Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OMP, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry.
Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Agent Executor (AX) is Google's open agentic orchestration runtime
Astrid is a portable, capability-secure operating system for composable software.
Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()
The sandbox agent framework.
Agent Substrate: the core system
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Run thousands of AI agent sandboxes on the cheapest machines.
agent runtime security - zero trust, zero setup, zero latency agent sandboxing
The World's First Virtual Terminal for AI Agents
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
- google-meet
- meeting-assistant
- meeting-minutes
- meeting-notes
chroot, mount --bind, and binfmt_misc without privilege/setup for Linux
- chroot-environment
- userland-exec
- rootfs
- chroot
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents
Experimental Linux microvm setup with a TypeScript Control Plane as Agent Sandbox
Ultrafast serverless GPU inference, sandboxes, and background jobs
Sandboxes for coding agents, CI runners and RL training
Multi-OS sandbox to run AI agents with better constraints (it is not 100% secure, but enough)
Sandbox for securely executing untrusted programs
Centaur is frontier, agentic infrastructure that you own. Centaur is like Claude Tag, but open source and on steroids.
Hermit launches linux x86_64 programs in a special, hermetically isolated sandbox to control their execution. Hermit translates normal, nondeterministic behavior, into deterministic, repeatable behavior. This can be used for various applications, including replay-debugging, reproducible artifacts, chaos mode concurrency testing and bug analysis.
A ChatGPT plugin that allows you to load and edit your local files in a controlled way, as well as run any Python, JavaScript, and bash script. (No longer active - check https://github.com/ykdojo/safeclaw/)