Sandbox
14 repos for computer · Codex · TestingClear
K-Dense-AI/
science-superpowers

Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.

328
HeshamFS/
materials-simulation-skills

Agent Skills for computational materials science -- numerical stability, solvers, meshing, convergence, and simulation workflows.

66
AMAP-ML/
LongHorizon-Harness

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

1.5k

The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.

973

Self-evolving browser automation for Codex, Claude Code, and Cursor—learn reusable site knowledge and safely replay verified routines with agent-browser.

102
ugarchance/
record-and-replay-skill

Agent-agnostic record & replay skill: watch a user demonstrate a workflow (browser via Playwright, desktop via OpenAdapt) and turn it into a reusable AI-agent skill. Works with Claude Code, Codex CLI, opencode.

36

Compile, verify, and run multi-agent DAGs across Pi, Codex, Claude Code, OpenCode, and Grok—with resume, replay, and incremental recomputation.

71
Core-Mate/
OpenGUI
Core-Mate/OpenGUIFrameworks & SDKs

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

1.8k

clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable scripts, verifying every action and routing it through a single safety gate.

400

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

362