Sandbox
59 repos for sandbox · CodingClear

secure multiplexed execution paths for agents - zero trust, zero setup, zero latency.

4k

Control Claude Code, Codex CLI and Gemini CLI from Telegram. Live streaming, persistent memory, cron jobs, webhooks, Docker sandboxing.

455
matlab/
agent-skills-playground

A sandbox for prototyping and demonstrating Agent Skills for MATLAB and Simulink work.

176

AI coding agent with one Python core and three front-ends — headless CLI, Textual TUI, and an Electron desktop. Works with any OpenAI-compatible API, with risk-tiered permissions, event-sourced replayable sessions, and a fail-closed OS-level sandbox.

119
ruvnet/
metaharness

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

645

HTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.chat.

149

Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.

508
lookfree/
cc-harness

Desktop workbench for Claude Code — live subagent topology, token cost breakdown with drill-down, hook sandbox, config audit. Reads your session files locally. Electron, MIT.

48

Playwright for coding agents. Benchmark Claude Code, Codex, Gemini, and OpenCode on your own tasks - and test that your skills, MCP servers, and CLIs work when an agent uses them. Sandboxed YAML suites, activation checks, A/B experiments, CI gates.

127
ComposioHQ/
composio

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

30k
gradion-ai/
ipybox

Unified execution environment for Python code, shell commands, and programmatic MCP tool calls.

73

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

22k

✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.

8.7k
sbusso/
claudeclaw

Use Claude to orchestrate agents like OpenClaw

192
Osteoporosis/
luna-chat-coder

Agent Skill and repository template for end-to-end software development entirely inside ordinary Web AI chat.

63
microsoft/
wassette

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP

942
astrid-runtime/
astrid
astrid-runtime/astridFrameworks & SDKs

Astrid is a portable, capability-secure operating system for composable software.

10k
mgorabbani/
askdb

Give AI agents safe access to your database.

73
TokenRhythm/
opensquilla

OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

7k
strukto-ai/mirageFrameworks & SDKs

The World's First Virtual Terminal for AI Agents

3.6k
ZIB-IOL/
The-Agentic-Researcher

A practical framework for AI-Assisted Research in Mathematics and Machine Learning

95