Commit Graph
181 Commits
Author SHA1 Message Date
github-actions[bot] 60ad3a4222 chore: daily ranking refresh 2026-10-10 04:54:47 +00:00
github-actions[bot] 27bc6703fc chore: daily ranking refresh 2026-10-09 05:09:26 +00:00
github-actions[bot] 9eb2b311ad chore: daily ranking refresh 2026-10-08 05:06:20 +00:00
github-actions[bot] aff71f3f54 chore: daily ranking refresh 2026-10-07 04:56:04 +00:00
github-actions[bot] 40fb59ddec chore: daily ranking refresh 2026-10-06 05:27:03 +00:00
github-actions[bot] e63f56b8a3 chore: daily ranking refresh 2026-10-05 04:40:42 +00:00
github-actions[bot] 28594aecaa chore: daily ranking refresh 2026-10-04 04:52:56 +00:00
github-actions[bot] 655c7c7bf6 chore: daily ranking refresh 2026-10-03 04:21:45 +00:00
github-actions[bot] f0d074023b chore: daily ranking refresh 2026-10-02 04:39:13 +00:00
github-actions[bot] 350bd5e3dd chore: daily ranking refresh 2026-10-01 16:23:47 +00:00
tiennm99 809067d7a0 feat(agents): track t3code
Add T3 Code as an agent development environment. OpenClaw and Hermes Agent were reviewed and left out as general-purpose assistants.
2026-10-01 23:23:19 +07:00
github-actions[bot] 3d00a0a7b2 chore: daily ranking refresh 2026-10-01 04:48:01 +00:00
github-actions[bot] c239cc3582 chore: daily ranking refresh 2026-09-30 04:36:25 +00:00
github-actions[bot] f6556619e0 chore: daily ranking refresh 2026-09-29 06:09:42 +00:00
tiennm99 98e5b90951 feat(agents): curate descriptions and track 3 new agents
Add MiMo-Code, pr-agent and open-swe, and note upstream status changes for gpt-pilot, kimi-cli and SWE-agent.
2026-09-29 13:09:13 +07:00
github-actions[bot] 14a013a151 chore: daily ranking refresh 2026-09-29 04:50:24 +00:00
github-actions[bot] 1fd937f853 chore: daily ranking refresh 2026-09-28 04:19:43 +00:00
github-actions[bot] 43d78bdb34 chore: daily ranking refresh 2026-09-27 04:18:29 +00:00
github-actions[bot] 5afed448f6 chore: daily ranking refresh 2026-09-26 04:05:01 +00:00
github-actions[bot] 98f8f8a676 chore: daily ranking refresh 2026-09-25 03:59:48 +00:00
github-actions[bot] af6e8a613c chore: daily ranking refresh 2026-09-24 03:44:00 +00:00
github-actions[bot] d45add8dd0 chore: daily ranking refresh 2026-09-23 03:51:50 +00:00
github-actions[bot] c7fd2c1464 chore: daily ranking refresh 2026-09-22 03:54:05 +00:00
github-actions[bot] b139ceab55 chore: daily ranking refresh 2026-09-21 03:56:41 +00:00
github-actions[bot] c3159c1f0b chore: daily ranking refresh 2026-09-20 03:58:55 +00:00
github-actions[bot] f8e782c22a chore: daily ranking refresh 2026-09-19 03:43:08 +00:00
github-actions[bot] 18f17a6fe9 chore: daily ranking refresh 2026-09-18 03:46:21 +00:00
github-actions[bot] 1b4a6d3125 chore: daily ranking refresh 2026-09-17 03:59:17 +00:00
github-actions[bot] b47754fabe chore: daily ranking refresh 2026-09-16 15:31:21 +00:00
github-actions[bot] 8eeda94f82 chore: daily ranking refresh 2026-09-16 15:28:54 +00:00
tiennm99 1a5792e69e Merge branch 'add-orca-paseo-ade' 2026-09-16 22:27:46 +07:00
tiennm99 00c90c5be9 feat: split data update from site build; publish via Cloudflare Pages
The updater fetched GitHub metadata and rendered the dashboard payload in
a single step, so anything that published the site needed a GITHUB_TOKEN.
Cloudflare Pages builds from a Git webhook and has no business holding
one.

Split the tool into three modes. The default update step still fetches
GitHub and now records every API-sourced field in data/metadata.json,
which is committed alongside README.md and data/history.jsonl. The new
-build mode joins that snapshot with data/agents.yml and
data/history.jsonl to render dist/ with no network access and no token;
-check is unchanged.

Supporting changes:

- computeDeltaAt anchors the delta windows to when the data was fetched
  rather than the wall clock, so a redeploy days later reproduces the
  same Δ7d instead of sliding the window past its slack allowance.
- writeSiteData takes updatedAt explicitly for the same reason: the
  timestamp labels data freshness, not build time.
- sortStats is extracted from fetchStats so the build step re-ranks
  identically from committed metadata.
- An agents.yml entry with no metadata yet is omitted with a warning
  instead of failing the build, which would otherwise block every deploy
  between merging a new entry and the next nightly run.
- update.yml drops the GitHub Pages deploy steps and commits
  data/metadata.json; ci.yml runs `go run . -build` so a build that would
  break on deploy breaks in CI first.
- site/_headers stops the edge serving a stale data.json after a refresh.
- docs/DEPLOY.md covers the Cloudflare setup, including the one-time
  bootstrap of data/metadata.json that the build depends on.

Also carries the in-progress curation work already in the tree: the
module rename to awesome-ai-dev-tools, retagged entries, and removal of
the archived Roo-Code, void, continue and suna entries.
2026-09-16 22:24:48 +07:00
tiennm99 21ad0d47a5 feat: admit agent development environments; add Orca and Paseo
Criterion 1 previously excluded "workspaces for agents", which ruled out
the ADE category entirely. ADEs are the surface a developer actually works
in, the same way a coding agent is, so they now qualify on their own terms.
Libraries, SDKs, skill collections and observability-only layers stay out.

- Widen inclusion criterion 1 in templates/readme.tmpl and document the
  two admitted kinds in docs/CONTRIBUTING.md.
- Add `orchestration` to the Workflow facet in validate.go so ADEs are
  filterable as a distinct class on the dashboard.
- Add stablyai/orca (70.0k) and getpaseo/paseo (17.5k).

README.md is regenerated from the template by the daily run; its
Contributing section is updated here so it is not stale in the meantime.

go run . -check: 43 agents valid. go test ./...: ok.
2026-09-16 21:11:54 +07:00
github-actions[bot] f086baf98b chore: daily ranking refresh 2026-09-16 14:01:47 +00:00
BlueSkyID666andBlueSkyID666 9a8048560b Add Orkas (#14)
Signed-off-by: BlueSkyID666 <280636370+BlueSkyID666@users.noreply.github.com>
Co-authored-by: BlueSkyID666 <280636370+BlueSkyID666@users.noreply.github.com>
2026-09-16 21:01:22 +07:00
github-actions[bot] 01d80a470e chore: daily ranking refresh 2026-09-16 03:54:03 +00:00
github-actions[bot] 932cb21b94 chore: daily ranking refresh 2026-09-15 03:56:38 +00:00
github-actions[bot] 971e3880ba chore: daily ranking refresh 2026-09-14 03:57:14 +00:00
github-actions[bot] e8ee1de536 chore: daily ranking refresh 2026-09-13 03:49:30 +00:00
github-actions[bot] 408328cfd9 chore: daily ranking refresh 2026-09-12 03:41:55 +00:00
github-actions[bot] 7b990b555d chore: daily ranking refresh 2026-09-11 09:25:09 +00:00
github-actions[bot] 0de86badc5 chore: daily ranking refresh 2026-09-11 09:07:30 +00:00
github-actions[bot] c64cd0c559 chore: daily ranking refresh 2026-09-11 08:46:52 +00:00
github-actions[bot] a99972438b chore: daily ranking refresh 2026-09-11 08:40:45 +00:00
tiennm99 eb12bcc2cb feat: replace category with a multi-facet tag vocabulary
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.
2026-09-11 15:40:18 +07:00
github-actions[bot] e49c487700 chore: daily ranking refresh 2026-09-11 07:37:51 +00:00
github-actions[bot] 2e2ad56add chore: daily ranking refresh 2026-09-11 07:30:12 +00:00
github-actions[bot] 1262e3435b chore: daily ranking refresh 2026-09-11 07:21:35 +00:00
tiennm99 94e9852cfd feat(agents): track 14 active agents, drop 3 abandoned ones
Adds deepseek-harness (top of the list by stars), grok-build,
openinterpreter, Codewhale, DeepSeek-Reasonix, openclaude, oh-my-pi,
open-code-review, prime-agent, jcode, DeepCode, freebuff, kimi-cli and
claurst, all meeting the inclusion criteria.

Drops bolt.new, plandex and trae-agent: no upstream push in 21, 11 and 7
months respectively.

Also points avante.nvim at its current canonical slug and maps the old
history key so its star history stays attached.
2026-09-11 14:21:11 +07:00
github-actions[bot] 3a911dd3a5 chore: daily ranking refresh 2026-09-11 03:37:50 +00:00