Search Results for "sandbox" - Page 4
Sort By:
Showing 282 open source projects for "sandbox"
View related business solutions-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
ZeroClaw
Fast, small, and fully autonomous AI assistant infrastructure
...The framework features a compact single binary with fast cold and warm startup times and very low memory overhead, making it suitable even for resource-constrained hardware like small servers or edge devices. Security is a first-class concern, with sandbox controls, encrypted secrets, allowlisted operations, and scoped filesystem access by default, helping reduce risk when running autonomous agents. -
2
Dockerlings
Learn docker in your terminal, with bite sized exercises
...Designed for both beginners and developers who want a hands-on introduction to containerization, it gamifies common Docker tasks like managing images, containers, networks, and volumes so you can practice repeatedly without needing external tutorials or sandbox environments. The tool runs as a terminal application that presents interactive prompts and verifies your commands instantly, giving immediate feedback on whether you’ve completed the step correctly. Instead of reading static documentation, dockerlings turns learning into a mini-adventure where each successful command unlocks the next lesson, helping solidify understanding through practical repetition. -
3
Monty
A minimal, secure Python interpreter written in Rust for use by AI
Monty is an experimental, security-focused Python interpreter implemented in Rust and intended for running AI-generated Python safely under strict constraints. The project’s core goal is to enable code execution in environments where untrusted or model-produced code must be tightly sandboxed to reduce risk. Rather than offering a full “general-purpose Python runtime with everything enabled,” Monty is designed to be minimal and controlled, making it easier to reason about what code can do and... -
4
OpenYurt
Extending your native Kubernetes to edge(project under CNCF)
OpenYurt is built based on upstream Kubernetes and is now hosted by the Cloud Native Computing Foundation(CNCF) as a Sandbox Level Project. OpenYurt has been designed to meet various DevOps requirements against typical edge infrastructures. It provides a consistent user experience for managing the edge applications as if they were running in the cloud infrastructure. It addresses specific challenges for cloud-edge orchestration in Kubernetes such as unreliable or disconnected cloud-edge networking, edge autonomy, edge device management, region-aware deployment, and so on. ... -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
5
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
...Its architecture combines large-scale data synthesis, a skill-augmented CUDA development environment, and long-horizon reinforcement learning to build intrinsic optimization capability rather than relying on simple post-hoc tuning. The system operates in a ReAct-style loop where the agent profiles baseline implementations, writes CUDA code, compiles it in a sandbox, and iteratively refines performance. CUDA-Agent has demonstrated strong benchmark results, achieving high pass rates and significant speedups compared with compiler baselines such as torch.compile. -
6
CRM
An open-source, agentic-first CRM
...Email threads, meetings, signature blocks, optional web research, and enrichment services can provide evidence. Durable sessions survive reloads and deployments, while a restricted sandbox prevents direct database access and network egress. The project is single-tenant and uses Google sign-in with an environment-based allow list. -
7
Cap'n Proto
Serialization/RPC system - core tools and C++ library
...The repository contains the main compiler, C++ runtime, KJ library components, tests, style guidance, release tooling, and development branches. It is especially useful for systems programming, service communication, sandbox communication, and low-latency infrastructure. -
8
Danghuangshang
AI Court Building Complete Tutorial - From Zero Basics to Advanced
...Agents can be assigned responsibilities such as coding, architecture, finance, operations, marketing, project management, legal review, and automated code inspection. The system includes memory, scheduled tasks, sandbox isolation, multi-platform access, and a web dashboard for monitoring status and usage. It is intended for users who want a practical AI agent team template rather than a low-level framework they must assemble from scratch. -
9
Boneyard
Auto generated skeleton loading framework
Boneyard is an experimental or utility-focused repository that serves as a collection of discarded, archived, or exploratory code projects. It functions as a sandbox where developers can store unfinished ideas, prototypes, or deprecated implementations without removing them entirely. The project provides a space for experimentation, allowing developers to revisit past work, extract useful components, or learn from previous attempts. It often contains a variety of code snippets or mini-projects that may not be production-ready but still hold educational or practical value. ... -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
10
claude-code-best-practice
Practice made claude perfect
claude-code-best-practice is a structured knowledge repository that documents advanced workflows, architectural patterns, and optimization strategies for developers using Claude Code in agentic development environments. Rather than being a traditional software library, the project functions as a living playbook that demonstrates how to compose skills, agents, memory files, and rules into maintainable AI-assisted coding systems. The repository emphasizes modularity and progressive disclosure,... -
11
glChAoS.P
3D GPUs Strange Attractors and Hypercomplex Fractals explorer
glChAoS.P is a GPU-accelerated, real-time graphics project for visualizing complex mathematical fractals, attractors, and particle systems using OpenGL and GLSL. It’s an interactive sandbox for visual experimentation with chaotic systems, combining beautiful visuals with user control via keyboard and GUI. The software includes extensive customization of rendering parameters, camera movement, and output formats, including support for VR and 360-degree panoramic videos. It’s widely used for both scientific visualization and generative art. -
12
Clusternet
[CNCF Sandbox Project] Managing your Kubernetes clusters
An open-source project that helps users manage multiple Kubernetes clusters as easily as ‘visiting the Internet’ (thus the name ‘Clusternet’). It is a general-purpose system for controlling Kubernetes clusters across different environments as if they were running locally. Manage multiple Kubernetes clusters (running on public cloud, private cloud, hybrid cloud, or at the edge) from a single management cluster. Deploy Helm Charts, all Kubernetes built-in resources (like Deployments) and CRDs... -
13
Oasis
Inference script for Oasis 500M
...Because it’s an inference-focused repository, it’s especially useful as a practical reference for running the model, wiring inputs, and producing the autoregressive sequence of gameplay frames. It also serves as a research sandbox for people exploring how far interactive generative models can go with smaller, more accessible checkpoints compared to massive internal systems. -
14
Apodex FrontierAgent
FrontierAgent, our agent framework, open-sourced alongside it
FrontierAgent is an open-source agent runtime, terminal application, and evaluation suite for long-horizon research and file-based work. Its ReAct workflow provides a stateful agent that can research, read files, execute commands, and create deliverables inside a task-scoped sandbox. Agent Team mode adds a coordinator that divides work among parallel sub-agents and synthesizes their results. A live task board tracks pending, active, completed, blocked, and canceled work. Users can provide new instructions while an agent is running without discarding the active session. The same modular workflow engine also powers benchmark evaluations and can connect to OpenAI-compatible model endpoints. -
15
Shepherd
Runtime substrate that turns agent's execution into a Git-like trace
Shepherd is an early-stage Python runtime for building agents and meta-agents around reversible, inspectable execution traces. It records interactions and workspace changes as durable run histories instead of immediately applying an agent's output. Each result can be reviewed, executed separately, selected, merged, released, or discarded. Tasks are declared as Python functions whose signatures and documentation define the agent contract and required resources. Read-only and read-write... -
16
Omnigent
A meta-harness for all your AI agents
Omnigent is a meta-harness for managing many AI agents through one shared layer. It works with Claude Code, Codex, Cursor, Pi, and custom YAML-defined agents, so users can swap or combine agent runtimes without rebuilding their workflows. Sessions can move across terminal, browser, desktop, and mobile interfaces while keeping messages, files, terminals, and subagents in sync. The platform supports collaboration, shared live sessions, co-driving, conversation forking, and remote access from... -
17
GenMedia Creative Studio
AI generative media user experience highlighting use of APIs
...The repository also includes experiments and MCP-related materials for connecting generative media capabilities to agent workflows. It is not an officially supported Google product, so it is best treated as a reference implementation and creative sandbox rather than a managed commercial service. -
18
OpenSquilla
Token-Efficient AI Agent with same budget, higher intelligence density
OpenSquilla is a token-efficient microkernel AI agent runtime designed for CLI, web UI, and chat-based workflows. It routes each turn through a shared loop that can select lower-cost models when appropriate while preserving tool dispatch, retries, memory, and decision logging. The project supports multiple LLM providers through a pluggable provider layer, making it adaptable to different model ecosystems. It includes persistent memory, built-in web search, on-device embeddings, and... -
19
quickjs-emscripten
Safely execute untrusted Javascript in your Javascript
quickjs-emscripten is a JavaScript library that compiles the QuickJS engine into WebAssembly using Emscripten, enabling developers to run JavaScript code inside a sandboxed environment within browsers or server-side JavaScript runtimes. It provides a secure and isolated execution context, making it particularly useful for running untrusted or user-generated code safely. The library abstracts the complexity of loading and initializing the WebAssembly module, offering convenient APIs to create... -
20
Rust Port
The Rust workspace under rust/ is the current systems-language port
...The project emphasizes agent-based execution, where tasks are broken down into steps and handled iteratively, simulating how modern AI coding tools operate in production environments. It is often used as a sandbox for exploring how large-scale coding agents behave, including their decision-making processes, tool usage, and workflow orchestration. The system likely includes abstractions for handling file systems, executing commands, and maintaining context across sessions, allowing for more persistent and intelligent coding interactions. -
21
database.build
In-browser Postgres sandbox with AI assistance
database.build is an innovative in-browser development environment that allows users to instantly create and interact with fully functional PostgreSQL databases directly within their browser, powered by WebAssembly technology. It eliminates the need for traditional database setup by running a lightweight version of PostgreSQL locally using PGlite, enabling developers to experiment, prototype, and analyze data without relying on external servers. Each database instance is paired with a large... -
22
hematite
A simple Minecraft written in Rust with the Piston game engine
Hematite is an experimental open-source project that attempts to reimplement aspects of the Minecraft game engine using the Rust programming language. Developed within the Piston ecosystem, the project serves primarily as a technical experiment exploring how Rust can be used to build complex game systems such as rendering, world simulation, and client architecture. Hematite aims to replicate core elements of Minecraft’s mechanics while leveraging Rust’s safety guarantees and modern... -
23
HSharp
HSharp is a library used to analyze markup language like HTML
HSharp appears to be an experimental C#/.NET project exploring higher-level abstractions or helper patterns (the naming hints at “H#” as a layer or framework on top of C#). It groups together utilities, base classes, and conventions so that common app logic can be written faster and with less boilerplate. The repo acts as a sandbox for testing these patterns in real code, which is helpful if you want to see how the author structures services, models, or infrastructure concerns. Because it’s source-first, you can cherry-pick the parts you want into your own .NET apps and ignore the rest. The idea is to make everyday C# tasks (initialization, configuration, helpers) feel more concise and expressive. ... -
24
Wallaby
Concurrent browser tests for your Elixir web apps
...Generally, bash is widely available, but it does not come pre-installed on Alpine Linux. If you're testing a Phoenix application with Ecto and a database that supports sandbox mode, you can enable concurrent testing by adding the Phoenix.Ecto.SQL.Sandbox plug to your Endpoint. It's important that this is at the top of endpoint.ex before any other plugs. -
25
NelmioApiDocBundle
Generates documentation for your REST API from annotations
The NelmioApiDocBundle bundle allows you to generate documentation in the OpenAPI (Swagger) format and provides a sandbox to interactively experiment with the API. This bundle supports Symfony route requirements, PHP annotations, Swagger-Php annotations, FOSRestBundle annotations, and apps using API-Platform. For models, it supports the Symfony serializer, the JMS serializer and the willdurand/Hateoas library. It does also support Symfony form types.
