- 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.