kern
kern: rootless container runtime and sandbox with no daemon. Runs agent tool calls and LLM-generated code in kernel-enforced containers.
kern at a Glance
- How you use it
- CLI, Python and Node packages, or MCP server
- Who it's for
- Developers and agents running code, CI jobs, and build steps
- Works with
- Claude Desktop Claude Code Cursor LangChain MCP pi
kern Key Features
- Agent tool-call sandbox
- Isolated code execution
- OCI image support
- Resource limits
- Rootless container runtime
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
kern Alternatives
mcp-server-code-execution-mode
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat. - elusznik/mcp-server-code-execution-mode
agent-safehouse
Sandbox your LLM coding agents on macOS. Kernel-level enforcement via sandbox-exec — deny-first, composable, zero dependencies.
Octomind
Open-source AI coding agent and agent runtime: one binary, any model, MCP-native. Runs in terminal, CI, or as a daemon. - Muvon/octomind
cplt
Sandbox for AI coding agents. Runs Copilot CLI, Claude Code, OpenCode, Gemini CLI, Antigravity, Pi, goose or a plain shell inside a kernel-level sandbox, with git and gh guards and sandbox policy committed to the repository. - navikt/cplt
Semantic Kernel
Integrate cutting-edge LLM technology quickly and easily into your apps - microsoft/semantic-kernel
Capsule
Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments. - capsulerun/runtime