Tilde.run: An Agent Sandbox with a Transactional, Versioned Filesystem

Tilde.run is a sandbox for AI agents that turns every agent run into a reversible transaction. It creates a single versioned filesystem from multiple data sources — GitHub, S3, and Google Drive are mounted as a single ~/sandbox directory. Every file is versioned from the first commit, and any agent run can be rolled back instantly with one command.
Key Features
Versioned Composable Filesystem
A real POSIX filesystem—any tool, any language, no SDKs. Mount code from GitHub, training data from S3, and documents from Google Drive as a single ~/sandbox. Example mounts:
4 mounts
~/sandbox
├── code github acme/ml-pipeline
├── data s3 acme-data/training
├── docs gdrive team-wiki
└── output local
All versioned, all reversible.
Safe Serverless Sandboxes
Each run is a transaction in a fresh, isolated container. On clean exit, changes commit atomically; on failure, nothing changes. No backups to restore, no manual cleanup.
Network Isolation
Cloud metadata, private networks, and unauthorized hosts are blocked by default. Every outbound request is policy-checked and logged. Example egress log:
12:04:01 GET api.openai.com /v1/completions ALLOW
12:04:03 POST api.anthropic.com /v1/messages ALLOW
12:04:05 GET pypi.org /simple/pandas ALLOW
12:04:07 POST evil-exfil.io /upload DENY
12:04:08 GET 169.254.169.254 /metadata DENY
12:04:09 PUT registry.npmjs.org /my-pkg DENY
Time Travel & Audit Trail
Browse the full timeline, inspect diffs, and revert any commit instantly. Every change is tied to the human, process, or agent that produced it.
Agent-first RBAC
Agents have scoped permissions—never full user access. Granular policies in a simple DSL. Example policy:
analyst-policy
GetObject (path: "/data/*") ?
PutObject (path: "/reports/*") # require human approval!
! PutObject (path: "/secrets/*")
Quickstart
Install in one line:
$ curl -fsSL https://tilde.run/install | sh
Run an agent in a sandbox:
$ tilde exec my-team/documents \
--image python:3.12 \
-- /sandbox/code/agent.py --input /sandbox/data/reports
sandbox running...
sandbox completed. exit code: 0, commit id: c9d0e1f2
Or start an interactive shell:
$ tilde shell my-team/documents --image python:3.12
root@sb-7f3a9c01:/sandbox$ _
Python SDK:
import tilde
repo = tilde.repository("my-team/documents")
with repo.shell(image="python:3.12") as sh:
sh.run("pip install pandas")
result = sh.run("python agent.py --input /sandbox/data")
print(result.stdout.text())
Integrates with Claude, AWS S3, LangGraph, Google Drive, and Hugging Face.
📖 Read the full source: HN AI Agents
👀 See Also

Claude Code Rebuilt a SaaS Onboarding Flow in 6 Hours vs Developer's 3-Week Quote, Boosting Activation 13 Points
A SaaS founder used Claude Code to rebuild their entire onboarding flow (signup → profile → first invoice → dashboard tutorial) in 6 hours, replacing a developer's $4,500, 3-week estimate. Activation rate improved 13 points from 35% to 48%.

Building a Sub-500ms Voice Agent: Architecture and Performance Insights
A developer built a voice agent from scratch achieving ~400ms end-to-end latency with full STT → LLM → TTS streaming. Key insights include treating voice as a turn-taking problem, using semantic end-of-turn detection, and colocating all components for minimal latency.

Free AI Product Launch Playbook Repository for Claude Users
A developer has released a free repository containing a structured AI product launch playbook designed to work with Claude. The repo organizes launch experience into practical stages including strategy, preparation, execution, and includes templates and tool references.

Claude File History: VS Code Extension for Tracking Claude Code Sessions
A VS Code extension called Claude File History tracks every Claude Code session that touched your files, allowing you to find past conversations, preview what was discussed, and resume conversations with a double-click.