Enables MCP clients to submit, monitor, and manage jobs on shared NVIDIA GPUs, inspect logs and status, cancel work, and interact with isolated virtual displays through screenshots, window inspection, and input.
Provides a persistent compute queue for AI agents, enabling them to submit hardware-aware GPU jobs, monitor execution, and retrieve results and artifacts across sessions via MCP tools.
Enables MCP-aware agents to estimate, submit, monitor, cancel, and retrieve artifacts from Jungle Grid workloads, supporting asynchronous AI execution, batch processing, training, fine-tuning, and access to logs and managed outputs.
Enables coding agents and other MCP clients to hand bounded jobs to remote worker agents, track progress, and review reports or patches before accepting results, with repository access denied until explicitly granted and owner approval required.
Enables MCP clients to securely execute bounded coding tasks through registered backends, with idempotent job submission, status polling, and artifact retrieval. It isolates each job in Git worktrees and supports optional branch publishing and pull request creation under strict policy constraints.