Show HN: Bot-bottle – secure runtime, DLP and remote control for local agents
Hey! About 6 months ago, I started looking for a tool to safely run coding agents on my (security sensitive) developer machine. Specifically, I wanted a tool that: - I could use regardless of the model or harness running underneath - I could build simple, composable, plaintext security policies for - Provided strong vm level isolation - Hid credentials from agents - Scanned and monitored everything going in and out of agent workspace - Allowed me to use the same mobile flow I had gotten used to
Read original source
Source record
Recorded metrics
points · 1 votes
2026-11-11 20:00:17.870Z
cumulative since publication
Research analysis
Project record
Repository: diderisoft/bot-bottle. Source account: Hey! About 6 months ago, I started looking for a tool to safely run coding agents on my (security sensitive) developer machine. Specifically, I wanted a tool that: - I could use regardless of the model or harness running underneath - I could build simple, composable, plaintext security policies for - Provided strong vm level isolation - Hid credentials from agents - Scanned and monitored everything going in and out of agent workspace - Allowed me to use the same mobile flow I had gotten used to
Observed adoption & comparisons
Source votes: 1 votes (Nov 11, 2026 UTC; cumulative since publication) Recent records to compare: “Show HN: Motion Debugger – A browser critic for AI slop” (Show HN, Nov 12, 2026); “Show HN: Receipts, agent skills that make PRDs and metrics cite their evidence” (Show HN, Nov 12, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.