation, and can be used from the terminal or written through coding agents such as Claude Code. Workflows can be saved as reusable skills and replayed; when the environment changes or a fixed step fails, model-driven exploration can help recover before execution continues.

Sidebox is Simular's managed cloud-computer platform for autonomous agents. It provides Windows cloud desktops that agents can occupy and control, with Mac and Linux support described as available and Android support described as forthcoming. Developers can access the cloud computers through an interface or API, allowing agents to perform computer-use workflows across desktop applications and legacy systems.

Semwright is an open-source semantic layer and broker that gives AI agents typed interfaces to real software. Agents discover application capabilities, resolve named objects, and request typed operations with explicit inputs; policy checks authority and scope before execution, while references, jobs, readback, and execution evidence make object identity and results inspectable. It is designed to replace pixel-based interaction with application-native operations and supports Figma, Chromium, Blender, and MLT video through drivers. The project exposes the broker through MCP, a CLI, and an SDK, and can be installed on Linux, macOS, and Windows. The page states that the initial release starts with read-only permissions and that its independent security review is incomplete.

Sapien is an AI-powered market research platform that builds synthetic populations—simulated audiences grounded in purchase histories, behavioral and research data, demographics, surveys, and public conversations. It uses these populations to run surveys, qualitative interviews, and comparison tests for products, prices, and campaigns, with options to add customer data and past research for context. Sapien returns interactive reports with predictions, segment comparisons, recommendations, and the responses behind the findings. Users can ask follow-up questions of the same simulated audience; the service states that its team builds the audience, runs the study, and provides same-day predictions and interpretation.