A single category could not describe tools that ship as a CLI, an editor
plugin and a desktop app at once, and 7 of the 40 entries were filed
under a surface they only partly match — cline is "an SDK, IDE extension
or CLI assistant" in one `extension` slot, Reasonix ships CLI, desktop
and VS Code under `cli`, warp is a terminal filed as `ide`.
Tags cover five facets: surface (at least one), model access, workflow,
integration, and origin (at most one). tagVocabulary in validate.go is
the single source of truth — the validator, its error messages, and the
dashboard's filter chips all derive from it, the last via a new facets
field in site/data.json.
The dashboard now filters on tags with multi-select chips grouped by
facet: OR within a facet, AND across facets, plus a clear-filters
control, and search matches tags as well as name and description. Only
tags some row actually carries get a chip, so chips and rows cannot
disagree. Tag pills are tinted per facet, replacing the category badge.
All 40 entries are tagged from each repo's own README, topics and docs;
CONTRIBUTING documents every tag and the evidence rule for applying one.
A leftover `category:` key now fails validation with a message naming
its replacement, rather than being silently ignored.
README.md and data/history.jsonl are the regenerated updater output.
The maintenance criterion was unfalsifiable, so entries went years
without a push before anyone noticed by hand. The updater already
fetches pushedAt; warn when it is older than 90 days, alongside the
existing rename and archival annotations. Archived repos keep their own
warning rather than getting two.
Quantify the criterion in the README and CONTRIBUTING: dropped after 6
months idle, flagged past 3, with removal still a human decision.
Also correct two CONTRIBUTING claims the code contradicts — duplicates
are rejected by CI rather than ignored at run time, and renames do carry
history over once canonicalKeyMigrations has the old key.
- notes for gpt-engineer, void, Roo-Code (archived upstream) — shown
as badges + italics on the dashboard; kept for historical value
- README Contributing now states inclusion criteria: must BE a coding
agent (not tooling for agents), ~10k+ stars, open source + maintained
- resolves ambiguity for community PRs proposing sub-bar repos
- Add pi, OpenHands, warp, gpt-pilot, qwen-code, kilocode, onlook,
dyad, trae-agent, copilot-cli (19 -> 29 tracked repos)
- Update renamed slugs to canonical owners (anomalyco/opencode,
aaif-goose/goose, AntonOsika/gpt-engineer) with history key
migrations so star deltas survive the rename
- Generate site/data.json each run and deploy site/ (interactive
table + star-history chart) to GitHub Pages from the daily
workflow, since GITHUB_TOKEN bot pushes cannot trigger a separate
Pages workflow
Two new short docs unblock new contributors who currently have to read
the Go source to figure out the GITHUB_TOKEN requirement and the
agents.yml schema:
- docs/LOCAL_DEV.md walks through the PAT setup, the local run command,
what files the run modifies, and how to revert before opening a PR.
- docs/CONTRIBUTING.md documents the agents.yml fields, enumerates the
six valid category values, and explains the rename and deprecation
policy now that history is keyed canonically.
Also add a one-sentence caption under the table in readme.tmpl so the
Delta7d column has a definition in the rendered README.
Go updater that fetches AI agent coding tool repo stats via GitHub GraphQL
(batched, one query), sorts by star count, appends a daily snapshot to
data/history.jsonl, and regenerates README.md from templates/readme.tmpl.
Daily workflow at .github/workflows/update.yml refreshes rankings and
commits changes. Seed list in data/agents.yml covers 19 tracked repos.
tiennm99