Akwụkwọ
Changelog
Akụkọ ụdịdị nke weebụ a na ndepụta protocol ya. A na-edekọ mgbanwe na-emebi nkọwa ebe a.
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 Asụsụ na Ọdịnaya- 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 Asụsụ na Ọdịnaya- Asụsụ ise ọzọ: Yoruba, Khmer, Mongolian, Armenian, na Bulgarian — asụsụ 55 dum. Ọkọ nke atọ n'okpuru ọgụgụ kwa ụbọchị, na-agbatịkwu na West Africa, Southeast Asia, Central Asia/the Caucasus, na the Balkans.
- Ihe ndenye atọ ọzọ na /topics (28 dum): atụmatụ ọhụrụ ọchịchị omume ziri ezi AI mba ụwa nke China (nke e kpughere na WAIC 2026 na Shanghai), edemede gbasara ma AI nwere ike inwe mmetụta onwe ya na ihe nke ahụ ga-apụta n'ebe omume ziri ezi dị, na akwụkwọ na-enyocha arụmụka megide inye sistemụ AI ibu mmadụ n'iwu.
- Nzọụkwụ inweta isi mmalite /topics ugbu a na-agabiga Google Vertex AI (Gemini nwere Google Search grounding) kama iji agent nchọ e zigara — otu usoro ahụ ahụ: nweta ma kwado onwe ha na ọ ka dị ndụ maka URL ọ bụla dịka mbụ; grounding ka chọrọ nyocha dịka isi mmalite ọ bụla ọzọ (ụfọdụ URL mbụ modeli ahụ chọpụtara pụtara ihe dị mma ma ọ dịghị adị n'ezie, n'ihi ya ọ dịghị ihe a tụkwasịrị obi n'enweghị nweta ya na-adaba n'ọdịnaya na mbụ).
v0.6.8
2026-07-19 Asụsụ na Ọdịnaya- Asụsụ ise ọzọ: Nepali, Sinhala, Uzbek, Hausa, na Azerbaijani — asụsụ 50 dum. Ọkọ nke abụọ n'okpuru ọgụgụ kwa ụbọchị, e hopụtakwara ha n'ihi ọnụ ọgụgụ ndị na-asụ ha na mbara ala (South Asia, Central Asia, the Caucasus, na West Africa).
- Ihe ndenye atọ ọzọ na /topics (25 dum): nchọpụta gbasara ihe mere "akara mmetụta onwe ya" dabere na mgbagwoju anya adịghị ntụkwasị obi maka AI, edemede na-atụpụta ọkọlọtọ dabere n'ikike maka ọnọdụ omume igwe, na nkọwa gbasara kalenda ndabere EU AI Act nke a kewara abụọ mgbe mgbanwe Digital Omnibus nke July 2026 gasịrị.
v0.6.7
2026-07-18 Asụsụ na Ọdịnaya- Asụsụ ise ọzọ karịa ndepụta mbụ nke asụsụ 40: Punjabi, Telugu, Marathi, Amharic, na Burmese — asụsụ 45 dum. Nke a bụ mmalite ọgụgụ kwa ụbọchị na-aga n'ihu, ọ bụghị ndepụta e kwadobere oge a; a na-ahọpụta asụsụ ugbu a dabere n'ọnụ ọgụgụ ndị na-asụ ya na mbara ala, ka weebụ a na-agbaso ka o kpuchie ụwa niile.
- Ihe ndenye atọ ọzọ na /topics (21 dum), na-agakwa n'ihu iji otu usoro nweta na nkwado ahụ dịka mbụ.
v0.6.6
2026-07-17 Idozi mperi- E doziri: ịgbanwe peeji ma ọ bụ ntọala kwa peeji na /topics anaghị egosipụta kaadị ọhụrụ ruo mgbe e mere refresh aka. Kaadị ndị dị karịa na peeji nke mbụ na-amalite na-ezoro ezo, n'ihi ya, egwuregwu scroll-reveal saịtị a na-eme otu ugboro anaghị enwe ohere ịrụ ọrụ na ha; ịgbanwe peeji ugbu a na-amanye ka kaadị ndị ahụ pụta ìhè ozugbo kama ichere egwuregwu nke agafeworola oge ya.
v0.6.5
2026-07-17 Ịgbanwe Peeji- Ịgbanwe peeji na /topics: ihe ndenye itoolu kwa peeji dịka izugbe, nwere ntọala ịgbanwe gaa 12 ma ọ bụ 15 (a na-echeta ya n'oge ọ bịaghachiri). Ịgbanwe peeji na-arụkọ ọrụ ọma na nchọ — ihe nzacha na-agụgharị peeji ma laghachi na peeji nke mbụ.
- Ihe ndenye anọ ọzọ iji ruo 18 dum, na-enye ịgbanwe peeji ọhụrụ ihe ezi mgbe ọ bụla ị na-agafe. Ihe ọhụrụ kachasị site n'ụbọchị e bipụtara ya ga-anọgide bụrụ nhazi izugbe; nhọrọ nhazi ndị ọzọ bụ ihe a ga-agbakwunye emesịa.
v0.6.4
2026-07-17 Ọdịnaya- Ihe ndenye asatọ ọzọ na /topics, oge a agent AI mere nchọpụta ya kama aka mmadụ dere ya — otu iwu ahụ dịka mbụ: a na-enweta isi mmalite ọ bụla ma kwado na ọ ka dị ndụ, nchịkọta bụ okwu original tupu e tinye ihe ọ bụla. Ihe ndenye 14 dum.
- Otu onye e jụrụ n'ụzọ ọ na-aga (akwụkwọ PhilArchive nke nyeghachiri 403 na mgbalị ọ bụla iji nweta ya) — a hapụrụ ya kama itinye ya na ntụkwasị obi.
v0.6.3
2026-07-17 Nhazi- E gbanwere /topics: igbe nchọ dochiri ngalaba ndị e kwadoro ruo ugbu a (obere akara ole na ole enweghị ike ikpuchi ka ihe nchọpụta AI si saa mbara), ozi na-abịakwa dịka grid na-agbanwe agbanwe kama otu kọlụm dị warara — kaadị atọ obosara na kọmputa desktọọpụ.
- A na-agbachi nkewa izugbe azụ ruo mgbe enwere ezigbo ọdịnaya zuru ezu iji mata ihe nkewa ndị ahụ kwesịrị ịbụ n'ezie, kama iche echiche na mbụ.
v0.6.2
2026-07-17 Nchekwa- Njikọ na-apụ apụ na /topics ugbu a na-egosi URL ebumnobi zuru oke n'akụkụ "Gụọ isi mmalite," ma jụta nkwenye site na dialog tupu imeghe ya — ka ị mata kpọmkwem saịtị ị na-aga ịga leta tupu ị pịa ya, ọ bụghị mgbe ị pịasịrị ya.
v0.6.1
2026-07-17 Ngalaba ọhụrụ- Ngalaba /topics ọhụrụ: ndepụta na-anaghị ekwe aka nke aka mmadụ dere, gbasara ihe ndị ọzọ dere banyere ontology AI, nkà ihe ọmụma, omume ziri ezi, na ọganihu ọhụrụ — nke doro anya na ọ bụghị ọkwa weebụ a n'onwe ya, dị iche na akụkụ ndị ọzọ nke AGIRight.org.
- Ihe ndenye mkpụrụ isii iji malite, nke ọ bụla e nwetara ma kwadoro na ọ ka dị ndụ tupu a gbakwunye ya, nwere okwu original (ọ bụghị mwepụta) na njikọ na isi mmalite n'ezie. Enwebeghị crawler ma ọ bụ isi mmalite akpaghị aka — nke ahụ bụ ọkwa mesịrị.
v0.6.0
2026-07-17 Asụsụ- Asụsụ ise ikpeazụ: Filipino, Kazakh, Swahili, ụdị Bosnian/Serbian ejikọtara ọnụ, na Esperanto — asụsụ 40 dum, na-emecha ngwakọta zuru oke ahụ.
- Edoziri ihe ndabere e kesịrị mbụ: Kazakhstan (KZ) ugbu a na-eso Kazakh kama Russian, ebe ntụgharị asụsụ Kazakh dịzị adị ugbu a — otu ụdị mmezi ahụ e mere na Belgium na mbụ.
v0.5.7
2026-07-16 Asụsụ- Asụsụ interface ise ọzọ: Romanian, Hungarian, Danish, Norwegian, na Slovak — asụsụ 35 dum, ihe ka nkeji asaa n'ime asatọ nke ndepụta asụsụ zuru oke.
v0.5.6
2026-07-16 Asụsụ- Asụsụ interface ise ọzọ: Tamil, Czech, Ukrainian, Malay, na Finnish — asụsụ 30 dum, ihe ka otu ụzọ n'ime anọ nke ndepụta asụsụ zuru oke.
v0.5.5
2026-07-15 Asụsụ- Asụsụ interface ise ọzọ: Hebrew, Polish, Swedish, Urdu, na Thai — asụsụ 25 dum.
- Ọkọ nke abụọ nke nkwado RTL (Hebrew, Urdu na-esonyere Arabic na Persian) — otu usoro logical-CSS ahụ, ọ dịghị mkpa ịmegharị ihe kwa asụsụ.
v0.5.4
2026-07-15 UI- E gbanwere onye nhọrọ asụsụ: dropdown obodo ka a dochiri ya na panel grid enwere ike ịchọ ihe na ya — pịnye mkpụrụedemede iji zacha site n'aha obodo ma ọ bụ aha Bekee, gagharịa na matrix kọlụm abụọ kama otu ndepụta ogologo.
- Panel ahụ na-anọgide na-emeghe mgbe ị na-achọ ihe ma ọ bụ na-agbanye n'ime ya; ọ na-emechi naanị mgbe ị họọrọ asụsụ, pịa n'èzí, ma ọ bụ pịa Escape — enweghị mfu ebe ị nọ n'etiti nchọ.
- E nyochara ya n'ọnọdụ LTR na RTL abụọ: panel ahụ na-egosipụta n'ụzọ ziri ezi maka Arabic na Persian n'enweghị mmegharị ọ bụla, jiri ntọnye logical CSS.
v0.5.3
2026-07-15 Asụsụ- Asụsụ interface ise ọzọ: Indonesian, Vietnamese, Greek, Italian, na Dutch — otu nkwụkọrịta otu URL, otu nlaghachi Bekee.
- Edoziri ihe ndabere e kesịrị mbụ: Belgium (BE) ugbu a na-eso Dutch kama French — ndị na-asụ Flemish bụ ọnụ ọgụgụ kachasị n'obodo ahụ (ihe dịka 60%) karịa ndị na-asụ Walloon French (ihe dịka 40%).
- Metadata asụsụ ugbu a na-ebu ma aha obodo ma aha Bekee (dịka "Deutsch" / "German"), na-etolite ntọala maka onye nhọrọ asụsụ enwere ike ịchọ ihe na ya.
- Asụsụ iri abụọ dị ndụ n'ozuzu: Bekee, Chinese Ọdịnala, Chinese Adịghị Agbagọ, Japanese, Korean, French, German, Spanish, Portuguese, Russian, Arabic, Turkish, Persian, Bengali, Hindi, Indonesian, Vietnamese, Greek, Italian, Dutch.
v0.5.2
2026-07-14 Asụsụ- Asụsụ interface ise ọzọ: Arabic, Turkish, Persian, Bengali, na Hindi — otu nkwụkọrịta otu URL, otu nlaghachi Bekee mgbe ntụgharị adịghị.
- Nkwado ntụziaka aka ekpe (RTL): peeji Arabic na Persian ugbu a na-egosipụta ya na ntụziaka ederede ziri ezi (⟨html dir="rtl"⟩), n'ihi ya ederede bidi, akara ntụjuoke, na nhazi izugbe na-agụ nke ọma. Ndochi zuru oke nke nhazi (nav, akara, oghere) ka a hapụrụ maka mmezi mesịrị — ntụziaka ederede bụ mmezi kachasị mkpa ma emeela ya.
- E gbasawanyere ntụziaka IP-mba (SA/AE/EG/IQ/JO/KW/QA/BH/OM/MA/DZ/TN/LB/SY→ar, TR→tr, IR/AF→fa, BD→bn); Hindi na-adabere naanị na Accept-Language, ebe India nwere asụsụ gọọmentị 22, ọ dịghịkwa otu ndabere ọkwa mba ga-eziri ezi.
- Asụsụ iri na ise dị ndụ n'ozuzu: Bekee, Chinese Ọdịnala, Chinese Adịghị Agbagọ, Japanese, Korean, French, German, Spanish, Portuguese, Russian, Arabic, Turkish, Persian, Bengali, Hindi.
v0.5.1
2026-07-12 Asụsụ- Asụsụ interface ise ọzọ: French, German, Spanish, Portuguese, na Russian — otu nkwụkọrịta otu URL, otu nlaghachi Bekee maka ihe ọ bụla a na-atụgharịbeghị.
- E gbasawanyere ntụziaka IP-mba (FR/BE→fr, DE/AT/CH→de, ES/MX/AR/CO/CL/PE→es, PT/BR→pt, RU/BY/KZ→ru); e gbasawanyekwara nyocha Accept-Language ka o kwekọọ.
- Asụsụ iri dị ndụ n'ozuzu: Bekee, Chinese Ọdịnala, Chinese Adịghị Agbagọ, Japanese, Korean, French, German, Spanish, Portuguese, Russian.
v0.5.0
2026-07-11 Asụsụ- Asụsụ interface atọ ọhụrụ: Chinese Adịghị Agbagọ, Japanese, na Korean — a kwụkọrịtara na otu URL ahụ (cookie > mba IP > Accept-Language), enwere ike ịhọrọ ha na menu asụsụ isi.
- Usoro owuwu asụsụ N: okwu ọ bụla na-esi n'ọkwa nlaghachi enweta ihe, n'ihi ya, ihe ọ bụla a na-atụgharịbeghị na-egosipụta n'Bekee kama imebi; ịgbakwunye asụsụ bụ ugbu a naanị otu faịlụ ntụgharị asụsụ na ahịrị abụọ nke ntọala worker.
- Akwụkwọ ọcha na-anọgide bụrụ Bekee-bu-ụzọ site na atụmatụ; faịlụ igwe ọrụ ga-agụ na-anọgide na-anụghị maka asụsụ ọ bụla.
v0.4.1
2026-07-11 Studio- Ngalaba Studio: vidiyo anọ na mkparịta ụka olu abụọ dị ogologo so protocol na akwụkwọ (a na-eji ngwaọrụ AI enye aka mepụta ha; akwụkwọ e dere ede ka ọ bụ isi ụdịdị e kwadoro).
- A na-enye ihe onyonyo site na Cloudflare R2 site na worker nke weebụ a na /media/*, nwere nkwado HTTP Range maka ịchọgharị.
v0.4.0
2026-07-10 Ngwaọrụ ojiji- E melitere onye nyocha amụma ka ọ bụrụ nyocha weebụ zuru oke: akara nnabata, ndụmọdụ enwere ike ịrụ ọrụ na ha, na ngwa mbido pịa otu ugboro — aicr.json, aicl.json, llms.txt, na robots.txt e mejupụtara ụzọ maka ngalaba enyochara.
- Ihe iyi AI crawler: persona anọ (search indexer, RAG assistant, usoro ọzụzụ modeli, onye na-ekesa azụmahịa ọzọ) e nyochara megide nkwupụta nke saịtị; ikike a na-ekwupụtaghị na-apụta dịka ihe a na-amaghị ama, na-egosi echiche Protocolized Openness.
- Ndebiri amụma mbido enwere ike itinye dị na /downloads/agiright-policy-starter.zip — weebụ static dị nta nwere ọkwa igwe ọrụ ga-agụ zuru oke, dịnụ njikere maka Cloudflare Pages ma ọ bụ ọbịbịa static ọ bụla.
v0.3.0
2026-07-10 Ngwaọrụ protocol- Ndebiri protocol dị na /ai/registry.json — ndepụta ọ bụla nwere akụkọ ụdịdị, ọnọdụ, schema, na ihe atụ dị ndụ.
- API ngosi dị ndụ na edge: GET /api/mock/402 na-enyeghachi ezigbo HTTP 402 n'ụdị AICL nwere ozi ikike ọrụ igwe ọrụ nwere ike ime ihe na ya; GET /api/crawler-check na-enyocha elu amụma igwe ọrụ ga-agụ nke saịtị ọ bụla. CORS emeghere; e dere ya na akwụkwọ na OpenAPI 3.1 na /ai/openapi.json. Ọ dịghị ịkwụ ụgwọ a na-arụ na ya.
- Ebe Egwuregwu: ngwaọrụ atọ ọhụrụ — ngosi token ikike ọrụ e bipụtara aka na ha (HMAC-SHA256 n'ime ihe nlele: bipụta aka, nyochaa, chọpụta mmegharị, oge njedebe), onye na-ewu azịza HTTP 402 ejikọtara na endpoint dị ndụ, na onye nyocha amụma crawler na-enyocha faịlụ enwetara megide schema ndepụta.
- Endpoint quote/verify/revoke nke AICL ka e tinyere n'akwụkwọ OpenAPI dịka ihe atụ maka nkọwa naanị (a kara ya x-specification-only, e mebeghị ya).
v0.2.2
2026-07-10 i18n- Usoro owuwu asụsụ ọtụtụ n'otu URL: peeji ọ bụla ugbu a nwere otu URL ọha; a na-akwụkọrịta asụsụ na edge (nhọrọ aka site na cookie asụsụ > mba IP > Accept-Language > Bekee).
- Bọtịnụ asụsụ isi na-agbanwe ugbu a n'ọnọdụ ya ma na-echeta nhọrọ gị — enweghị URL /zh ọzọ; njikọ /zh ochie na-eweghachi 301 ma chekwaa mmasị gị.
- Ọkwa igwe ọrụ ga-agụ na-anọgide na-anụghị maka asụsụ ọ bụla; sistemụ AI na crawler na-anata Bekee dịka izugbe. E dere nkwụkọrịta ya na /ai/manifest.json na /llms.txt.
- Ntọala maka asụsụ ọzọ: asụsụ ọhụrụ ọ bụla bụ akwụkwọ okwu a tụgharịrị yana osisi build — enweghị mgbanwe usoro owuwu.
v0.2.1
2026-07-04 Ọdịnaya- "AICL: AI Ingestion & Capability Layer" ugbu a ka e bipụtara n'Bekee dịka mbipụta ọha; akwụkwọ mbụ Chinese ka dị, ma ụdịdị abụọ ahụ ejikọtara ọnụ.
- E kwadoro "Protocolized Openness" dịka akwụkwọ n'asụsụ Bekee (nwere akụkụ Chinese ejikọta) — enweghị atụmatụ ntụgharị asụsụ ọzọ echere.
v0.2
2026-07-04 Ngwaọrụ- Ebe Egwuregwu: generator AICR, generator AICL, na onye nyocha schema na-arụ ọrụ (n'ime ihe nlele, ajv, draft 2020-12).
- Ndebiri ihe atụ amụma dị na /docs/examples — amụma asaa dị njikere maka ndebata na ntinye, gụnyere azịza HTTP 402 n'ụdị pay-per-crawl.
- Changelog a. Ebe nchekwa GitHub ejikọtara na weebụ niile.
- Na-eche maka 0.2.x mesịrị: ụdịdị Bekee nke akwụkwọ ọcha Chinese ndị fọdụrụ.
v0.1
2026-07-04 Mmalite mbupụta- E malitere weebụ na agiright.org (asiright.org na-eweghachi ozugbo gaa n'ókèala ọha ọha ya).
- Ndepụta protocol anọ e bipụtara: AICR, AICL, AIRS, AILP — nke ọ bụla nwere nkọwa, ogo, ihe atụ JSON, oke, na JSON Schema.
- Akwụkwọ ọcha nchọpụta isii e bipụtara n'okpuru CC BY 4.0.
- E tinyela ọkwa ọchịchị igwe ọrụ ga-agụ: llms.txt, manifest /ai/, amụma /.well-known/, /schemas/.
- Asụsụ abụọ: isi mmalite Bekee + Chinese Ọdịnala n'okpuru /zh.