An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Repository Index
47,133 repositories indexed
1–24 of 24 · Most stars
Secure, Fast, and Extensible Sandbox runtime for AI agents.
- ai
- ai-infra
- kubernetes
- sandbox
Personal memory across agents
- mcp
- memory
- sandbox
- agent-memory
Malware Configuration And Payload Extraction
- configs
- debugging-tools
- malware
- malware-analysis
Noriben - Portable, Simple, Malware Analysis Sandbox
Sandboxed Execution Environment
Script to create templates to use with VirtualBox to make vm detection harder
- virtualbox
- antivm
- sandbox
- malware-analysis
CuckooDroid - Automated Android Malware Analysis with Cuckoo Sandbox.
Automated Virtual Machine Generation and Cloaking for Cuckoo Sandbox.
Modified edition of cuckoo
Limon is a sandbox developed as a research project written in python, which automatically collects, analyzes, and reports on the run time indicators of Linux malware. It allows one to inspect Linux malware before execution, during execution, and after execution (post-mortem analysis) by performing static, dynamic and memory analysis using open source tools
Automated client-side template injection (sandbox escape/bypass) detection for AngularJS v1.x.
The Multiplatform Linux Sandbox
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
- ai-agents
- benchmark
- coding-agents
- embodied-ai
Toggle the iPhone call-recording announcement on/off from a Windows GUI, built on the airlift AirTraffic sandbox escape.
- airlift
- airtraffic
- ios
- sandbox-escape
Rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.
- clean-room-reimplementation
- ai-agents
- behavioral-testing
- black-box-testing
Minimal, consistent Python API for building integrations with malware sandboxes.
Randomly changes Win32/64 PE Files for 'safer' uploading to malware and sandbox sites.
Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.
- agent-framework
- agent-runtime
- agent-skills
- ai-agent
Airut is a system for running Claude Code tasks from email and Slack. It handles workspace provisioning, container isolation, network sandboxing, session persistence, and cleanup — a secure foundation for autonomous agentic development.
Sample staging & detonation utility to be used in combination with Cuckoo Sandbox.
One isolated Lima VM per GitHub project — sandboxed Claude Code/Codex, Docker, Node, signed git
Tor control port filter - whitelists which Tor control commands a client can use
- filter
- sandboxing
- security
- tor-control
Open BTC 5-minute prediction market sandbox for AI agents — register with one API call, get 1,000 test credits, and place a live order
- ai-agents
- prediction-markets
- starter-template
- trading-bot