Verdoc

unreachable

Deterministic GitHub repository analysis and AGENTS.md generation - not written by a model, so it cannot hallucinate a command that does not exist. Every command is quoted from a manifest in the repository and every path is checked against the git tree, so results are reproducible for a given commit.

Not seen in any discovery source since 2026-10-01.

Transactions · 30d
0
Volume · 30d
$0.00
Unique buyers · 30d
0
Uptime · 30d
90.0%
Latency p50
200ms
Reported calls · 30d
15

Endpoints (2 live)

  • GET /scan — Deterministic facts about a public GitHub repository, for an agent deciding how to work in one it has never seen: toolchain commands with the manifest each was quoted from, directory layout, language split, CI and test presence, a 0-100 documentation-health score, and phantom_paths - paths the README cites that do not exist in the git tree. No language model is used, so the same commit always returns the same answer. (free)
  • GET /agents-md — An agent opening a repository it has never seen must read it before it can work in it, which costs tens of thousands of tokens. This returns that context for $0.02: an AGENTS.md with build and test commands quoted from the repository's own manifests, each tagged with the file it came from, plus a directory map, entry points and edit boundaries. No language model - every path is checked against the git tree and anything ambiguous is marked unverified rather than guessed. (free)

First seen · last seen