sandbase-harness
sandbaseai
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.
GITHUB TOPIC
7projects include this topic
The "agent-runtime" topic on GitHub groups 7 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by sandbase-harness with 634 GitHub stars. sandbase-harness — Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
sandbaseai
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.
ZSeven-W
Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Codex · GLM).
runzhliu
Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI, and headless CLI.
OpenCnid
A durable, full-access runtime agent built on DeepSeek Harness
agent-runtime-interface
ARI (Agent Runtime Interface): one shell, any coding-agent harness. An interface specification derived from source-level study of DSH, Codex, ZCode, OpenCode, Pi, and ACP.
siweimofang
AI renovation advisor - main repo (knowledge base + DSH plugin + GEO)
xingtu1996
Frontline AI engineering scaffold: one-command pull of all skills/hooks/rules/specs/MCP/CLI|One-command AI engineering scaffold, aggregates a full agent asset stack (DSH-compatible)