AI Index / Open-source developer documentation tools / History

Open-source developer documentation tools — AI Recommendation History

What AI assistants recommended for open-source developer documentation tools, date by date. Every ranking we publish is frozen the day it publishes, so this is a record of what was said — not a re-computation of what today's data would say about the past.

Record: 26 dated snapshots · Aug 14, 2026 – Sep 8, 2026

Answer archive Methodology Data studies JSON

What changed

Computed by comparing each dated snapshot with the one before it. Share moves smaller than 1pp are treated as noise and left out — the same threshold that suppresses trend arrows on the ranking.

Sep 8, 2026vs Sep 7, 2026

▲ INBookStack entered the top 10 (#11 → #7)
▲ INWiki.js entered the top 10 (#12 → #10)
▼ OUTRedocly left the top 10 (#9 → #11)
▼ OUTGitBook left the top 10 (#10 → #12)
▲BookStack moved #11 → #7
▲Wiki.js moved #12 → #10
▼Redocly moved #9 → #11
▼GitBook moved #10 → #12
▲Python moved #4 → #3
▼Material moved #3 → #4
▼Redoc moved #7 → #8
▼Read the Docs moved #8 → #9
▲Git +8.1pp (41% → 49.1%)
▲BookStack +7.6pp (28.2% → 35.8%)
▲Wiki.js +5.2pp (23.1% → 28.3%)
▲MkDocs +4.8pp (74.4% → 79.2%)
▼Redoc -4.5pp (38.5% → 34%)
▲Sphinx +4.3pp (41% → 45.3%)
▲Docusaurus +4.1pp (84.6% → 88.7%)
▼Redocly -3.7pp (28.2% → 24.5%)
▼GitBook -3.7pp (28.2% → 24.5%)
▲Read the Docs +1.3pp (30.8% → 32.1%)
▼Material -1pp (53.8% → 52.8%)

Sep 7, 2026vs Sep 6, 2026

No change above the noise floor.

Sep 6, 2026vs Sep 5, 2026

No change above the noise floor.

Sep 5, 2026vs Sep 4, 2026

No change above the noise floor.

Sep 4, 2026vs Sep 3, 2026

No change above the noise floor.

Sep 3, 2026vs Sep 2, 2026

No change above the noise floor.

Sep 2, 2026vs Sep 1, 2026

No change above the noise floor.

Sep 1, 2026vs Aug 31, 2026

No change above the noise floor.

Aug 31, 2026vs Aug 30, 2026

No change above the noise floor.

Aug 30, 2026vs Aug 29, 2026

No change above the noise floor.

Aug 29, 2026vs Aug 28, 2026

No change above the noise floor.

Aug 28, 2026vs Aug 27, 2026

No change above the noise floor.

Aug 27, 2026vs Aug 26, 2026

Methodology change: extraction rules 4-7 → 5-7 between these dates. Differences below may reflect the rule change rather than a change in what AI recommends — see the methodology changelog.

▲ INRead the Docs entered the top 10 (#11 → #8)
▲ INRedocly entered the top 10 (#16 → #9)
▼ OUTBookStack left the top 10 (#8 → #11)
▼ OUTWiki.js left the top 10 (#9 → #12)
▲Redocly moved #16 → #9
▲Read the Docs moved #11 → #8
▼BookStack moved #8 → #11
▼Wiki.js moved #9 → #12
▼Wiki.js -7.1pp (30.2% → 23.1%)
▼Git -6.2pp (47.2% → 41%)
▼BookStack -5.8pp (34% → 28.2%)
▲Redocly +5.6pp (22.6% → 28.2%)
▼Material -4.7pp (58.5% → 53.8%)
▼Python -4.7pp (58.5% → 53.8%)
▼Docusaurus -4.1pp (88.7% → 84.6%)
▲Read the Docs +2.5pp (28.3% → 30.8%)
▼MkDocs -1.1pp (75.5% → 74.4%)

Aug 26, 2026vs Aug 25, 2026

No change above the noise floor.

Aug 25, 2026vs Aug 24, 2026

No change above the noise floor.

Aug 24, 2026vs Aug 23, 2026

No change above the noise floor.

Aug 23, 2026vs Aug 22, 2026

▲ INGitBook entered the top 10 (#13 → #10)
▼ OUTRead the Docs left the top 10 (#10 → #11)
▲GitBook moved #13 → #10
▲Python moved #5 → #4
▼Git moved #4 → #5
▼Read the Docs moved #10 → #11
▲Python +12.2pp (46.3% → 58.5%)
▲Material +4.8pp (53.7% → 58.5%)
▼BookStack -3.3pp (37.3% → 34%)
▲Sphinx +2.7pp (38.8% → 41.5%)
▼Wiki.js -2.6pp (32.8% → 30.2%)
▼Docusaurus -2.3pp (91% → 88.7%)
▼Git -2.1pp (49.3% → 47.2%)
▼Read the Docs -1.6pp (29.9% → 28.3%)
▲GitBook +1.4pp (26.9% → 28.3%)

Aug 22, 2026vs Aug 21, 2026

▲ INRead the Docs entered the top 10 (#11 → #10)
▼ OUTHugo left the top 10 (#10 → #12)
▼Hugo moved #10 → #12
▲Sphinx moved #7 → #6
▼Redoc moved #6 → #7
▲Read the Docs moved #11 → #10
▲Python +4.4pp (41.9% → 46.3%)
▲Read the Docs +2.9pp (27% → 29.9%)
▼Hugo -2.7pp (31.1% → 28.4%)
▲Sphinx +2.3pp (36.5% → 38.8%)
▲BookStack +2.2pp (35.1% → 37.3%)
▲Docusaurus +1.8pp (89.2% → 91%)
▲MkDocs +1.8pp (74.3% → 76.1%)
▲Wiki.js +1.7pp (31.1% → 32.8%)

Aug 21, 2026vs Aug 20, 2026

▲Sphinx moved #8 → #7
▼BookStack moved #7 → #8
▼Git -5.1pp (53.7% → 48.6%)
▼Docusaurus -4.8pp (94% → 89.2%)
▼Wiki.js -3.2pp (34.3% → 31.1%)
▼Material -2.6pp (56.7% → 54.1%)
▼Redoc -2.5pp (40.3% → 37.8%)
▼BookStack -2.2pp (37.3% → 35.1%)
▼MkDocs -1.8pp (76.1% → 74.3%)
▼Hugo -1.7pp (32.8% → 31.1%)

Aug 20, 2026vs Aug 19, 2026

Methodology change: extraction rules 4-5 → 4-7 between these dates. Differences below may reflect the rule change rather than a change in what AI recommends — see the methodology changelog.

▲ INSphinx entered the top 10 (#11 → #8)
▼ OUTDocmost left the top 10 (#9 → #12)
▲Python moved #10 → #5
▲Sphinx moved #11 → #8
▼Hugo moved #7 → #10
▼Docmost moved #9 → #12
▼Redoc moved #5 → #6
▼BookStack moved #6 → #7
▼Wiki.js moved #8 → #9
▲Python +13.6pp (28.2% → 41.8%)
▲Sphinx +7.6pp (28.2% → 35.8%)
▼Hugo -5.7pp (38.5% → 32.8%)
▲Material +5.4pp (51.3% → 56.7%)
▲MkDocs +4.3pp (71.8% → 76.1%)
▲Git +2.4pp (51.3% → 53.7%)
▼Docmost -2.4pp (30.8% → 28.4%)
▼Wiki.js -1.6pp (35.9% → 34.3%)
▼BookStack -1.2pp (38.5% → 37.3%)

Aug 19, 2026vs Aug 18, 2026

▲ INPython entered the top 10 (#20 → #10)
▼ OUTDocsify left the top 10 (#10 → #12)
▲Python moved #20 → #10
▼Docsify moved #10 → #12
▲Redoc moved #6 → #5
▼BookStack moved #5 → #6
▲Hugo moved #8 → #7
▼Wiki.js moved #7 → #8
▲Python +9.9pp (18.3% → 28.2%)
▲Hugo +6.8pp (31.7% → 38.5%)
▼MkDocs -6.5pp (78.3% → 71.8%)
▼BookStack -6.5pp (45% → 38.5%)
▼Material -3.7pp (55% → 51.3%)
▼Docsify -2.7pp (28.3% → 25.6%)
▼Wiki.js -2.4pp (38.3% → 35.9%)
▼Redoc -2.3pp (43.3% → 41%)
▼Git -2pp (53.3% → 51.3%)
▼Docusaurus -1.8pp (96.7% → 94.9%)

Aug 18, 2026vs Aug 17, 2026

No change above the noise floor.

Aug 17, 2026vs Aug 16, 2026

No change above the noise floor.

Aug 16, 2026vs Aug 15, 2026

No change above the noise floor.

Aug 15, 2026vs Aug 14, 2026

No change above the noise floor.

The ranking, date by date

Top 10 on each archived date, exactly as published. Cite a date and it stays true: snapshots are append-only, and a correction appends a new revision rather than overwriting the original.

Sep 8, 202653 sampled answers · window 2026-08-11 – 2026-09-08 · rules v5-7

#1Docusaurus88.7%
#2MkDocs79.2%
#3Python54.7%
#4Material52.8%
#5Git49.1%
#6Sphinx45.3%
#7BookStack35.8%
#8Redoc34%
#9Read the Docs32.1%
#10Wiki.js28.3%

Sep 7, 202639 sampled answers · window 2026-08-10 – 2026-09-07 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Sep 6, 202639 sampled answers · window 2026-08-09 – 2026-09-06 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Sep 5, 202639 sampled answers · window 2026-08-08 – 2026-09-05 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Sep 4, 202639 sampled answers · window 2026-08-07 – 2026-09-04 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Sep 3, 202639 sampled answers · window 2026-08-06 – 2026-09-03 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Sep 2, 202639 sampled answers · window 2026-08-05 – 2026-09-02 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Sep 1, 202639 sampled answers · window 2026-08-04 – 2026-09-01 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Aug 31, 202639 sampled answers · window 2026-08-03 – 2026-08-31 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Aug 30, 202639 sampled answers · window 2026-08-02 – 2026-08-30 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Aug 29, 202639 sampled answers · window 2026-08-01 – 2026-08-29 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Aug 28, 202639 sampled answers · window 2026-07-31 – 2026-08-28 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Aug 27, 202639 sampled answers · window 2026-07-30 – 2026-08-27 · rules v5-7

#1Docusaurus84.6%
#2MkDocs74.4%
#3Material53.8%
#4Python53.8%
#5Git41%
#6Sphinx41%
#7Redoc38.5%
#8Read the Docs30.8%
#9Redocly28.2%
#10GitBook28.2%

Aug 26, 202653 sampled answers · window 2026-07-29 – 2026-08-26 · rules v4-7

#1Docusaurus88.7%
#2MkDocs75.5%
#3Material58.5%
#4Python58.5%
#5Git47.2%
#6Sphinx41.5%
#7Redoc37.7%
#8BookStack34%
#9Wiki.js30.2%
#10GitBook28.3%

Aug 25, 202653 sampled answers · window 2026-07-28 – 2026-08-25 · rules v4-7

#1Docusaurus88.7%
#2MkDocs75.5%
#3Material58.5%
#4Python58.5%
#5Git47.2%
#6Sphinx41.5%
#7Redoc37.7%
#8BookStack34%
#9Wiki.js30.2%
#10GitBook28.3%

Aug 24, 202653 sampled answers · window 2026-07-27 – 2026-08-24 · rules v4-7

#1Docusaurus88.7%
#2MkDocs75.5%
#3Material58.5%
#4Python58.5%
#5Git47.2%
#6Sphinx41.5%
#7Redoc37.7%
#8BookStack34%
#9Wiki.js30.2%
#10GitBook28.3%

Aug 23, 202653 sampled answers · window 2026-07-26 – 2026-08-23 · rules v4-7

#1Docusaurus88.7%
#2MkDocs75.5%
#3Material58.5%
#4Python58.5%
#5Git47.2%
#6Sphinx41.5%
#7Redoc37.7%
#8BookStack34%
#9Wiki.js30.2%
#10GitBook28.3%

Aug 22, 202667 sampled answers · window 2026-07-25 – 2026-08-22 · rules v4-7

#1Docusaurus91%
#2MkDocs76.1%
#3Material53.7%
#4Git49.3%
#5Python46.3%
#6Sphinx38.8%
#7Redoc37.3%
#8BookStack37.3%
#9Wiki.js32.8%
#10Read the Docs29.9%

Aug 21, 202674 sampled answers · window 2026-07-24 – 2026-08-21 · rules v4-7

#1Docusaurus89.2%
#2MkDocs74.3%
#3Material54.1%
#4Git48.6%
#5Python41.9%
#6Redoc37.8%
#7Sphinx36.5%
#8BookStack35.1%
#9Wiki.js31.1%
#10Hugo31.1%

Aug 20, 202667 sampled answers · window 2026-07-23 – 2026-08-20 · rules v4-7

#1Docusaurus94%
#2MkDocs76.1%
#3Material56.7%
#4Git53.7%
#5Python41.8%
#6Redoc40.3%
#7BookStack37.3%
#8Sphinx35.8%
#9Wiki.js34.3%
#10Hugo32.8%

Aug 19, 202639 sampled answers · window 2026-07-22 – 2026-08-19 · rules v4-5

#1Docusaurus94.9%
#2MkDocs71.8%
#3Material51.3%
#4Git51.3%
#5Redoc41%
#6BookStack38.5%
#7Hugo38.5%
#8Wiki.js35.9%
#9Docmost30.8%
#10Python28.2%

Aug 18, 202660 sampled answers · window 2026-07-21 – 2026-08-18 · rules v4-5

#1Docusaurus96.7%
#2MkDocs78.3%
#3Material55%
#4Git53.3%
#5BookStack45%
#6Redoc43.3%
#7Wiki.js38.3%
#8Hugo31.7%
#9Docmost31.7%
#10Docsify28.3%

Aug 17, 202660 sampled answers · window 2026-07-20 – 2026-08-17 · rules v4-5

#1Docusaurus96.7%
#2MkDocs78.3%
#3Material55%
#4Git53.3%
#5BookStack45%
#6Redoc43.3%
#7Wiki.js38.3%
#8Hugo31.7%
#9Docmost31.7%
#10Docsify28.3%

Aug 16, 202660 sampled answers · window 2026-07-19 – 2026-08-16 · rules v4-5

#1Docusaurus96.7%
#2MkDocs78.3%
#3Material55%
#4Git53.3%
#5BookStack45%
#6Redoc43.3%
#7Wiki.js38.3%
#8Hugo31.7%
#9Docmost31.7%
#10Docsify28.3%

Aug 15, 202660 sampled answers · window 2026-07-18 – 2026-08-15 · rules v4-5

#1Docusaurus96.7%
#2MkDocs78.3%
#3Material55%
#4Git53.3%
#5BookStack45%
#6Redoc43.3%
#7Wiki.js38.3%
#8Hugo31.7%
#9Docmost31.7%
#10Docsify28.3%

Aug 14, 202660 sampled answers · window 2026-07-17 – 2026-08-14 · rules v4-5

#1Docusaurus96.7%
#2MkDocs78.3%
#3Material55%
#4Git53.3%
#5BookStack45%
#6Redoc43.3%
#7Wiki.js38.3%
#8Hugo31.7%
#9Docmost31.7%
#10Docsify28.3%

Read any date directly

Every archived date is machine-readable at /api/index/open-source-documentation-tools/as-of/<YYYY-MM-DD>, which returns the ranking as it stood, with the extraction version and revision it was published under. Dates before the record begins return no_record rather than a recomputation — we do not reconstruct history on demand and present it as what we said. See what the engines actually said.

[ORBATOR]