# earendil-works/gondolin

Experimental Linux microvm setup with a TypeScript Control Plane as Agent Sandbox

Repository: https://github.com/earendil-works/gondolin
Canonical: https://ross.abutalabs.com/products/gondolin
Homepage: https://earendil-works.github.io/gondolin
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-07-06T10:21:13+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 84, longevity 15
- inputs: {"age_days": 211, "days_push": 58, "days_rel": 106, "gap_med": 0, "n_releases_24m": 26}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2034, forks 124 (observed 2026-08-28T04:06:07.909079+00:00)

## What it is
Gondolin is a TypeScript library and CLI that runs untrusted AI-agent code inside fast local Linux micro-VMs (QEMU by default, optional libkrun backend). Network egress and filesystem access are controlled programmatically from the host, with secrets injected only for allowed destinations to prevent exfiltration.

## Use cases
- sandbox AI agent generated code before running it
- run curl commands with secrets the guest can never see
- restrict which hosts a sandboxed process can reach
- snapshot and resume isolated dev sessions
- give agents a disposable Linux environment with controlled filesystem access
- prevent credential exfiltration from untrusted code

## When to choose
- you run LLM-generated code locally and need egress and secret protection
- you want programmable network/filesystem policy in JavaScript
- you need fast-booting micro-VMs on macOS or Linux without cloud sandboxes

## When to avoid
- you need production-grade, audited isolation guarantees
- you are not on macOS or Linux
- you need Windows sandboxing or GPU workloads inside the VM

## Facets
- artifact type: library
- maturity: experimental
- function: security, networking, secrets-management, cli, developer-tools
- domain: security, developer-tools, self-hosted
- platform: cli
- tags: microvm, qemu, libkrun, agent-sandbox, egress-control, secret-injection, typescript, ai-agent-safety, sandboxing, virtualization, ai-agents, linux, macos, nodejs

## Member repositories
- earendil-works/gondolin (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:07.909079+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:59:23.826749+00:00, confidence not recorded.
  - readme: https://github.com/earendil-works/gondolin (fetched 2026-08-28T04:06:07.909079+00:00, sha d6af7fc177ae)
  - homepage: https://earendil-works.github.io/gondolin (fetched 2026-08-29T10:39:08.747591+00:00, sha a0463825852a)
- Data as of 2026-08-30T08:39:29.467469+00:00.