Awesome GitHub RepositoriesSandboxed Code Evaluators

Hydro is an online judge platform and competitive programming management system. It provides the infrastructure to host programming contests, manage a library of programming problems, and evaluate code submissions against predefined test cases and time limits. The system utilizes a distributed code execution engine that scales judging tasks across multiple worker nodes to process high volumes of submissions. It is built as a modular judge framework, employing a plugin-based architecture that allows for the extension of system functionality without modifying the core source code. The platform

OnlineJudge is an automated platform for managing programming contests and evaluating submitted source code. It provides a complete online judge system that compiles, runs, and scores code submissions against predefined test cases within a sandboxed execution environment, ensuring the host system remains protected from untrusted user code. The platform supports both ACM-style penalty-based scoring and OI-style point-based scoring, with real-time leaderboard computation that dynamically updates participant rankings as submissions are judged. Contest organizers can create and schedule timed com

EvalXR is an interactive Rust compiler that compiles code into dynamically loaded libraries for iterative evaluation without restarting the process. It serves as a Rust Jupyter kernel, a notebook runtime, and a REPL environment, all with state retention across evaluations. The project provides a stateful Rust evaluation engine that runs code snippets in isolated sandboxes while keeping functions and variables alive between executions. It supports cell-based execution, compiling Rust code into a shared library and loading it into the same process to preserve state, with an error-aware compilat

PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

mcp-context-forge is a Model Context Protocol federation gateway that unifies diverse AI tool servers and APIs into a single consistent interface for discovery and execution. It acts as a centralized proxy that aggregates multiple servers and APIs, allowing AI agents to access and invoke a unified set of tools, prompts, and resources. The project distinguishes itself through a multi-protocol translation bridge that converts communication between standard I/O, SSE, gRPC, and REST to enable interoperability between disparate tool servers. It includes a comprehensive LLM evaluation framework for

Scala Exercises is an interactive learning platform designed for mastering the Scala programming language through browser-based coding challenges. It functions as a comprehensive educational framework that structures programming lessons into sequential modules, providing immediate feedback on user-submitted code through automated validation. The platform distinguishes itself by treating educational content as modular, versioned artifacts that can be dynamically registered and integrated as project dependencies. This architecture allows for the creation of custom learning paths where exercises