Back to Marketplace
Models & MCPInfrastructure

sandbase-harness

sandbaseai/sandbase-harness

sandbase-harness is a tool for DeepSeek Harness. Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.

sandbaseai/sandbase-harness Screenshot preview
Stars
634
Forks
59
Issues
2
Update
41 days

REVIEW SCORECARD

Review Scorecard

8.2/10Good
License compliance9.0
Engineering quality8.0
Content completeness8.0
Repository scale7.0
Maintenance activity8.0

✓ No risk detected · Automated scan results are for reference only, not an official endorsement

PROJECT READMEREADMEExpandCollapse

Loading GitHub README...

PROJECT TOPICS

Project topics

VALIDATION LADDER

Validation progress

Outside plugin validation
01Store discoveryPassed
02ClassificationPassed
03Structure checkNot applicable
04Sandbox validationNot applicable

FAQ

Frequently Asked Questions

What is sandbase-harness used for?

Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure

How popular is sandbase-harness?

sandbase-harness has 634 stars and 59 forks on GitHub, last updated 2026-08-23.

What license does sandbase-harness use?

sandbase-harness is distributed under the Apache-2.0 license.

Is sandbase-harness compatible with DeepSeek Harness?

sandbase-harness is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.

CLASSIFICATION EVIDENCE

Classification evidence

Project typeInfrastructure
Feature categoryModels & MCP
Rule confidenceHigh

The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:ai-infrastructure、agent-observability、agent-sandbox、docker、mcp-server、model-context-protocol、openai-compatible、sandbox。