Pangram verdict · v3.3
We believe that this document is primarily human-written, with some AI-generated content detected
AI likelihood · overall
MixedArticle text · 791 words · 5 segments analyzed
Let AI agents loose on production. Without the risk. Tilde turns every agent run into a transaction you can roll back. Code from GitHub, data from S3, and documents from Drive show up as a single versioned filesystem. Every outbound call is checked and logged. Autonomous code, finally safe to use against real data. Free to start · Join the private preview$ curl -fsSL https://tilde.run/install | sh
Reversible by default Roll back any agent run with one commandOne filesystem, all your data GitHub, S3, and Drive as a single ~/sandboxContained by default Isolated runs, every network call auditedYou stay in control Per-action policies and human approval gates
Hugging FaceClaudeAWS S3LangGraphGoogle DriveHugging FaceClaudeAWS S3LangGraphGoogle Drive
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. Every file is versioned from the first commit, and any agent run can be rolled back instantly. SOURCES~/sandboxgithub acme/ml-pipelines3 acme-data/traininggdrive team-wikilocal output/├─code├─data├─docs└─output all versioned · all reversible Safe Serverless Sandboxes Stop fearing the rogue-agent outcome.
Each run is a transaction in a fresh, isolated container - on a clean exit, changes commit atomically; on failure, nothing changes. No backups to restore, no manual cleanup, no infrastructure to manage. networkfilesystemcompute my-agent.pypython:3.12 512MB 2 CPU Network Isolation Stop data exfiltration, credential abuse, and prompt-injected callouts before they leave the box. Cloud metadata, private networks, and unauthorized hosts are blocked by default. Every outbound request is policy-checked and logged against the agent that made it. 12:04:01 GET api.openai.com/v1/completions ALLOW12:04:03 POST api.anthropic.com/v1/messages ALLOW12:04:05 GET pypi.org/simple/pandas ALLOW12:04:07 POST evil-exfil.io/upload DENY12:04:08 GET 169.254.169.254/metadata DENY12:04:09 PUT registry.npmjs.org/my-pkg DENY3 allowed 3 blocked Time Travel & Audit Trail Know exactly what happened, who did it, and why - down to the file. Browse the full timeline, inspect diffs, and revert any commit instantly. Every change is tied to the human, process, or agent that produced it. a1b2c3d4e5f67890ab12cd342d ago now@ 7890a1b2 rogue-agent · 4h ago− secrets/prod-keys.yaml+ exfil/dump.tar.gz~ config/network.json Agent-first RBAC Agents are first-class citizens, with their own scoped permissions - never your full user access.
Allow, deny, or require human approval per agent, per repository, per action. Granular policies in a simple, readable DSL. A analyst-agentREAD /data/*.csvALLOWWRITE /reports/q1.mdAPPROVEWRITE /secrets/keysDENYanalyst-policyGetObject(path:"/data/*")?PutObject(path:"/reports/*") # require human approval!!PutObject(path:"/secrets/*")
## QuickstartRun commands and interactive shells in sandboxes from your terminal. Built for CI/CD and agentic automation.Run agents in interactive shells or one-shot sandboxes, stream output, and commit. Done in a few lines of Python.Tell Claude to spin up a sandbox, run your agent, and atomically commit the results. In plain English.CLI 1 # Install in one line 2 $ curl -fsSL https://tilde.run/install | sh 3 4 # Run an agent in a sandbox 5 $ tilde exec my-team/documents \ 6 --image python:3.12 \ 7 -- /sandbox/code/agent.py --input /sandbox/data/reports 8 sandbox running... 9 sandbox completed. exit code: 0, commit id: c9d0e1f2 10 11 # Or start an interactive shell 12 $ tilde shell my-team/documents --image python:3.12 13 root@sb-7f3a9c01:/sandbox$ _ 1 import tilde 2 3 repo = tilde.repository("my-team/documents") 4 5 # Run an agent in an interactive sandbox 6 with repo.shell(image="python:3.12") as sh: 7 sh.run("pip install pandas") 8 result = sh.run("python agent.py --input /sandbox/data") 9 print(result.stdout.text())
10 11 # Or one-shot execution 12 result = repo.execute("python agent.py", image="python:3.12") 13 print(result.stdout.text()) 14 15 # Full audit trail 16 for commit in repo.timeline(): 17 print(commit.id[:8], commit.message)You Analyze the CSV files in our S3 data bucket and write a report to /sandbox/reports Agent I'll run the analysis on /sandbox/data/inputs/s3/, and commit the results. tilde exec my-team/documents \ --image analyst:latest \ -- ./code/agent.py --input ./data/inputs/s3 --output ./reportsAnalysis complete. 3 reports generated.Agent Sandbox execution complete, approval requiredWaiting for approval to commit sandbox results
sandbox sb-7f3a9c01Generate compliance reports from uploaded contractsanalyst-agent · 2 minutes ago+ reports/q1-summary.md + reports/q1-metrics.json + charts/revenue-trend.png - staging/raw-export.csve5f6a7b8Code review sandbox: fix auth middlewarecode-review-agent · 1 hour agoc9d0e1f2Import customer documents from S3sarah@acme.ai · 3 hours ago01 setupCompose FilesystemBuild a versioned repository from GitHub, S3, Drive, and more. Spin up an isolated sandbox with everything your agent needs.02 executeRun AgentYour agent runs in isolation. Every file write is staged. The entire run is captured as a transaction -- committed atomically or discarded entirely.03 decideCommit or RollbackReview the results. Approve and commit – or roll back and discard. One command, zero risk.
>Built by the team behind lakeFS We built lakeFS - the open-source data versioning layer trusted by some of the world's largest organizations to manage billions of objects. Tilde is built on that same battle-tested versioning foundation, reimagined as the filesystem platform the autonomous AI agent era demands.
~/workspace | my-team/documents ready$tilde exec acme/docs -- python agent.py● completed · committed a1b2c3d4$_ Make agents safe. Your first transactional, reversible agent run in 60 seconds. Join the private preview.