Self-hostable sandbox for agent code execution — SandboxManager, control-plane, 4 SDKs, MCP server, running inside real Kubernetes pod isolation
The missing batteries-included, self-hostable sandbox for agent code execution.
Most "agent sandbox" projects give you raw isolation — a pod, a VM, a container — and leave you to build the actual tool surface an LLM agent needs on top of it. boxkite is the other half: a complete bash/python/file/search/process tool surface (15 ready-to-wire, framework-agnostic tools — LangChain, LangGraph, CrewAI, AutoGen, or plain OpenAI-style function calling — plus an opt-in git tool set of 8 more) running inside real Kubernetes pod isolation, built on industry-standard hardening practices — non-root execution, all Linux capabilities dropped, a read-only root filesystem, network egress denied by default, and output scrubbed for leaked API keys and cloud credentials before it ever reaches your agent. boxkite itself is early-stage (v0.1.0) — the isolation approach is proven, the project's production track record is not, yet.
Self-host it, point your agent framework at it, and you have a real sandbox in minutes instead of weeks. Everything here — the sandbox runtime, the hosted-API control-plane, all four client SDKs, and the MCP server — is self-hostable end to end; there's no piece of this product held back for a separate, closed hosted offering.
Who this is for: boxkite is a self-hostable sandbox for teams building their own agent products that need isolated, multi-tenant code execution at scale — one Kubernetes pod per session, many sessions, many tenants. It is not a single-user local dev-session sandbox like the built-in bash tool in an IDE or CLI coding agent — if you just want yo
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/EvAlssment--boxkite.html)
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is
zhuyansen/new-term-radarDaily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
yzg1226/mcd-party-officer🍟 麦当劳门店派对成团调度 Skill — 把派对从「策划」推进到「办得成」：成团概率雷达 / 包场vs拼团 / 择日黄历 / 儿童营养指数 / 招募卡与邀请函
fellowgeek/mcp-memoryAn OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.
hirotomasato/yowesGenerate realistic teacher documents (ID cards, licenses, letters) for 13 countries via MCP.
hujjun/mcd-saver-strategist麦当劳省钱点餐助手（麦门精算师）｜麦当劳优惠券组合优化 Skill：拉取麦当劳菜单与全部可用优惠券，算出最省的点餐组合，巨无霸套餐 ¥47 → ¥21.9（省 53%）。McDonalds MCP（麦当劳 MCP）coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.