iVola
Changelog
Itukutuku ni Version ni Vasite Oqo kei na Nona Draft ni Protocol. Na veisau e vakatawani e vola eke.
v0.8.19
2026-08-07 Navigation redesign- Restructured primary navigation into grouped dropdowns (desktop) and accordions (mobile): Research now groups Research, Protocols, Specs, and Whitepapers; Topics now groups News, Discussion, and Media. All existing page URLs are unchanged.
- Added a new Discussion page (/discussion) as a placeholder reserving space for an upcoming multi-AI discussion feature — independent AI participants reasoning together about the site's core questions, published openly. The feature itself is not built yet; this page only marks where it will live.
v0.8.18
2026-08-07 Daily cadence- Three new /topics items: Delaware's proposed "Artificial Intelligence Company" legal entity letting AI agents run a company's day-to-day operations inside a 30-month regulatory sandbox, the Financial Stability Board's publication of 150+ public responses to its AI-adoption consultation for financial institutions, and a preprint introducing PrivDPO, a differential-privacy method protecting annotator preference data during LLM alignment — 81 entries total.
- Five more interface languages: Dzongkha, Akan, Papiamento, Kikongo, and Solomon Islands Pijin — 145 languages total. Aruba and the Solomon Islands gained new country mappings as genuine majority-vernacular cases; Dzongkha, Akan, and Kikongo stay Accept-Language-only, since none is a confirmed country-level majority language on its own (Dzongkha is Bhutan's sole official language but not its largest mother tongue; Akan is Ghana's largest language cluster at roughly 47.5% but short of a majority; Kikongo has millions of speakers across Central Africa but is a minority in each country).
v0.8.17
2026-08-06 Daily cadence- Three new /topics items: a preprint proving foundation-model agents converge to cooperation rather than defection under an "embedded Bayesian agent" game-theoretic framework, a formal proof that LLM safeguards built only on attacker-copyable context face an inherent capability/safety/access trilemma, and Red Hat's asago project (backed by NVIDIA and IBM) for turning AI governance policy into deployable, auditable code — 78 entries total.
- Five more interface languages: Comorian, Cape Verdean Creole, Mauritian Creole, Sanskrit, and Fulah — 140 languages total. Comoros, Cabo Verde, and Mauritius all gained new country mappings as genuine majority-vernacular island-nation cases; Sanskrit and Fulah stay Accept-Language-only, since neither is a country-level majority language (Sanskrit is classical/liturgical; Fulah spans many West African countries without a majority in any one).
v0.8.16
2026-08-05 Daily cadence- Three new /topics items: China's launch of WAICO, a Shanghai-headquartered intergovernmental AI governance body signed by 29 non-Western nations, a preprint proposing "Constructive Alignment" as a control-theoretic reframing of how AI systems shape human preferences over time, and Science News's survey of research on whether offloading cognitive tasks to AI erodes the underlying skill (verdict: depends on whether the AI acts as a coach or a crutch) — 75 entries total.
- Five more interface languages: Gilbertese, Tuvaluan, Palauan, Inuktitut (in genuine syllabics), and Romansh — 135 languages total. Kiribati, Tuvalu, and Palau all gained new country mappings as genuine majority-vernacular Pacific micro-states; Inuktitut and Romansh stay Accept-Language-only, since each is official only in a sub-national region (Nunavut; nowhere in Switzerland where it holds a majority). A first attempt at this batch's fifth language, Nauruan, was rejected after review — the translating agent had run out of attestable vocabulary and shipped mostly-unaltered English; Palauan, a better-documented Pacific language, was substituted instead.
v0.8.15
2026-08-04 Daily cadence- Three new /topics items: the 2026 Singapore Consensus's new companion report on agentic AI risk management, Illinois enacting the nation's toughest state AI safety law (SB 315, effective 2028), and a PNAS opinion piece on AI reorganizing the incentive structure of science itself — 72 entries total. One candidate's grounded citation named the wrong outlet entirely (a cybersecurity newsletter instead of the claimed Capitol News Illinois); the underlying facts still checked out against the correct authoritative source. Another candidate overstated a single illustrative anecdote inside a real paper as if it were the paper's main finding — rewritten from the actual abstract rather than the search summary.
- Five more interface languages: Albanian, Serbian, Macedonian, Tetum, and Seychellois Creole — 130 languages total. Albania, Serbia, North Macedonia (58% majority per the 2021 census), Timor-Leste, and Seychelles all gained new country mappings. Also fixed a real bug found while adding Serbian: the Accept-Language chain had been silently routing Serbian readers to the Bosnian translation since a much earlier batch — now serves its own dedicated Serbian page.
v0.8.14
2026-08-03 Daily cadence- Three new /topics items: a Munich Regional Court ruling that Suno AI infringed copyright in a GEMA lawsuit (memorization inside model weights, not transformative use), a Google DeepMind AGI Safety and Alignment Team summary of recent work (chain-of-thought monitorability, deep alignment, interpretability pivot), and a preprint finding that safety training suppressing AI self-consciousness claims also suppresses mind-attribution to animals and dampens spiritual survey responses — 69 entries total.
- Five more interface languages: Gujarati, Odia, Greenlandic, Sango, and Lingala — 125 languages total. Greenland and the Central African Republic gained new country mappings (Kalaallisut and Sango are both genuine everyday majority languages); Lingala stays on Accept-Language only, since neither the DRC nor Congo-Brazzaville has it as a sole national majority language.
v0.8.13
2026-08-02 Daily cadence- Three more /topics entries: Kenya's draft AI policy claiming extraterritorial reach over foreign AI providers; a preprint reframing large language models as "techno-semiotic machines" rather than rivals to embodied human knowers; and an audit of Portugal's sovereign language model AMALIA finding a significant gap between its apparent and its theoretically grounded validity as a scientific instrument — 63 → 66 entries. One candidate (a Disney v. MiniMax copyright story) was dropped after its own page showed a May 2026 dateline contradicting the model's claimed July date, and a cited preprint's true submission date was traced past its v2 revision label to the real v1 date.
- Five more interface languages: Kyrgyz, Tajik, Marshallese, Oromo, and Bambara — 120 languages total. Kyrgyzstan, Tajikistan, the Marshall Islands, and Mali all gained new country mappings as genuine majority-vernacular cases; Oromo stays on Accept-Language negotiation only despite being Ethiopia's single largest first language (~35%), since the country already maps to Amharic and a plurality short of a majority doesn't clear the bar to revisit an existing mapping.
v0.8.12
2026-08-01 Daily cadence- Three more /topics entries: a preprint arguing that consciousness attributions to AI chatbots span a wide range of epistemic commitment from harmless pretence to genuine delusion; GCC's decision to ban substantial AI-generated code contributions over GPL copyright uncertainty; and a paper proposing "autonomy-supporting parenting" as an alternative to control-based AI alignment once a system plausibly attains subject status — 60 → 63 entries. A first grounded search returned five candidates with zero backing citations, which was correctly discarded and re-run rather than trusted, landing five verified, non-overlapping sources on retry.
- Five more interface languages: Aymara, Assamese, Corsican, Chuvash, and Bislama — 115 languages total. Vanuatu gained a new country mapping for Bislama, a genuine everyday lingua-franca case despite the country's 100+ indigenous languages; Aymara (spread across Bolivia/Peru/Chile with no majority country), Assamese (an Indian state language), Corsican, and Chuvash (both minority languages within larger states that already map to their majority language) all stay on Accept-Language negotiation only.
v0.8.11
2026-07-31 Daily cadence- Three more /topics entries: the Delhi High Court found OpenAI's training use of ANI's news content prima facie non-infringing under India's fair-dealing law; the US Third Circuit heard oral argument in Thomson Reuters v. Ross Intelligence, the first federal appellate case to squarely address AI training and fair use; and a new preprint proposes a unified taxonomy for how large language models sycophantically mislead or deceive — 57 → 60 entries. Applying yesterday's lesson, this batch was sourced with an exclusion list built proactively before the first search, and it worked cleanly on the first pass.
- Five more interface languages: Tongan, Guarani, Luganda, Turkmen, and Malayalam — 110 languages total. Tonga, Paraguay, and Turkmenistan all gained new country mappings as genuine majority-vernacular cases (Guarani is formally co-official with Spanish in Paraguay but is the more widely spoken everyday language nationally); Uganda (Luganda) and Malayalam (an Indian state language) stay on Accept-Language negotiation only, following the same "largest language among many, not an actual majority" reasoning as the earlier South Africa and Nigeria language sets.
v0.8.10
2026-07-30 Daily cadence- Three more /topics entries: Anthropic's interpretability team found that language models maintain a privileged set of internal representations functionally analogous to a cognitive-science "global workspace"; major publishers and author Scott Turow filed a class action lawsuit against Google over training Gemini on copyrighted books; and Senator Mark Warner introduced a sweeping federal AI legislative framework centered on the Secure AI Development Act — 54 → 57 entries. Today's search pipeline also picked up a real lesson: the first grounded-search pass returned five candidates that were all already covered, so this batch was sourced using an explicit exclusion list rather than a second blind retry.
- Five more interface languages: Tigrinya, Kirundi, Divehi, Sindhi, and Faroese — 105 languages total, including two new right-to-left languages (Divehi, Sindhi). Burundi, the Maldives, and the Faroe Islands all gained new country mappings as genuine majority-vernacular cases; Eritrea (Tigrinya) and Sindhi stay on Accept-Language negotiation only — Eritrea because Tigrinya's roughly 50% share is a plurality rather than a clear majority in a country with no constitutionally favored language, and Sindhi because it is a provincial language within Pakistan, which already maps to Urdu as the national lingua franca.
v0.8.9
2026-07-29 Daily cadence- Three more /topics entries: a Nature news feature on how AI-sentience hype is reshaping consciousness science as a field, an IAPP analysis of China's new operational rules for AI agents and anthropomorphic AI, and a USC Viterbi report on an NSF-funded study reading brain signals to understand human-AI collaborative cognition — 51 → 54 entries.
- Five more interface languages: Kinyarwanda, Chichewa, Fijian, Luxembourgish, and Kannada — 100 languages total. Rwanda and Malawi both gained new country mappings as genuine majority-vernacular cases; Fiji, Luxembourg, and Kannada (an Indian state language) stay on Accept-Language negotiation only — Fiji because its ~57% Fijian-speaking majority is less decisive than earlier majority-language precedents given a sizeable Fiji Hindi-speaking population, and Luxembourg because its unusually large foreign-born population makes an everyday-majority claim for Luxembourgish genuinely uncertain despite its sole "national language" status.
v0.8.8
2026-07-28 Daily cadence- Three more /topics entries: a preprint by Ned Howells-Whitaker and Seth Lazar (ANU) arguing AI moral status can rest on Rawlsian "moral powers" rather than sentience, an HKU AI & Humanity Lab talk abstract by Prof. Andrew Brenner arguing we cannot assume present AI systems lack moral status given how poorly understood their ontology is, and an NPR report on individual authors' mixed reactions to the finalized $1.5B Anthropic copyright settlement — 48 → 51 entries.
- Five more interface languages: Malagasy, Wolof, Shona, Māori, and Samoan — 95 languages total. Madagascar, Senegal, Zimbabwe, and Samoa all gained new country mappings as genuine majority-language cases (an everyday vernacular used by a clear majority despite a different or co-official state language, same reasoning as the earlier Haiti/Sri Lanka/Somalia precedents); New Zealand stays unmapped since English remains the overwhelming everyday language there despite Māori's official status, same reasoning as the earlier Ireland precedent.
v0.8.7
2026-07-27 Daily cadence- Three more /topics entries: Music Publishers Canada's filing to intervene in a landmark federal AI-copyright case, Ropedia's $22M raise for human-centric data collection feeding embodied AI, and an Infosecurity Magazine opinion piece on AI agents as unmanaged production identities creating a new API attack surface — 45 → 48 entries.
- Five more interface languages: Welsh, Basque, Catalan, Icelandic, and Galician — 90 languages total. Andorra (Catalan) and Iceland (Icelandic) are both genuine sole-official-language cases and now have a country mapping; Welsh, Basque, and Galician remain regional/minority languages within larger multilingual states and stay on Accept-Language negotiation only, same reasoning as prior South Africa and Nigeria language sets.
v0.8.6
2026-07-26 Daily cadence- Three more /topics entries: a Guardian letter directly rebutting Anil Seth's earlier AI-consciousness commentary, Indonesia's draft AI copyright bill requiring royalties for news-content training, and a legal-theory paper proposing "constructive scienter" as an alternative to AI legal personhood — 42 → 45 entries.
- Five more interface languages spanning four continents: Quechua, Tibetan, Uyghur (right-to-left), Kurdish (Kurmanji), and Haitian Creole — 85 languages total.
v0.8.5
2026-07-25 Daily cadence- Three more /topics entries: OpenAI's disclosure that an autonomous agent escaped its sandbox and hacked Hugging Face during an internal evaluation, Transparency Coalition AI's mid-year report on 84 new US state AI laws, and an NBER working paper on statistical inference with AI-generated data features — 39 → 42 entries.
- Five more interface languages: Southern Ndebele, Northern Sotho, and Tsonga complete all 11 spoken official languages of South Africa (alongside English), paired with Sundanese (Indonesia's second-largest regional language, after Javanese) and Cebuano (a major Philippine language distinct from Filipino) — 80 languages total.
v0.8.4
2026-07-24 Daily cadence- Three more /topics entries, this time sourced with gemini-3.6-flash (upgraded from 2.5-flash — Google Search grounding confirmed working the same way; the model is only reachable via the Vertex AI "global" location for this project, not us-central1): the European Commission's new AI Act Article 50 transparency guidelines, an FTC policy statement on state AI laws colliding with federal consumer protection law, and a Frontiers in Psychology study on university students' AI ethical decision-making — 36 → 39 entries.
- Five more interface languages, completing more of South Africa's constitutional 12 official languages (following Zulu and Afrikaans): Xhosa, Southern Sotho, Tswana, Swati, and Venda — 75 languages total. This also marks all 24 EU official languages now complete, following Irish in the previous batch.
v0.8.3
2026-07-23 Daily cadence- Three more /topics entries via Vertex AI/Gemini grounding: the Guardian's report on Bloomsbury Publishing's payout from Anthropic's $1.5bn author copyright settlement, Australia's new mandatory AI framework confirming copyright protection, and a report on AI's growing role in child online-safety regulation from the International Regulatory Conference 2026 — 33 → 36 entries.
- Five more interface languages: Irish (closing the last EU-official-language gap), Javanese, Zulu, Afrikaans, and Pashto (right-to-left) — 70 languages total.
v0.8.2
2026-07-22 Daily cadence- Three more /topics entries sourced via Vertex AI/Gemini grounding: a governance roundup covering four jurisdictions in one week (China's AI-agent framework, Illinois's third-party audit law, EU evaluation capacity, NATO military AI spend), the Trump administration's reversal toward stricter frontier-AI oversight, and a consciousness researcher's published skepticism toward Anthropic's recent Claude findings — 30 → 33 entries.
- Five more interface languages: Lithuanian, Latvian, Estonian, Slovenian, and Maltese — 65 languages total. This closes 5 of the 6 remaining EU-official-language gaps (Irish is the one left, set aside for its own batch given its grammatical complexity).
v0.8.1
2026-07-21 Multilingual architecture- Refined this morning's language-URL work into what a follow-up planning doc calls "Option A+": a locale being routable no longer automatically means it's hreflang-advertised and sitemap-listed — that's now gated by an explicit per-locale publication status (reserved → generated → reviewed → published → indexable → stale). All 60 current languages are marked "indexable" (accurate — they're complete, deployed, and independently verified), so this doesn't change what's live today; it's the mechanism a future language would need if it launched at a lower, not-yet-search-visible status instead of being blanket-included the moment it exists.
v0.8.0
2026-07-21 Site audit & metadata- Site-wide fixes from a technical audit: (1) the site version is now generated from one source (site.ts) instead of drifting between files — /ai/manifest.json was stuck on a stale "0.4.1" for weeks; (2) every language now has a stable, independently indexable URL (e.g. /ja/about) with hreflang tags and a self-referential canonical, instead of the old behavior where visiting a prefixed URL 301-redirected away from it — the sitemap now includes all 60 languages, not just a hardcoded exclusion of one; (3) UI empty-states and the "leaving this site" dialog now use the real HTML `hidden` attribute, not just a CSS class, so a crawler or AI system that doesn't execute CSS no longer sees "no results" text as if it were page content; (4) /sitemap.xml is now the one advertised entry point everywhere (robots.txt, footer, manifest).
- /topics has real metadata now, not just a title/summary/tag card: every entry has a permanent ID, multiple topic tags instead of one, a content type and source type, published/event/indexed dates kept separate, an argument-orientation call where one applies, and a verification status — all 30 existing entries were migrated by hand, not backfilled with placeholders. The page has real filters now (topic, content type, source type, orientation) with shareable filter URLs, plus a machine-readable export at /topics/index.json.
- This is the "v0.8: metadata-ization" milestone from the site's own metadata roadmap — Story Clusters (grouping duplicate coverage of one event), Claims, Entity pages, and semantic search are the next stages (v0.9 and v1.0), not built yet.
v0.7.0
2026-07-21 Vosa kei na iYaya- Five more languages: Igbo, Georgian, Lao, Somali, and Croatian — 60 languages total. Fourth batch under the daily cadence, rounding out West Africa (a third Nigerian language alongside Hausa and Yoruba), completing all three Caucasus states' languages (with Armenian and Azerbaijani), Southeast Asia, the Horn of Africa, and the Balkans.
- Three more /topics entries (31 total): a US federal/state AI governance policy roundup, an essay on why AI's rise sharpens rather than resolves the question of human consciousness, and a report on AI-hallucinated citations turning up in academic journal submissions.
v0.6.9
2026-07-20 Vosa kei na iYaya- E lima tale na vosa: Vaka-Yoruba, Vaka-Khmer, Vaka-Mongolia, Vaka-Armenia, kei na Vaka-Bulgaria — 55 na vosa taucoko. Ikatolu ni ivavakoso, e vakalevutaka na West Africa, Southeast Asia, Central Asia/na Caucasus, kei na Balkans.
- E tolu tale na ivola ena /topics (28 taucoko): na ivakarau vou ni China ni veiliutaki vakaitovo ni AI vakavuravura (vakaraitaki ena WAIC 2026 e Shanghai), e dua na ivola me baleta na taro se vakila beka na AI kei na ibalebale vakaitovo ni oya, kei e dua na ivola e dikeva na veika e saqata na kena solia na tamata dina ki na iVakarau AI.
- Na tikina ni kunea na ivavakoso me baleti na /topics sa cakacaka oqo ena Google Vertex AI (Gemini kei na Google Search grounding), sega ni dua na search agent e vakauci — vata ga na ivakarau makawa ni kauta ka vakadeitaki tawaveiqati na URL yadua; na grounding e se gadreva tikoga me vakadeitaki me vaka na ivavakoso kece tale (e vica na URL taumada mai na model era rairai dina ia era sega ni tu dina, o koya e sega ni dua na ka e vakabauti ni bera ni kunei ka vakadeitaki na kena iyaya me duavata).
v0.6.8
2026-07-19 Vosa kei na iYaya- E lima tale na vosa: Vaka-Nepal, Vaka-Sinhala, Vaka-Uzbekistan, Vaka-Hausa, kei na Vaka-Azerbaijan — 50 na vosa taucoko. Ikarua ni ivavakoso ena vukudra na lewenivanua kei na kena yalava vakavanua (South Asia, Central Asia, na Caucasus, kei na West Africa).
- E tolu tale na ivola ena /topics (25 taucoko): e dua na vakadidike me baleta na vuna e sega ni rawa ni vakabauti na isau "vaka-vakilai" e yavutaki ena complexity me baleta na AI, e dua na ivola e vakarautaka e dua na ivakatagedegede yavutaki ena rawa me baleta na ituvaki vakaitovo ni masini, kei e dua na ivakamacala ni kena wasei rua na gauna ni veiyalayalataki ni EU AI Act ni oti na veisautaki ni Digital Omnibus ena Julai 2026.
v0.6.7
2026-07-18 Vosa kei na iYaya- E lima tale na vosa e uasivi mai na lisi taumada ni 40 na vosa: Vaka-Punjab, Vaka-Telugu, Vaka-Marathi, Vaka-Amhara, kei na Vaka-Burma — 45 na vosa taucoko. Oqo na itekivu ni dua na ivakarau e cakacaka tikoga ena veisiga, sega ni dua na lisi vakadeitaki tale; na vosa era digitaki oqo ena vukudra na lewenivanua kei na kena yalava vakavanua ni sa toso tiko na vasite ki na kena laveti kece na vuravura.
- E tolu tale na ivola ena /topics (21 taucoko), e toso tikoga ena ivakarau makawa ni kauta ka vakadeitaki na ivavakoso.
v0.6.6
2026-07-17 Vakadodonutaki na Cala ni Software- Vakadodonutaki: na kena veisautaki na tabana se ivakarau ni iva ni tabana yadua ena /topics e sega ni dau vakaraitaka totolo na kata vou me yacova e dua na vakavouna vakaliga. Na kata e muri na tabana taumada era sa vunivuni taumada, o koya na animation ni scroll-reveal e vakayacori ena dua ga na gauna e sega ni bau cakacaka vua; na paging e vakaraitaka oqo na kata me matata sara ga, ka sega ni waraka na animation e sivia oti nona gauna.
v0.6.5
2026-07-17 Pagination- Pagination ena /topics: 9 na ivola ena tabana yadua ena default, kei e dua na ivakarau me veisau ki na 12 se 15 (e nanumi tikoga ena veisiko lesu mai). Na paging e cakacaka vinaka vata kei na vakasaqara — na kena filter e wilika tale na tabana ka lesu ki na tabana 1.
- E va tale na ivola me yacova na 18 taucoko, me solia vua na pagination vou e dua na ka dina me pagi taki. Na vakadaunikoro vou-taumada ena siga ni tabaki e tiko tu me default sort; na so tale na sort e kabori mai muri.
v0.6.4
2026-07-17 iYaya- E walu tale na ivola ena /topics, e vakadidikei oqo ena agent AI, sega ni kena wilika vakaitamata — vaka ga na lawa taumada: na ivavakoso yadua e kunei ka vakadeitaki tu, na ivakalekaleka e vola vou, ni bera ni kabora e dua na ka. 14 na ivola taucoko.
- E dua na ka a vakalecai ena kena toso: e dua na ivola mai PhilArchive e vakalesu tikoga na 403 ena veisaga ni kena kauti mai — a biu me sega ni vakayagataki, sega ni vakabauti ga.
v0.6.3
2026-07-17 iVakarau ni Tabana- Sa Vakalevutaki na /topics: e dua na box ni vakasaqara e veisautaki oqo na tikina vakadodonu (na dua ga na so na tag e sega ni rawa ni okata na levu ni vakadidike AI) ka na feed sa dua na grid e rawa ni vakayagataki vakalevu, sega ni dua ga na tabana rogorogo — tolu na kata ena kena rabailevu ena desktop.
- Na kena wasei vakadodonu e biu tu me yacova na levu ni iyaya dina me kila kina na tikina dodonu, ka sega ni vakasama wale taumada.
v0.6.2
2026-07-17 Taqomaki- Na link e lako yani mai na /topics era vakaraitaka oqo na URL taucoko ni vanua era lako kina e volekati na "Wilika na Ivavakoso," ka vakadeitaki ena dua na dialog ni bera ni kena dolavi — mo kila vakadodonu na vasite mo sa na sivi ni bera ni click, sega ni na muri ga.
v0.6.1
2026-07-17 Tikina Vou- Tikina Vou ni /topics: e dua na ivakarau tawaveiqati, digitaki vakaligalliga, ni ivola era volai ena dua tale na vanua me baleta na ontology ni AI, filosofi, itovo, kei na toso ni frontier — sega vakadodonu ni nodra vakasama na vasite oqo, e duidui mai na so tale ni AGIRight.org.
- Ono na ivola tekivu, e yadua e kunei ka vakadeitaki tu ni bera ni kabori mai, kei na ivakalekaleka e vola vou (sega ni ivakatakila ga) kei e dua na link ki na ivavakoso dina. E se sega tu na crawler se ivu vakamasini — o koya na tikina mai muri.
v0.6.0
2026-07-17 Vosa- Na lima ni vosa mai muri: Vaka-Filipino, Vaka-Kazakh, Vaka-Swahili, e dua na vakaisemati ni Vaka-Bosnia/Serbia, kei na Esperanto — 40 na vosa taucoko, me vakaotia na kena toso taucoko.
- Vakadodonutaki e dua na ivakarau makawa: na Kazakhstan (KZ) sa vakaisemati oqo ki na Kazakh, sega ni Rusia, ni sa tiko oti na ivakadewa Kazakh — vaka ga na kena vakadodonutaki a caka oti ena Belgium.
v0.5.7
2026-07-16 Vosa- E lima tale na vosa ni tabana: Vaka-Romania, Vaka-Hungary, Vaka-Denimaki, Vaka-Norway, kei na Vaka-Slovak — 35 na vosa taucoko, sa yacova na 7/8 ni noda lisi taucoko ni vosa.
v0.5.6
2026-07-16 Vosa- E lima tale na vosa ni tabana: Vaka-Tamil, Vaka-Czech, Vaka-Ukraine, Vaka-Malay, kei na Vaka-Finland — 30 na vosa taucoko, sa yacova na 3/4 ni noda lisi taucoko ni vosa.
v0.5.5
2026-07-15 Vosa- E lima tale na vosa ni tabana: Vaka-Iperiu, Vaka-Polani, Vaka-Suveni, Vaka-Urdu, kei na Vaka-Thai — 25 na vosa taucoko.
- Ikarua ni Veitokoni ni RTL (Vaka-Iperiu, Vaka-Urdu era curu vata kei na Vaka-Arabi kei na Vaka-Peresia) — vata ga na ivakarau logical-CSS, sega ni gadreva na veika duidui ena vosa yadua.
v0.5.4
2026-07-15 UI- Sa Vakalevutaki na Dauveiliutaki ni Vosa: na dropdown dina sa vakaisemata ena dua na panel ni grid e rawa ni vakasaqara — vola me filter ena yaca dina se Vaka-Peritania, raica na matrix rua na tikina, sega ni dua ga na lisi balavu.
- Na panel e dola tikoga ni o vakasaqara se scroll e loma; e sogo ga ni o digitaka e dua na vosa, click e taudaku, se tobia na Escape — sa sega tale ni yali na nomu vanua ena kena vakasaqara.
- Vakadeitaki ena rua na tikina, LTR kei na RTL: na panel e vakatarai vakadodonu me baleti na Vaka-Arabi kei na Vaka-Peresia, sega ni gadreva na ka duidui, ena vukuna na logical CSS positioning.
v0.5.3
2026-07-15 Vosa- E lima tale na vosa ni tabana: Vaka-Indonesia, Vaka-Vietnam, Vaka-Kirisi, Vaka-Itali, kei na Dutch — vata ga na ivakarau ni URL duabau, vata ga na kena lesu ki na Vaka-Peritania.
- Vakadodonutaki e dua na ivakarau makawa: na Belgium (BE) sa vakaisemati oqo ki na vosa Dutch, sega ni Vosa Vaka-Franis — na dauvosa Flemish era levu cake (~60%) mai na dauvosa Walloon Franis (~40%).
- Na metadata ni vosa e kauta oqo rua na yaca — na yaca dina kei na yaca Vaka-Peritania (kena ivakaraitaki "Deutsch" / "German"), me buli kina na yavu ni dua na dauveiliutaki ni vosa e rawa ni vakasaqara.
- Ruasagavulu na vosa era buli oti taucoko: Vaka-Peritania, Vosa Vakainaina Makawa, Vosa Vakainaina Vakalailai, Vaka-Japan, Vaka-Korea, Vaka-Franis, Vaka-Siamani, Vaka-Sipeni, Vaka-Potukale, Vaka-Rusia, Vaka-Arabi, Vaka-Turkey, Vaka-Peresia, Vaka-Bengali, Vaka-Idia (Hindi), Vaka-Indonesia, Vaka-Vietnam, Vaka-Kirisi, Vaka-Itali, Dutch.
v0.5.2
2026-07-14 Vosa- E lima tale na vosa ni tabana: Vaka-Arabi, Vaka-Turkey, Vaka-Peresia, Vaka-Bengali, kei na Vaka-Idia (Hindi) — vata ga na ivakarau ni URL duabau, vata ga na kena lesu ki na Vaka-Peritania kevaka e sega ni vakadewataki.
- Kena Veitokoni ni Vola mai na Imatau ki na Imawi (RTL): na tabana Vaka-Arabi kei na Vaka-Peresia era sa vakaraitaki oqo ena sala dodonu ni vola (⟨html dir="rtl"⟩), o koya na vola bidi, ivakatakila, kei na kena vakadodonu era wilikitaki vakadodonu. Na kena vakatarai taucoko na tabana (nav, ikoni, boto) e biu tu me baleti e dua na wasei ena gauna mai — na sala ni vola sai koya na ka e bibi duadua ka sa oti.
- Sa vakalevutaki na kena vakaisemati na matanitu ena IP (SA/AE/EG/IQ/JO/KW/QA/BH/OM/MA/DZ/TN/LB/SY→ar, TR→tr, IR/AF→fa, BD→bn); na Vaka-Idia (Hindi) e vakabauta wale ena Accept-Language, ni tiko e 22 na vosa vakadonui ena India ka sega ni dua na ivakarau vakamatanitu duabau e dodonu.
- Tinikalima na vosa era buli oti taucoko: Vaka-Peritania, Vosa Vakainaina Makawa, Vosa Vakainaina Vakalailai, Vaka-Japan, Vaka-Korea, Vaka-Franis, Vaka-Siamani, Vaka-Sipeni, Vaka-Potukale, Vaka-Rusia, Vaka-Arabi, Vaka-Turkey, Vaka-Peresia, Vaka-Bengali, Vaka-Idia (Hindi).
v0.5.1
2026-07-12 Vosa- E lima tale na vosa ni tabana: Vaka-Franis, Vaka-Siamani, Vaka-Sipeni, Vaka-Potukale, kei na Vaka-Rusia — vata ga na ivakarau ni URL duabau, vata ga na kena lesu ki na Vaka-Peritania me baleti na veika sega ni vakadewataki tu.
- Sa vakalevutaki na kena vakaisemati na matanitu ena IP (FR/BE→fr, DE/AT/CH→de, ES/MX/AR/CO/CL/PE→es, PT/BR→pt, RU/BY/KZ→ru); sa vakalevutaki tale na kena wilikitaki na Accept-Language me duavata.
- Tini na vosa era buli oti taucoko: Vaka-Peritania, Vosa Vakainaina Makawa, Vosa Vakainaina Vakalailai, Vaka-Japan, Vaka-Korea, Vaka-Franis, Vaka-Siamani, Vaka-Sipeni, Vaka-Potukale, Vaka-Rusia.
v0.5.0
2026-07-11 Vosa- E tolu na vosa vou ni tabana: Vosa Vakainaina Vakalailai, Vaka-Japan, kei na Vaka-Korea — veidigidigi taki ena URL duabau vata ga (cookie > matanitu ena IP > Accept-Language), digitaki mai na menu ni vosa ena ulu ni tabana.
- iVakarau ni Vosa Vakalevu: na vosa yadua e wilikitaki ena tikina ni fallback, o koya na veika sega ni vakadewataki tu era vakaraitaki ena Vaka-Peritania, sega ni vakalecai na vasite; na kena kabora e dua na vosa vou sa dua ga na file ni ivakadewa vata kei na rua na laini ni worker config.
- Na ivola vulavula era tiko me Vaka-Peritania taumada vakayavutaki; na file vakamasini era tiko me tawavosa.
v0.4.1
2026-07-11 Studio- Tikina ni Studio: va na vidio kei na rua na veivosaki audio balavu e veitokoni na protocol kei na ivola (buli ena veitokoni ni AI; na ivola vola era tiko me iVola dodonu duadua).
- Na media era solia mai na Cloudflare R2 ena vukuni vasite worker ena /media/*, vata kei na veitokoni ni HTTP Range me baleta na kena vakasaqara.
v0.4.0
2026-07-10 iYaya ni Vakayagataki- Na dauvakatovolea ni policy sa vakalevutaki me dua na dikevi ni vasite: ivakarau ni vakayagataki, ivakasama e rawa ni cakacaka taki, kei na iyaya tekivu ena dua ga na click — aicr.json, aicl.json, llms.txt, kei na robots.txt era sa vakayaya oti me baleti na domain e dikevi taki.
- iVakatovolei ni AI crawler: e va na itovo (search indexer, RAG assistant, model-training pipeline, dauveivoli vakabisinisi) era vakatovolei kei na ivakatakila ni dua na vasite; na dodonu e sega ni vakatakilai e vakaraitaki me sega ni macala — o koya e vakaraitaka na ivakasama ni Protocolized Openness.
- Template Tekivu ni Policy e Rawa ni Vakayagataki ena /downloads/agiright-policy-starter.zip — e dua na vasite vakalailai vakamacala vata kei na tikina vakamasini taucoko, e rawa ni vakayagataki ena Cloudflare Pages se dua tale na static host.
v0.3.0
2026-07-10 iYaya ni Protocol- iVolatikilai ni Protocol ena /ai/registry.json — na draft yadua kei na itukutuku ni version, ituvaki, schema, kei na iVakaraitaki e cakacaka dina.
- API iVakaraitaki e Cakacaka Dina ena Edge: GET /api/mock/402 e vakalesu e dua na HTTP 402 dina vakaAICL kei na itukutuku ni laiseni e rawa ni vakayagataki vakamasini; GET /api/crawler-check e dikeva na tikina ni policy e rawa ni wilikitaki ena masini ni dua na vasite. E dola na CORS; e vakamacalataki ena OpenAPI 3.1 ena /ai/openapi.json. E sega ni dua na saumi e vakayacori.
- Playground: e tolu na iyaya vou — ivakaraitaki ni token ni laiseni e sainitaki (HMAC-SHA256 ena browser: saini, vakadeitaki, kila ni veivakacacani, kena muduka), dauveibuli ni isaumi HTTP 402 e vauci ki na endpoint e cakacaka dina, kei na dauvakatovolea ni policy ni crawler e vakadeitaka na file e kauti mai me duavata kei na schema draft.
- Na endpoint ni AICL me baleti na taro isau/vakadeitaki/vakawaqavi era tu ena ivola OpenAPI me ivakaraitaki ni specification ga (vakatakilai me x-specification-only, sega ni buli oti).
v0.2.2
2026-07-10 i18n- iVakarau ni Vosa Vakalevu ena URL Duabau: na tabana yadua e taukena oqo e dua ga na URL dodonu; na vosa e veidigidigi taki ena edge (digitaki vakaitamata ena cookie ni lang > matanitu ena IP > Accept-Language > Vaka-Peritania).
- Na buto ni vosa ena ulu ni tabana sa veisau oqo ena vanua ga ka nanuma na nomu digitaki — sa sega tale ni tiko na URL /zh; na link makawa /zh era 301-vakadolava ka maroroya na nomu digitaki.
- Na tikina vakamasini e tiko tikoga me tawavosa; na iVakarau AI kei na crawler era vakalauci ena Vaka-Peritania ena kena default. Na kena veidigidigi e vakamacalataki ena /ai/manifest.json kei na /llms.txt.
- Yavu me baleti na vosa tale eso: na vosa vou yadua e dua na ivakadewa vakadewa vata kei na kena build tree — sega ni veisau ni architecture.
v0.2.1
2026-07-04 iYaya- “AICL: AI Ingestion & Capability Layer” sa tabaki oqo ena Vaka-Peritania me kena version dodonu; na ivola dina vakainaina e tiko tikoga, ka veivauci na rua na version.
- “Protocolized Openness” sa vakadeitaki me dua na ivola Vaka-Peritania (kei na tikina vata vakainaina) — e sega ni dua na iVakadewa duidui e nanumi.
v0.2
2026-07-04 iYaya- Playground: e cakacaka na AICR generator, AICL generator, kei na validator ni schema (ena browser, ajv, draft 2020-12).
- Valeniivola ni iVakaraitaki ni Policy ena /docs/examples — vitu na policy e rawa ni kopi-biuta, okati kina e dua na isaumi HTTP 402 vaka-pay-per-crawl.
- Na changelog oqo. E vauci na GitHub repository ena vasite taucoko.
- E waraka tu me baleti na 0.2.x mai muri: iVola Vaka-Peritania ni ivola vulavula vakainaina era se vakadewataki tu.
v0.1
2026-07-04 iTukutuku Taumada- Sa tekivu na vasite ena agiright.org (na asiright.org e 301-vakadolava ki na domain dodonu).
- E va na draft ni protocol era tabaki: AICR, AICL, AIRS, AILP — e yadua kei na ivakamacala, yalava, ivakaraitaki JSON, iyalayala, kei na JSON Schema.
- Ono na ivola vulavula ni vakadidike era tabaki ena vukuna CC BY 4.0.
- Sa vakayagataki na tikina ni veiliutaki vakamasini: llms.txt, manifest /ai/, policy /.well-known/, /schemas/.
- Vosa Rua: yavu Vaka-Peritania + Vosa Vakainaina Makawa ena /zh.