TheAiSingularity/hermesclaw
Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack
This project helps developers and MLOps engineers securely run autonomous AI agents in production environments. It takes a large language model (LLM) and a set of predefined AI agent "skills" as input. The output is a robust, sandboxed AI agent that can perform tasks like web searches, code reviews, or anomaly detection, while preventing unintended actions like unauthorized network access or file system changes. This is for AI developers, MLOps engineers, or system administrators who need to deploy AI agents with strict security and behavioral controls.
Use this if you need to run AI agents with powerful capabilities but require hardware-enforced security policies to prevent them from accessing unauthorized networks, writing to critical files, or executing dangerous system calls.
Not ideal if you are a non-technical end-user looking for a simple, off-the-shelf AI assistant without needing to manage its underlying infrastructure or security configurations.
Stars
13
Forks
1
Language
Shell
License
MIT
Category
Last pushed
Mar 31, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/TheAiSingularity/hermesclaw"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ghostwright/phantom
An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure...
dograh-hq/dograh
Open Source Voice Agent Platform
gmickel/flow-next
Plan-first AI workflow plugin for Claude Code, OpenAI Codex, and Factory Droid. Zero-dep task...
joseairosa/recall
Persistent cross-session memory for Claude & AI agents. Self-host on Redis/Valkey, or use the...
lintsinghua/claude-code-book
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent...