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

Show HN: WUPHF — Karpathy-Style LLM Wiki with Markdown + Git as Source of Truth
WUPHF ships a wiki layer for AI agents using Markdown + Git for persistence, bleve (BM25) + SQLite for retrieval, with entity fact logs, wikilinks, and a daily lint cron. Runs locally with no vector DB dependency yet.

Claude Code Prompt Improver v0.5.3: Plan Mode Refactor and Subagent-First Research
v0.5.3 adds a PreToolUse hook for plan mode readability (clean rewrites, no decision history) and moves vague prompt research to Task/Explore subagents on Haiku to save main-context tokens. The plugin now works on Windows and has 1.4K+ GitHub stars.

Claude Code protocol file reduces repetitive questioning
A developer created a single .md file for ~/.claude/rules/ that infers task type and risk from the first message, eliminating Claude Code's typical three-question sequence before starting work.

Scaffold Framework Addresses Claude Code Memory and Workflow Issues
Scaffold is a 17-skill framework for Claude Code that provides persistent memory, decision enforcement, and workflow gates. It uses a 3-tier model routing system for token savings and can be installed via the Claude Code plugins menu.