by sandbaseai
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
# Add to your Claude Code skills
git clone https://github.com/sandbaseai/sandbase-harnessGuides for using ai agents skills like sandbase-harness.
Last scanned: 8/15/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@ai-sdk/anthropic: Vulnerability found",
"severity": "low"
},
{
"type": "npm-audit",
"message": "@ai-sdk/openai: Vulnerability found",
"severity": "low"
},
{
"type": "npm-audit",
"message": "@ai-sdk/provider-utils: @ai-sdk/provider-utils has an Uncontrolled Resource Consumption issue",
"severity": "low"
},
{
"type": "npm-audit",
"message": "@ai-sdk/react: Vulnerability found",
"severity": "low"
},
{
"type": "npm-audit",
"message": "@ai-sdk/ui-utils: Vulnerability found",
"severity": "low"
},
{
"type": "npm-audit",
"message": "@hono/node-server: Node.js Adapter for Hono: Path traversal in `serve-static` on Windows via encoded backslash (`%5C`)",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@vitest/mocker: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "ai: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "esbuild: esbuild enables any website to send any requests to the development server and read the response",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "hono: Hono: ReDoS in CORS middleware via Access-Control-Request-Headers",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "jsondiffpatch: jsondiffpatch is vulnerable to Cross-site Scripting (XSS) via HtmlFormatter::nodeBegin",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "nanoid: nanoid: non-secure generators can loop indefinitely with negative size",
"severity": "high"
},
{
"type": "npm-audit",
"message": "postcss: PostCSS: incomplete fix of GHSA-6g55-p6wh-862q — attacker-controlled sourceMappingURL reads arbitrary .map files when `from` is unset",
"severity": "high"
},
{
"type": "npm-audit",
"message": "vite: Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling",
"severity": "high"
},
{
"type": "npm-audit",
"message": "vite-node: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "vitest: Vulnerability found",
"severity": "critical"
},
{
"file": "README.md",
"line": 276,
"type": "secret-exfiltration",
"message": "Instruction appears to send credentials/secrets to an external endpoint",
"severity": "medium"
}
],
"status": "FAILED",
"scannedAt": "2026-08-15T04:29:46.532Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how sandbase-harness compares with popular alternatives.
sandbase-harness is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by sandbaseai. Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console. It has 642 GitHub stars.
sandbase-harness failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.
Clone the repository with "git clone https://github.com/sandbaseai/sandbase-harness" and add it to your Claude Code skills directory (see the Installation section above).
sandbase-harness is primarily written in TypeScript. It is open-source under sandbaseai on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh sandbase-harness against similar tools.
No comments yet. Be the first to share your thoughts!
Requires a passing catalog security scan. Resolve the flagged issues and resubmit to enable featuring.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
AI-readable project metadata: llms.txt · installation guide
A local-first runtime for AI agents. Sessions, sandboxed tools, memory, credentials, audit trails, and a built-in Console — all running on your machine or in your own infrastructure.
Building with DeepSeek Harness? The independent DeepSeek Harness Handbook provides source-backed runtime guides, multilingual troubleshooting, and a regularly updated Agent-first resource map.
Looking for a lightweight bridge instead of a full runtime? SandBase CLI connects 25 AI client targets to 2,000+ models and APIs through a local stdio MCP bridge. If it fits your workflow, star SandBase CLI so other agent users can discover it.
Need hosted model and media APIs instead? SandBase provides one interface for LLM, image, and video generation APIs, with the API quickstart covering keys and first calls.
git clone --branch v0.3.8 --depth 1 https://github.com/sandbaseai/sandbase-harness.git
cd sandbase-harness
npm ci
npm run build
mkdir ../my-agents && cd ../my-agents
node ../sandbase-harness/dist/index.js init
node ../sandbase-harness/dist/index.js start
# open http://127.0.0.1:3000/dashboard
Choose SandBase Harness when you need more than a model loop:
| Need | What Harness provides |
|---|---|
| Run generated code safely | Local, Docker, Kubernetes, and self-hosted worker sandboxes |
| Inspect long-running agents | Persistent sessions, resumable event streams, audit, and replay |
| Control tool access | MCP toolsets, credential vaults, permission policies, and approvals |
| Operate any model | OpenAI, Anthropic, MiniMax, and OpenAI-compatible providers, including DeepSeek V4 |
| Keep infrastructure yours | Local-first SQLite and file storage with no required hosted control plane |
If this runtime solves a real agent-infrastructure problem for you, star the repository so other builders can find it.
The project is also discoverable through these independent ecosystem directories:
io.github.sandbaseai/sandbase-harness entry; its version snapshot may lag the current release.Recently verified community references: