mcpsandbox: mcpsandbox provides a lightweight sandbox object inspired by Daytona-style ergonomics but built around command projection instead of a full VM or container. It maps capabilities into a minimal runtime and lets an agent use them through shell commands and a small typed API. It supports just-bash as the execution engine, built-in filesystem sandboxing, git integration, MCP-backed commands, TypeScript handlers, existing binaries, and external sandbox providers.; semble: Semble is a high-performance code search library designed for AI agents, providing instant access to precise code snippets. It offers significantly faster indexing and querying compared to transformer models, achieving 99% of their retrieval quality while running entirely on CPU without external dependencies.
Local development and testing of MCP tools
Enhancing AI agents (e.g., Claude Code, Cursor, Codex) with fast and accurate code search capabilities