Developer mrsirg97-rgb released rig, a single-binary local agent runtime that assembles context, streams an OpenAI-compatible model endpoint, executes tool calls, and repeats, shipping 18 built-in too…
OtoDock released version 1.6.0, a Fair Source self-hosted platform that wraps Claude Code and Codex CLI into a multi-tenant app, running each agent as a persistent process inside a bubblewrap sandbox …
Anthropic has introduced a local Bash sandbox mode for Claude Code on desktop, using OS-level isolation to restrict command execution and cutting permission prompts by 84% since development began in O…
A security researcher identified a vulnerability in bubblewrap (bwrap), a sandboxing tool used by Flatpak, that could allow escape from the sandbox, though the risk is limited to malicious Flatpak app…
Pi coding agent (pi.dev) eliminates permission prompts by running inside sandboxes, containers, or virtual machines, according to a developer's blog post. The author describes a custom shell script us…
Talos, an open-source autonomous agent from talos-agent.ch, runs on a user's own machine and executes tools only after a deterministic security kernel approves each action via a capability token valid…
DeepSeek Harness, an open-source agent framework released as a developer preview, ships a fail-closed filesystem sandbox using bubblewrap, Landlock, Seatbelt, or Windows ACLs, but its documentation st…
Anthropic's Claude Code sandbox allows reading credential files such as ~/.aws/credentials and ~/.ssh/ by default, and the model can retry commands with the dangerouslyDisableSandbox parameter, accord…
Anthropic shipped OS-level sandboxing for Claude Code, using Seatbelt on macOS and bubblewrap on Linux/WSL2. The sandbox constrains Bash commands and their child processes, but not Claude Code's Read,…
Sandbox-bwrap-nix, a lightweight sandbox combining bubblewrap and Nix, boots in under a second with no daemon or root privileges, providing isolated environments for running AI coding agents and exper…
Anthropic detailed the containment architectures it uses for Claude across web, developer, and desktop products, arguing that agent safety depends on deterministic limits on filesystem, network, and e…
Developer Joe Swell built flar, a tool to sandbox AI agents using bubblewrap, and discovered that each agent CLI implements history and resume differently, requiring custom backends. He let each agent…
Claude Code and Codex both use OS-level process sandboxing to prevent AI models from executing harmful shell commands, relying on Linux primitives like bubblewrap for filesystem isolation and seccomp …
Lmcli v0.7.0, a general-purpose LLM harness written in Go, has been released with smooth performance at 1M+ token context and features including composable agents, custom tools, sandboxed execution, a…