Vercel
A hosted agent whose coding workflows review pull requests, validate findings in a sandbox, and propose tested fixes.
Attributed output
GitHub public-attribution count, 2026-10-12
99.5K PRsAttributed outputGitHub public-attribution count, 2026-10-12Commits and PRs on public GitHub provably produced by this agent. Exact if it is visible through its own bot or workflow, an estimate if measured through attribution it declares (these can swing 30 to 40 percent between measurement runs at multi-million scale), and a floor either way.Index rank · all agents
of 47 agents · trailing 4 weeks PRs
#7Index rank · all agentsof 47 agents · trailing 4 weeks PRsRanked by agent-opened PRs in the trailing 4 complete weeks, matching the index. Agents without a tracked PR series follow, ordered by total attributed output. Other filters or sorts change the list position.n/a
Business signal
No sourced business metric
n/aBusiness signalNo sourced business metricPro / Enterprise + usage
Entry price
Inference tokens and platform usage
Pro / Enterprise + usageEntry priceInference tokens and platform usageNot published
GitHub stars
No public repo
Not publishedGitHub starsNo public repoNot published
npm demand/wk
Public npm counter
Not publishednpm demand/wkPublic npm counterWeekly package downloads as an install-demand floor; adjusted when the vendor's main install channel is no longer npm.From the public record
500 PRs · 401 repositories
Search window: – · captured Oct 14, 2026 (UTC)
99.6%498 / 500 sampled PRs
498 of 500 sampled PR titles explicitly name Web Analytics or Speed Insights. These span 400 repositories. In this sample, the Vercel Agent identity mostly appears as a product-integration installer; this is not a breakdown of every capability the product offers.
hiberin/hibersunda: “Install Vercel Speed Insights package” (merged). k4hav/FlixBase: “Setup Vercel Web Analytics Integration” (merged).
This is a sample of publicly attributed work, not total usage or a market-share estimate. Repositories are not customers. Attribution is declared in metadata, not independently verified tool execution; it does not prove exclusive authorship or autonomy. PR status is recorded at capture; merged does not establish correctness.
Up to 100 most recently created search results in each of five consecutive 28-day windows; post-filtered for attribution in the PR body, bot author, or Codex branch. Not a random or exhaustive sample.
Returned records dated Jun 21, 2026–Oct 11, 2026.
Download the dated audit evidence (JSON)Weekly attributed output on public GitHub. Output visible through the agent's own bot or workflow is exact; output measured through declared attribution is an estimate. Window: 2025-02-03 to 2026-10-05.
Public pull requests opened by Vercel Agent
Public PRs carrying explicit Vercel Agent task attribution. A conservative estimate: Vercel's shared automation also serves other products, so its broad activity is excluded. Reviews without an agent-authored PR are not counted.
Last full week (ending 2026-10-11): 2,009 agent-marked PRs (-4.2% week over week), search estimate.
Merge rate: 33.1% of its pull requests get merged (5,812 of 17,572 over 8 settled weeks, 2026-08-10 to 2026-10-04). The window ends about ten days back so recently-opened PRs have had time to merge.
GitHub review activity: 5.8% of its merged PRs had at least one GitHub review record before merging; the other 94.2% had none. This is a broad weekly signal and can include bot reviews; the human-review read below comes from the enriched PR sample.
Snapshot 2026-10-12, confidence Medium, tracked since 2026-06-09. Read the methodology.
Pricing snapshot: 2026-10-12. Check the vendor for current terms.
Inference at cost plus $0.25 per million tokens, on Vercel Pro or Enterprise.
The Vercel fee is $0.25 per million tokens in addition to provider inference. There is no fixed token budget.
| Plan | Price | Allowance | Unit | Token / Overage Notes |
|---|---|---|---|---|
| Agent usage | Provider inference + $0.25/M tokens | Pay for code-review usage on an eligible Vercel plan. | Tokens |
Summary checked 2026-10-12.
Available on Vercel Pro and Enterprise. Agent usage bills provider inference at cost plus $0.25 per million tokens; underlying Vercel product charges also apply.