Scanned repository says: fx is the smallest coding agent: one native binary with no runtime to install. It's written in Zig and runs the same on your laptop, in CI, or inside an agent sandbox.
Metal Mantra scanned this public repository on its own initiative; the maintainer did not submit it. Maintainers: scan the repository yourself to take this report over, or contact us.
Inspect GitHub sourceVotes show community interest, not safety. They never change this score.
Runtime safety, real-world agent capability, fitness for your use case or independent certification.
Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.
fx is the smallest coding agent: one native binary with no runtime to install. It's written in Zig and runs the same on your laptop, in CI, or inside an agent sandbox.
README.md:16node-chat: a terminal chat with streamed replies.
README.md:89browser-agent: the agent in WebAssembly behind a plain HTML form.
README.md:90nextjs-agent: a Next.js App Router form with a streaming route handler.
README.md:91Small and fast: the Apple silicon release has a hard size limit, and startup is benchmarked on every pull request. CI fails a change if any measured command takes longer than 2 ms on Linux (benchmarks).
README.md:22Any model: use Vercel AI Gateway, your ChatGPT or Grok subscription, or any OpenAI-compatible endpoint such as Ollama or OpenRouter (custom connections).
README.md:23Your own shell: commands run in your login shell with your aliases, functions, and PATH. fx runs your startup files once and reuses the result, so a slow .zshrc doesn't slow down every command.
README.md:25No matching setup or dependency statement was extracted from inspected metadata.
Report vulnerabilities through the contact page instead of a public issue.
README.md:139A license or copying file is present; its terms have not been reviewed.
LICENSE:1These are references in selected source files, not proof that a feature works at runtime.
Read from commit d93acc5 at Oct 12, 2026, 5:16 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.
Critical details are withheld publicly for the first 30 days after a scan. A matched pattern is a lead for investigation, not a confirmed vulnerability.
Dependencies: no lockfile or exact version pins at the repository root, so no advisory check was possible.
Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.
Verify the domain using the Metal Mantra DNS TXT challenge.
The code returns the model's raw text. Output that was never parsed or validated can pass mistakes straight to users or other systems.
Parse and validate the result before returning it.
No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.
Expose a clear Privacy Policy link on the official homepage.
No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.
Expose a clear Terms link on the official homepage.
Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.
No user reports yet.
Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.
Share the full report so its scope and limits travel with the score.
