SandBase Harness

MCP serverAI & models

This app connects your AI to SandBase Harness so it can run and keep track of agent work. Once added, your AI can start sessions, follow each turn of a run, collect the artifacts a run produces, and cancel a run that is no longer needed.

Unavailable. This server has no hosted endpoint yet, so ahel can't serve it.

After adding it, follow the setup instructions in its repository (github.com/sandbaseai/sandbase-harness) to connect it to your SandBase Harness.

What your AI can do with it

  • Work with your SandBase Harness agents
  • Start and follow agent sessions
  • See what happens in each turn of a session
  • Collect the artifacts a run produces
  • Cancel a session or run that is no longer needed

From the project's README

As published by sandbaseai/sandbase-harness in README.md.

English | 中文

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:

NeedWhat Harness provides
Run generated code safelyLocal, Docker, Kubernetes, and self-hosted worker sandboxes
Inspect long-running agentsPersistent sessions, resumable event streams, audit, and replay
Control tool accessMCP toolsets, credential vaults, permission policies, and approvals
Operate any modelOpenAI, Anthropic, MiniMax, and OpenAI-compatible providers, including DeepSeek V4
Keep infrastructure yoursLocal-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.

Find SandBase Harness

The project is also discoverable through these independent ecosystem directories:

Recently verified community references:

Pending community review:

Shortened here. Read the whole README on GitHub.

Signals

GitHub stars
642
Forks
66
Last commit
Sep 2026
Advanced
Delivery
sandbase-harness MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
io-github-sandbaseai-sandbase-harness
Source
github.com/sandbaseai/sandbase-harness