“code execution and sandboxes”

Internal meta skill for dispatching subagents, coordinating execution, and integrating reviewed results back into the main flow.

Lightweight Python framework and starting template for agents that let the model choose its own approach to each task.

Subagent "performance-analyzer" from nrwl/nx: Use this agent during PR review to analyze the runtime performance of a PR's changes along two axes - (1)…

Execute and track progress on PLANS.md execution plans.

Converge AIDE's three parallel agent runtimes (legacy daemon model-manager chat + harness/orchestrator.mjs, arch-ts model-router/chat.ts + routes/agent.ts…

Run shell/CMD commands directly on the host system.

Execute behavior changes with a RED -> GREEN -> REFACTOR loop when a practical automated test path exists.

Convert an existing specification or plan into concrete execution tasks, ordered implementation steps, and verification actions.

Proves AI-generated Python does what you asked: lint, types, security, sandbox run, exact fixes.

Operate on owned repositories in Vega Lab.

Policy enforcement, identity, sandboxing and reliability tooling for autonomous AI agents, installable with one pip command.

Code execution API that lets LLM-generated code run in isolation and returns its output.

Delegate hands-on implementation to OpenAI's Codex CLI (a GPT-family coding worker; default model gpt-6-astra) while Claude stays the manager: Claude writes a…

Managed platform on Google Cloud to build, scale, govern and optimize enterprise AI agents.

Autonomous AI microservices: 55 dynamic guardrails, contract audits & oracles via L402/x402/MPP.

MANDATORY CORE SKILL: Enforces the Autonomous Coding & Self-Correction Loop for Antigravity in every session.

Use DB-GPT 0.8.1 as an agentic AI data platform: install and configure provider profiles, operate its CLI and services, build agents and AWEL flows, ingest…

Secure, elastic infrastructure that runs AI-generated code in sandboxes created in under 90 milliseconds.

Snipara

snipara

Project-scoped memory and context for AI agents - durable decisions, source-backed retrieval, code graph context, and team collaboration

Provides binary exploitation techniques for CTF challenges.

Terminal AI coding agent that plans and applies changes across large projects, with a diff review sandbox.

Run Python code in a secure sandbox without local setup.

Open-source self-evolving general AI agent with a Docker sandbox that can run fully local on Ollama or vLLM models.

Operate OpenAI Codex CLI (terminal coding agent) to accomplish software engineering tasks.