tilde.run
tilde.runLet AI agents loose on production. Without the risk.
AI Toolsai-agentssandboxingversioningaudit-trailnetwork-isolationdevopssecurity
About
Tilde is a sandboxed execution platform that makes running AI agents on real production data safe and auditable. It composes GitHub, S3, and Google Drive into a single versioned POSIX filesystem, runs agents in isolated containers with network policy enforcement, and treats every run as an atomic transaction that can be rolled back with one command. It is built by the team behind lakeFS.
Problem
Running AI agents on real production data is risky because they can cause irreversible changes, exfiltrate data, or abuse credentials with no easy way to audit or undo their actions.
For
AI/ML engineers and platform teams deploying autonomous AI agents against production data
How it works
Tilde mounts code and data sources as a versioned filesystem, runs the agent in an isolated container with network call auditing and RBAC policies, then atomically commits or discards all changes at the end of the run.
Business model
freemium
Status
waitlist