Block
Open-source local AI agent from Block for coding and general computer workflows, with provider configuration and extension support.
Attributed output
GitHub public-attribution count, 2026-10-12
529Attributed 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
#26 of 40 CLI agents
#30Index rank · all agents#26 of 40 CLI agentsRanked 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 metric$0 BYOK
Entry price
BYOK only
$0 BYOKEntry priceBYOK onlyNot 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
88 commits · 10 repositories
Search window: – · captured Oct 14, 2026 (UTC)
4.5%4 / 88 sampled commits
4 of 88 unique sampled commits carry additional agent attribution (Codex, Claude). Counting each agent separately can therefore count the same commit more than once. This is shared attribution, not proof of a handoff or which tool did most of the work.
72.7%64 / 88 sampled commits
woodard/75fasmod accounts for 64 of the 88 distinct attributed commits returned. This makes the sample useful for studying that project’s workflow, but unsuitable as a picture of the agent’s wider adoption.
block/berd: “fix(berdctl): authenticate local control requests (#272)”. Hamlib/Hamlib: “Check for TIOCEXCL availability and conditionally compile ioctl calls”.
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.
Up to 100 returned search results ordered by commit date within the audit window; attribution trailers validated and duplicate SHAs removed across repositories. A recent convenience sample, not a random or exhaustive sample. Commit sample dates use the UTC committer timestamp, matching the search window. Excluded 1 commits with five or more distinct recognized agent/model credits in one message; broad credit lists are not used as evidence of a workflow.
Returned records dated Aug 4, 2026–Oct 8, 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 GitHub commits attributed to Goose
A conservative floor from explicit Goose attribution using its legacy organization identity. Broader name matches and newer attribution forms are excluded. This measures declared public work, not all Goose usage.
Last full week (ending 2026-10-11): 1 signed commits, search estimate.
Snapshot 2026-10-12, confidence Low, tracked since 2026-06-09. Read the methodology.
| Signal | Value | Type | Confidence |
|---|---|---|---|
| GitHub stars | 54,652 | Public metric | High |
Pricing snapshot: 2026-06-12. Check the vendor for current terms.
Free open-source agent from Block; runs on your own keys or existing Claude/ChatGPT/Gemini subscriptions.
Cost equals your provider's public token rate card.
| Plan | Price | Allowance | Unit | Token / Overage Notes |
|---|---|---|---|---|
| goose | $0 | Apache 2.0 agent with your own keys or local models. | BYOK |
Summary checked 2026-07-03.
Open-source local agent is free. Users pay configured model providers directly.