Show HN: AnyFrame – Sandboxes for AI Agents
TL;DR
Hey HN! com, a way to point Claude Code or Codex at any repo and get a fresh sandbox running it in seconds. com/tinyhq/anyframe-python AnyFrame has three key features - define an agent once (repo, install cmd, skills, MCPs) and it bakes a cached image - boot a session and chat with it from the web or from Python on the same channel - plug in MCP connectors (Linear, Sentry, …) once and toggle them per-agent. Let me know if you have any questions/comments/feature requests!
Nauti's Take
Promising build: AnyFrame lowers the bar to spin up Claude Code or Codex in a sandbox against any repo in seconds — a clear productivity win for agent tinkerers. Risk: Sandbox cache layers can obscure security assumptions; for sensitive code a second look at isolation and secrets handling is warranted.
For devs with agent workflows a useful tool; in enterprise contexts only after a security review.
Sources