From 448bfce4d88f961ed8056a2cb56e5ef7673ed598 Mon Sep 17 00:00:00 2001 From: root Date: Sun, 30 Aug 2026 13:42:06 +0800 Subject: [PATCH] docs: add SandBase Harness to agent sandboxes --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 937af86..4cadbfc 100644 --- a/README.md +++ b/README.md @@ -36,6 +36,7 @@ OS-level isolation uses Linux namespaces, cgroups, or kernel-enforced policies; - [packnplay](https://github.com/obra/packnplay) - Docker wrapper for AI assistants with automatic git worktree and devcontainer support - [yolobox](https://github.com/finbarr/yolobox) - CLI running AI agents in containers where home directory stays unmounted for safety - [CodeRunner](https://github.com/instavm/coderunner) - Secure local sandbox to run LLM-generated code on macOS using Apple containers and MCP +- [SandBase Harness](https://github.com/sandbaseai/sandbase-harness) - Self-hosted TypeScript agent runtime with persistent sessions, sandboxed tool execution, an MCP bridge, managed credentials, audit logs, and replayable runs - [SandboxAI](https://github.com/substratusai/sandboxai) - Docker-containerized runtime for safely executing AI-generated Python and shell commands - [llm-sandbox](https://github.com/vndee/llm-sandbox) - Python library executing LLM-generated code in Docker/Kubernetes/Podman with customizable security - [MCP Runner](https://github.com/abir-taheer/mcp-runner) - MCP server platform using Docker with gVisor runtime for multi-tenant isolation