emisar: emisar enables MCP-capable agents to perform declared infrastructure actions securely on remote hosts, governed by strict policy. It provides a control plane and an outbound-only runner that enforces execution limits and ensures audited, safe interaction with production systems.; mini-swe-agent: Mini-SWE-agent is a lightweight, 100-line AI agent designed to solve GitHub issues and more, offering a simplified yet performant alternative to larger coding agents. It focuses on minimalism, high performance on benchmarks like SWE-bench, and easy deployment across various environments.
Enabling AI/LLM agents to securely perform infrastructure actions.
Researchers for benchmarking, fine-tuning, or RL experiments without bloat