Agents tagged "sandboxing"

23 results
sandboxing ×
Dev & Engineering

MetaHarness

Turn a repository into a branded, governed, publishable AI agent harness.

★ 668 FS 86 Good 18d ago MIT
Automation & Ops

h5i — A Security-First Headless Browser for AI Agents

A lightweight, pure-Rust browser with no Chromium or V8, letting agents browse, scrape, test, and automate the web inside sandboxed, auditable sessions.

★ 652 FS 84 Good 1d ago Apache-2.0
Automation & Ops

Node9

Intercept, audit, and govern risky actions performed by autonomous coding agents.

★ 216 FS 82 Good 1d ago Apache-2.0
Dev & Engineering

Codemini CLI

An extremely restrained terminal-first coding + tasks CLI with a built-in Web UI, handling refactoring, Git workflows, pipelines, and research locally.

★ 192 FS 71 Some gaps 29d ago MIT
Dev & Engineering

Code on Incus (coi)

Give each AI coding agent its own isolated machine with root, Docker, systemd — and active threat defense.

★ 728 FS 66 Some gaps today MIT
Automation & Ops ✓ NVIDIA · Official

NVIDIA NemoClaw

A secure reference stack for operating always-on agents in NVIDIA OpenShell sandboxes.

★ 23k FS 65 Some gaps today Apache-2.0
Productivity & Collaboration

Open Cowork

A sandboxed desktop workspace for running multi-model AI tasks against files, documents, and desktop applications.

★ 2.2k FS 65 Some gaps 9d ago MIT
Dev & Engineering ✓ OpenAI · Official

OpenAI Agents SDK

A Python framework for tool-using, observable multi-agent workflows.

★ 30k FS 64 Some gaps 1d ago MIT
Dev & Engineering

DeerFlow Super Agent Harness

Open-source long-horizon SuperAgent harness that orchestrates sub-agents, memory, and sandboxes to research, code, and create.

★ 83k FS 63 Some gaps today MIT
Dev & Engineering

Omnigent

A shared control layer for coding agents, with multi-agent coordination, policy enforcement, and sandbox-backed execution.

★ 10k FS 62 Some gaps today Apache-2.0
Automation & Ops

microsandbox

Easy, fast, local microVMs for untrusted workloads like AI agents, user code, plugins, and CI jobs.

★ 8.3k FS 61 Some gaps 4d ago Apache-2.0
Automation & Ops

ZeroClaw — Personal AI assistant runtime

A single Rust binary that runs your own AI assistant across 30+ channels, ~20 model providers, and every major OS, with your data, keys, and machine.

★ 33k FS 60 Some gaps 1d ago Apache-2.0
Dev & Engineering

Orca

A DeepSeek-native terminal coding agent that reads code, edits files, runs commands, and verifies its own work until the task is done or it needs you.

★ 508 FS 59 Major gaps today MIT
Automation & Ops

JoySafeter

The AI-native enterprise security Agent platform — not just chatting: build, run, test, and trace autonomous agent teams with visual orchestration.

★ 311 FS 59 Major gaps 5mo ago Apache-2.0
Data & Analysis

DB-GPT: Open-Source Agentic AI Data Assistant

Connect your data, let AI write SQL and code autonomously, execute in sandboxes, and turn analysis into reports, insights, and action.

★ 20k FS 54 Major gaps 8d ago MIT
Dev & Engineering

Herm

A terminal-native AI coding agent that runs in containers by default, executing tasks safely without approval interruptions.

★ 231 FS 50 Major gaps 1mo ago MIT
Dev & Engineering

AgentScope Java

A Java framework for distributed, long-running, production-grade agents.

★ 5.8k FS 49 Major gaps today Apache-2.0
Productivity & Collaboration

OpenClaw Personal Assistant

A personal AI assistant that runs on your devices and meets you in the messaging channels you already use.

★ 390k FS 47 Major gaps 1d ago NOASSERTION
Automation & Ops

Open Browser

Give AI agents a browser — they click, type, navigate, and extract data autonomously from natural language tasks.

★ 9.5k FS 47 Major gaps 5mo ago MIT
Dev & Engineering

Banteg Agent Workflows

Isolate Codex and Claude coding tasks with worktrees, sandboxes, and devcontainers.

★ 372 FS 47 Major gaps 4mo ago
Automation & Ops

OpenAkita — Open-Source Multi-Agent AI Assistant

Not just chat — an AI team that gets things done.

★ 2k FS 45 Major gaps 6d ago AGPL-3.0
Dev & Engineering

CyberClaw Transparent Agent

An enterprise-grade transparent and controllable AI agent: full behavior auditing, two-phase safe invocation, and dual-watermark memory make every decision traceable.

★ 332 FS 45 Major gaps 13d ago MIT
Dev & Engineering

agentty

AI pair programming in your terminal: one static binary, sub-ms startup, any model, with local RAG that sends only the relevant code.

★ 604 FS 44 Major gaps today MIT