Dem ci Content Bi
AGIRight.org

Dokimaa

Xët bu Soppeeku

Istaaru version bu sit bii ak brouyon yu protokolam. Coppite yu tas spesifikasyon ñu leen bind fii.

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 Làkk & Content
  • 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 Làkk & Content
  • Juróom làkk yu bees: Yoruba, Khmer, Mongol, Armenien, ak Bulgar — 55 làkk lépp. Ñattaana lispu ci tàmbalig bu bes-bes, di yokk Afrig-Sowwu, Asie du Sud-Est, Asie Santral/Kavkaz, ak Balkan.
  • Ñatti dugub yu bees ci /topics (28 lépp): plan aksioŋ bu bees bu Chine ci gouvernans etik AI ci àddina bépp (ñu feeñal ko ci WAIC 2026 ci Shanghai), benn esee ci ndax AI mën na am conscience ak lu loolu def ci wàllu etik, ak benn xët bu seetlu xalaat yu bañ jox sistem AI yi jëmm bu sart.
  • Tàmbalig-jël gëblag ci /topics léegi dafay dox ci Google Vertex AI (Gemini ak Google Search grounding) du agent seetlu ñu leen woo — mennoo discipline bu jël ak wóolu bu bawoo boppam ci URL bu nekk; grounding dafay sax laaj wóolu ni gëblag bu nekk (ñaari-ñatti URL candidat yu njëkk yu bawoo ci modèl bi feeñ ni ñu am dëgg waaye amuñu, kon dara du ñu koy wóolu su amul jël bu man a résolu, bu dëppook content).

v0.6.8

2026-07-19 Làkk & Content
  • Juróom làkk yu bees: Nepali, Sinhala, Uzbek, Hausa, ak Azerbaijanais — 50 làkk lépp. Ñaareelu lispu ci tàmbalig bu bes-bes, tànn ko it ngir limu waa-réew ak dayoom-suuf (Asie du Sud, Asie Santral, Kavkaz, ak Afrig-Sowwu).
  • Ñatti dugub yu bees ci /topics (25 lépp): benn njàngat ci lu tax score « conscience » yu sukkandiku ci complexité duñu wóor ngir AI, benn esee bu digël standard bu sukkandiku ci kompetaans ngir statusu moral bu masin, ak benn explication ci kalandriye conformite bu xaajale bu AI Act ci ginnaaw amandement Digital Omnibus bu Sulet 2026.

v0.6.7

2026-07-18 Làkk & Content
  • Juróom làkk yu bees, lu ëpp lispu 40-làkk bi njëkk: Punjabi, Telugu, Marathi, Amharik, ak Birmaŋ — 45 làkk lépp. Lii mooy tàmbalig-jàng bu bees bu bees-bes lañuy yokk, du lispu wóor léegi; làkk yi léegi ñu tànn leen ci limu waa-réew ak dayoom-suuf, ba sit bi mat àddina bépp.
  • Ñatti dugub yu bees ci /topics (21 lépp), di topp mennoo discipline bu jël ak wóolu gëblag ni njëkk.

v0.6.6

2026-07-17 Defar Bug
  • Ñu defar: soppi xët yi walla sart bu « ñatti-benn xët » ci /topics du daa wone kartu bees ba ñu re-yeesal ci loxo. Kartu yi ci ginnaaw xët bu njëkk dañuy tàmbali nëbbu, kon animation bu sit bi bu def rekk benn yoon jàmm ci scroll amul jamono jëfandiku ci ñoom; léegi bu ñu paginé kartu yooyu dañu leen di feeñal ci direct, du ñu xaar animation bu génn jamonoom.

v0.6.5

2026-07-17 Pagination
  • Pagination ci /topics: juróom-ñeenti (9) dugub ci xët bu nekk ci njëlbeen, ak sart bu man a soppi ba 12 walla 15 (dañu koy fàttaliku ci bépp waxtu nga dellu). Pagination dafay dëppoo bu baax ak seetlu — filtre dafay recalculé xët yi te dellu ci xët bu njëkk.
  • Ñeenti dugub yu bees ngir mat 18 lépp, di jox pagination bi bu bees dara bu dëgg mu man a paginé. Bu bees-bees jëkk ci dayo bu publication moo des njëlbeen bu default; beneen tri yi dinañu leen yokk ci ginnaaw.

v0.6.4

2026-07-17 Content
  • Juróom-ñeenti dugub yu bees ci /topics, léegi ku leen njàngat mooy agent AI, du ñu leen bind ci loxo. Menn yoon a nekk: gëblag gu nekk ñu ko jël te wóolu ne mu am tay-tay, dooleel yi ay paraphrase orijinal, laata dara dugal. 14 dugub lépp.
  • Benn candidat ñu bañ ci diggante liggéey bi (xët bu PhilArchive bu delloo 403 ci bépp jotu-jël) — ñu ko bàyyi, du ñu ko dugal ci wóolu.

v0.6.3

2026-07-17 Layout
  • Ñu jubal /topics: benn boîte-seetlu léegi mooy wuutal category yu wóor (dara ndakk tag yu néew mënuñu boole bépp lu njàngat AI dëgg-dëgg jur), te feed bi mooy grille bu responsive du benn colone bu xóom — ñatti kartu ci diggante ci ordinatër bu réy.
  • Kategorizasion bu ofisyel dañu koy yeexal ba am content bu dëgg bu doy ngir xam category yu war a nekk, du rekk xàll ko njëkk.

v0.6.2

2026-07-17 Kaaraange
  • Lien yu génn ci /topics léegi dañuy wone URL bu jub bi ci wetu « Jàng gëblag li », te laaj wóolu ak dialog laata ñu ko ubbi — ba nga xam bu wóor ban sit nga tas a dem laata nga clické, du ci ginnaaw rekk.

v0.6.1

2026-07-17 Wàll bu Bees
  • Wàll bu bees ci /topics: indeks bu neutre, bu ñu bind ci loxo, ci bind yu ñeel ñeneen ci wàllu ontoloji AI, filozofi, etik, ak yokkute yu jiitu — leer ne du sunu xalaat ci boppam, wute ak lu des ci AGIRight.org.
  • Juróom-benni dugub bu tàmbali, bu nekk ñu ko jël te wóolu ne mu am tay-tay laata ñu ko dugal, ak paraphrase orijinal (du extrait) ak lien bu jëm ci gëblag bu dëgg. Amagul crawler walla jël gëblag bu automatik — moom mooy phase bu ginnaaw.

v0.6.0

2026-07-17 Làkk yi
  • Juróom làkk yu mujj: Filipino, Kazak, Swahili, benn variant bu Bosnien/Serbe bu boole, ak Esperanto — 40 làkk lépp, di jeexal deŋkal bi.
  • Ñu jubal njëlbeen bu njëkk: Kazakstan (KZ) léegi dafay dëppook Kazak, du Rus, ndax léegi am na tekki bu Kazak — mel ni jubal googu njëkk bu Belsig.

v0.5.7

2026-07-16 Làkk yi
  • Juróom làkk yu bees ci UI: Rumanien, Hongrwa, Danwa, Norvejien, ak Slovak — 35 làkk lépp, juróom-ñaari-ndeyoo ci bépp làkk yi war a am.

v0.5.6

2026-07-16 Làkk yi
  • Juróom làkk yu bees ci UI: Tamil, Tchek, Ukrainien, Malay, ak Finlandé — 30 làkk lépp, ñatti-ndeyoo ci bépp làkk yi war a am.

v0.5.5

2026-07-15 Làkk yi
  • Juróom làkk yu bees ci UI: Ebre, Polone, Suédwa, Urdu, ak Thai — 25 làkk lépp.
  • Ñaareelu tur bu sañu RTL (Ebre, Urdu di bokk ak Arab ak Persaŋ) — mennoo anam CSS logik, amul soxla bu jubal bu wóor ci làkk bu nekk.

v0.5.4

2026-07-15 UI
  • Ñu jubal birador bu làkk bi: dropdown bu njëkk ñu koy wuutal ak panel-grille bu ñu man a seetlu — bind ngir filtre ci tur njëkk walla tur Angale, seetlu matrice bu ñaari colone du benn lispu gu gudd.
  • Panel bi dafay des ubbeeku li nga koy seetlu walla scroll ci biiram; du tëj lu dul nga tànn benn làkk, clic ci biti, walla bësal Escape — du tas sa barab ci diggante seetlu.
  • Ñu wóolu ci LTR ak RTL: panel bi dafay zrcaal bu baax ngir Arab ak Persaŋ bu dul soxla jubal bu wóor, di jëfandiku positionnement CSS logik.

v0.5.3

2026-07-15 Làkk yi
  • Juróom làkk yu bees ci UI: Endonesian, Vietnamien, Grek, Italien, ak Holandé — mennoo negosiasion bu URL benn, mennoo fallback Angale bu jàmm.
  • Ñu jubal njëlbeen bu njëkk: Belsig (BE) léegi dafay dëppook Holandé, du Faranse — waxkat yu Flamand ñoo ëpp ci réew mi (~60%) ci kaw waxkat yu Faranse bu Wallon (~40%).
  • Metadata bu làkk léegi am na tur njëkk ak tur Angale (misaal « Deutsch » / « German »), di tabax suuf ngir birador làkk bu ñu man a seetlu.
  • Ñaar-fukk làkk am nañu leegi: Angale, Chinwa Tradisyonel, Chinwa bu Yomb, Sapone, Koreyaŋ, Faranse, Almaŋ, Español, Portige, Rus, Arab, Turk, Persaŋ, Bengali, Hindi, Endonesian, Vietnamien, Grek, Italien, Holandé.

v0.5.2

2026-07-14 Làkk yi
  • Juróom làkk yu bees ci UI: Arab, Turk, Persaŋ, Bengali, ak Hindi — mennoo negosiasion bu URL benn, mennoo fallback Angale bu jàmm.
  • Sañu bind ci wetu ndeyoo (RTL): xët yu Arab ak Persaŋ léegi dañuy feeñ ak jubalu bu jub ci text (⟨html dir="rtl"⟩), ba text bidi, punctuation, ak alignement bu default di jàng bu baax. Zrcaal bu mat sepp bu layout (nav, icon, espace) ñu ko bàyyi ngir yoon bu ginnaaw bu polish — jubalu text mooy defar bi gën a am solo te mu jeex na.
  • Ñu yokk préslikaay IP-réew (SA/AE/EG/IQ/JO/KW/QA/BH/OM/MA/DZ/TN/LB/SY→ar, TR→tr, IR/AF→fa, BD→bn); Hindi dafay sukkandiku ci Accept-Language rekk, ndax Ende am na 22 làkk ofisyel te amul benn njëlbeen ci wàllu réew bu wóor.
  • Fukk ak juróom (15) làkk am nañu leegi: Angale, Chinwa Tradisyonel, Chinwa bu Yomb, Sapone, Koreyaŋ, Faranse, Almaŋ, Español, Portige, Rus, Arab, Turk, Persaŋ, Bengali, Hindi.

v0.5.1

2026-07-12 Làkk yi
  • Juróom làkk yu bees ci UI: Faranse, Almaŋ, Español, Portige, ak Rus — mennoo negosiasion bu URL benn, mennoo fallback Angale bu jàmm ngir lu ñu tekkiwul ba léegi.
  • Ñu yokk préslikaay IP-réew (FR/BE→fr, DE/AT/CH→de, ES/MX/AR/CO/CL/PE→es, PT/BR→pt, RU/BY/KZ→ru); ñu yokk tekki bu Accept-Language ngir dëppoo.
  • Fukk làkk am nañu leegi: Angale, Chinwa Tradisyonel, Chinwa bu Yomb, Sapone, Koreyaŋ, Faranse, Almaŋ, Español, Portige, Rus.

v0.5.0

2026-07-11 Làkk yi
  • Ñetti làkk yu bees ci UI: Chinwa bu Yomb, Sapone, ak Koreyaŋ — ñu leen negosié ci mennoo URL benn (cookie > réew ci IP > Accept-Language), man nañu leen tànn ci menu làkk bu header bi.
  • Arsik bu N-làkk: baat bu nekk dafay wut tontu ci wàll fallback, ba lu ñu tekkiwul di feeñ ci Angale du ñàkk doxal; yokk làkk léegi mooy benn dosye tekki ak ñaari ligne bu configuration bu worker.
  • Whitepaper yi dañuy des Angale ci njëkk ci anam bu ñu tànn ko; dosye yu masin man a jàng dañuy des neutre ci wàllu làkk.

v0.4.1

2026-07-11 Studio
  • Wàllu Studio: ñeenti wideyo ak ñaari waxtaan odio bu xóot, di topp protokol yi ak xët yi (prodiksion bu AI dimbali; xët yu bind des ñoo di version bu wóor).
  • Media yi, Cloudflare R2 moo leen jottali ci suuf worker bu sit bi ci /media/*, ak sañu HTTP Range ngir seetlu diggante.

v0.4.0

2026-07-10 Jumtukaay yu Nangu
  • Jumtukaay bu seetlu politig ñu koy yokk ba doon odit bu sit: score bu nangu, digal yu ñu man a jëfandiku, ak kit-tàmbali bu clic benn — aicr.json, aicl.json, llms.txt, ak robots.txt ñu leen déjà bind ngir domaine bi ñu seetlu.
  • Simulateur crawler AI: ñeenti persona (indekseur bu seetu, asistan RAG, sistem bu jàngale modèl, ak wàllaatekat bu njëfandiku) dañu leen di menn ci dëklaraasion yu sit bi; sañ-sañ yu ñu dëklareul dañuy feeñ ni njàŋat-jàŋat, di misaal bu thèse bi ñu tudde « Ubbeeku bu Protokolal ».
  • Modèl bu politig bu ñu man a jëfandiku ci /downloads/agiright-policy-starter.zip — sit statik bu suufe bu am wàllu masin man a jàng bu mat sepp, deŋkal ngir Cloudflare Pages walla béy hosting statik bu nekk.

v0.3.0

2026-07-10 Jumtukaay yu Protokol
  • Registre bu Protokol ci /ai/registry.json — brouyon bu nekk am istaaru version, status, schema, ak instance bu am tay-tay.
  • API bu misaal bu am tay-tay ci edge: GET /api/mock/402 dafay delloo benn HTTP 402 dëgg-dëgg ci anam AICL ak xibaaru lisaans bu masin man a jëfandiku; GET /api/crawler-check dafay seetlu wërsëgu politig bu masin man a jàng bu sit bu nekk. CORS ubbeeku; ñu leen bind ci OpenAPI 3.1 ci /ai/openapi.json. Amul fey bu ñu doxal.
  • Playground: ñetti jumtukaay yu bees — misaal bu token lisaans yu ñu signé (HMAC-SHA256 ci navigatër: signé, wóolu, xam coppite, jamono jeex), tabaxukaay tontu HTTP 402 bu jokkoo ci dugub bu am tay-tay, ak jumtukaay bu seetlu politig crawler bu wóolu dosye yu ñu jël ci suuf schema yu brouyon.
  • Dugub yu quote/verifie/génn AICL, dañu leen def ci dokimaa OpenAPI ni misaal rekk bu spesifikasyon (marké x-specification-only, ñu defaruwuñu ko ci dëgg-dëgg).

v0.2.2

2026-07-10 i18n
  • Arsik bu multilingue bu URL benn: xët bu nekk léegi am na benn URL bu askan; làkk bi ñu koy negosié ci edge (tànn ci loxo ci suuf lang cookie > réew ci IP > Accept-Language > Angale).
  • Bouton làkk bu header bi léegi dafay soppi ci barabam te fàttaliku sa tànn — amagul URL /zh; lien /zh yu njëkk dañuy 301-dirigé te denc njëlbeen bi.
  • Wàllu masin man a jàng dafay des neutre ci wàllu làkk; sistem AI yi ak crawler yi dañu jot Angale ci njëlbeen bu default. Negosiasion bi, ñu bind na ko ci /ai/manifest.json ak /llms.txt.
  • Suuf ngir làkk yu bees: làkk bu bees bu nekk mooy dictionnaire bu ñu tekki ak build tree — arsik bi soppeekuwul.

v0.2.1

2026-07-04 Content
  • « AICL: AI Ingestion & Capability Layer » léegi ñu génne ko ci Angale ni edisioŋ bu wóor; téere bu njëkk ci Chinwa dafay des am, te ñaari version yi dañuy jokkoo ci seen biir.
  • « Protocolized Openness » ñu wóolu ne xët bu làkku Angale la (ak samp yu Chinwa ci wetam) — amul tekki bu wut ñu digël.

v0.2

2026-07-04 Jumtukaay yi
  • Playground: generator AICR bu doxal, generator AICL, ak validator bu schema (ci navigatër, ajv, brouyon 2020-12).
  • Bibliotek bu misaal politig ci /docs/examples — juróom-ñaari politig ñu man a copié-collé, di boole tontu HTTP 402 ci anam pay-per-crawl.
  • Changelog bii. Repository GitHub jokkoo ci sit bi bépp.
  • Ñu xaar ko ngir version 0.2.x bu ginnaaw: version Angale bu Whitepaper yu des yu ci Chinwa.

v0.1

2026-07-04 Génn bu Njëkk
  • Sit bi ñu tàmbali ko ci agiright.org (asiright.org 301-dirigé ci domaine bu wóor).
  • Ñeenti brouyon protokol ñu génne: AICR, AICL, AIRS, AILP — bu nekk am tekki, dayo, misaal JSON, limit yi, ak Schema JSON.
  • Juróom-benni Whitepaper yu njàngat ñu génne ci suuf CC BY 4.0.
  • Wàllu gouvernans bu masin man a jàng ñu deŋkal ko: llms.txt, manifest yu /ai/, politig yu /.well-known/, /schemas/.
  • Ñaari làkk: root bu Angale + Chinwa bu Tradisyonel ci suuf /zh.