arabic-ai-atlas
Summary: This MCP server lets you query the Arabic AI Atlas offline for Arabic AI models, datasets, benchmarks, tools, and organizations.
Search entries by case-insensitive substring across names, orgs, notes, tasks, and tags, with optional exact filters for type, country, and modality; results are sorted by Hugging Face downloads.
Recommend ranked entries for a task, optionally filtered by type, dialect, on-device suitability, and license; each result includes a score and explanation.
Fetch a single entry by id to get full details, links, and metrics.
Discover Arabic LLMs, ASR/TTS, OCR, embeddings, datasets, benchmarks, tools, agent skills, and organizations; use search to find ids for get.
Provides access to a curated catalogue of Arabic AI models, datasets and benchmarks sourced from Hugging Face, including download metrics; search and recommendation tools return entries with their Hugging Face model links and popularity stats.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@arabic-ai-atlas find an open-licensed Arabic speech recognition model for the Gulf dialect"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Open the interactive map โ ยท search, filter by dialect or license, share a filtered link.
Arabic AI Atlas
The Arabic AI ecosystem as a map, a list, and a skill your agent can install.
Install into your agent
claude plugin marketplace add h9-tec/arabic-ai-atlas
claude plugin install arabic-ai-atlas@arabic-ai-atlasRequires uv on PATH.
Then ask Claude: which open Arabic TTS runs on a phone? It answers from this atlas via the recommend MCP tool.
Add this to your .mcp.json:
{"mcpServers": {"arabic-ai-atlas": {"command": "uv", "args": ["run", "--frozen", "--no-dev", "--directory", "/path/to/arabic-ai-atlas", "python", "mcp/server.py"]}}}Related MCP server: agent101-mcp
How this repo works
YAML in
data/is the only hand-edited source.CI validates every PR against
data/schema.json.A nightly job pulls Hugging Face downloads and regenerates the map, README,
dist/atlas.jsonanddist/llms.txt.Wanted gaps (
data/wanted.yaml) are re-evaluated on every build, andbase_modellinks build the family tree and the MCPlineagetool.The repo is itself a Claude Code plugin: 5 skills + an MCP server that reads the atlas offline.
Entries by country
Country | Entries | LLM | ASR | TTS | OCR | Embedding | Datasets | Tools | Benchmarks | Papers | Orgs |
๐ International | 2200 | 210 | 119 | 58 | 32 | 30 | 710 | 238 | 75 | 671 | 23 |
๐ธ๐ฆ Saudi Arabia | 355 | 46 | 11 | 8 | 9 | 28 | 163 | 19 | 25 | 11 | 35 |
๐ฆ๐ช United Arab Emirates | 184 | 49 | 5 | 6 | 0 | 0 | 43 | 12 | 31 | 17 | 21 |
๐ช๐ฌ Egypt | 175 | 33 | 22 | 6 | 5 | 7 | 73 | 5 | 3 | 2 | 18 |
๐ถ๐ฆ Qatar | 128 | 9 | 3 | 0 | 2 | 0 | 63 | 10 | 17 | 19 | 5 |
๐ฒ๐ฆ Morocco | 71 | 13 | 5 | 2 | 2 | 1 | 29 | 4 | 7 | 3 | 5 |
๐ฉ๐ฟ Algeria | 42 | 3 | 1 | 3 | 0 | 0 | 18 | 15 | 1 | 0 | 1 |
๐ต๐ธ Palestine | 30 | 3 | 0 | 0 | 0 | 0 | 17 | 6 | 1 | 1 | 2 |
๐ฏ๐ด Jordan | 25 | 1 | 1 | 0 | 1 | 0 | 15 | 2 | 2 | 1 | 2 |
๐ฑ๐ง Lebanon | 23 | 14 | 0 | 0 | 0 | 0 | 6 | 1 | 0 | 1 | 1 |
๐น๐ณ Tunisia | 22 | 2 | 1 | 1 | 0 | 0 | 11 | 0 | 1 | 3 | 3 |
๐พ๐ช Yemen | 9 | 1 | 2 | 0 | 0 | 0 | 4 | 0 | 1 | 1 | 0 |
๐ฎ๐ถ Iraq | 8 | 2 | 0 | 0 | 0 | 0 | 4 | 0 | 1 | 0 | 1 |
๐ด๐ฒ Oman | 8 | 2 | 0 | 0 | 0 | 0 | 2 | 1 | 0 | 0 | 3 |
๐ธ๐ฉ Sudan | 7 | 0 | 1 | 0 | 0 | 0 | 3 | 0 | 0 | 1 | 2 |
๐ง๐ญ Bahrain | 5 | 1 | 2 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 1 |
๐ฐ๐ผ Kuwait | 4 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
๐ฑ๐พ Libya | 3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
๐ธ๐พ Syria | 3 | 2 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
Grid view
The same atlas as a country-by-type grid, with the most downloaded entries named in each cell.
Contents
๐ง Large Language Models
Showing 20 of 393 ยท see all 393 on the interactive map ยท full table
Name | Org | Country | Size | License | โฌ Downloads | Updated | Links |
AraBERTv02 | AUB MIND Lab | ๐ฑ๐ง LB | โ | unknown | 544K | 2024-03-26 | |
Llama 3.3 | Meta | ๐ INTL | 70B | llama3.3 | 353K | 2024-12-21 | |
Phi-4 | Microsoft | ๐ INTL | 4B | mit | 279K | 2026-07-14 | |
AraPoemBERT | King Saud University | ๐ธ๐ฆ SA | โ | cc-by-nc-4.0 | 112K | 2024-05-23 | |
bert-base-arabic-camelbert-mix-sentiment | CAMeL Lab, NYUAD | ๐ฆ๐ช AE | โ | apache-2.0 | 107K | 2021-10-17 | |
opus-mt-ar-en | Helsinki-NLP | ๐ INTL | โ | apache-2.0 | 107K | 2023-08-16 | |
SentimentArEng | qandos0 | ๐ INTL | โ | unknown | 96K | 2023-12-14 | |
ALLaM | SDAIA & IBM | ๐ธ๐ฆ SA | 7B | apache-2.0 | 94K | 2025-07-14 | |
ALLaM-7B-Instruct-preview | HUMAIN | ๐ธ๐ฆ SA | 7B | apache-2.0 | 92K | 2025-07-14 | |
aragpt2-base | AUB MIND Lab | ๐ฑ๐ง LB | 148M | unknown | 35K | 2023-10-30 | |
opus mt tc big ar en | Helsinki-NLP | ๐ INTL | โ | cc-by-4.0 | 35K | 2023-08-16 | |
opus-mt-en-ar | Helsinki-NLP | ๐ INTL | โ | apache-2.0 | 26K | 2023-08-16 | |
MARBERTv2 | UBC-NLP | ๐ INTL | โ | unknown | 23K | 2022-03-30 | |
bert-base-arabic-camelbert-da-sentiment | CAMeL Lab, NYUAD | ๐ฆ๐ช AE | โ | apache-2.0 | 17K | 2021-10-17 | |
bert-base-arabic-camelbert-msa-ner | CAMeL Lab, NYUAD | ๐ฆ๐ช AE | โ | apache-2.0 | 14K | 2021-10-17 | |
bert-base-arabic-camelbert-mix-ner | CAMeL Lab, NYUAD | ๐ฆ๐ช AE | โ | apache-2.0 | 11K | 2021-10-17 | |
Falcon Arabic | TII (UAE) | ๐ฆ๐ช AE | 7B | falcon-llm-license | 10K | 2025-05-31 | |
bert-base-arabertv2 | AUB MIND Lab | ๐ฑ๐ง LB | 136M | unknown | 10K | 2023-08-03 | |
bert-base-arabic-camelbert-mix | CAMeL Lab, NYUAD | ๐ฆ๐ช AE | โ | apache-2.0 | 6K | 2021-09-14 | |
bert-large-arabertv02 | AUB MIND Lab | ๐ฑ๐ง LB | 371M | unknown | 5K | 2023-08-03 |
๐๏ธ Speech Recognition
Showing 20 of 174 ยท see all 174 on the interactive map ยท full table
Name | Org | Country | License | โฌ Downloads | Updated | Links |
whisper-large-v3-turbo | OpenAI | ๐ INTL | mit | 5.1M | 2024-10-04 | |
openai/whisper-large-v3 | OpenAI | ๐ INTL | apache-2.0 | 3.6M | 2024-08-12 | |
wav2vec2-large-xlsr-53-arabic | jonatasgrosman | ๐ INTL | apache-2.0 | 2.3M | 2022-12-14 | |
Whisper Quran | Tarteel AI | ๐ INTL | apache-2.0 | 353K | 2022-12-13 | |
SeamlessM4T v2 | Meta | ๐ INTL | cc-by-nc-4.0 | 293K | 2024-01-04 | |
wav2vec2 quran phonetics | TBOGamer22 | ๐ INTL | apache-2.0 | 255K | 2026-01-21 | |
cohere-transcribe-arabic-07-2026 | Cohere Labs | ๐ INTL | apache-2.0 | 233K | 2026-07-13 | |
MMS-1b-all | Meta | ๐ INTL | cc-by-nc-4.0 | 220K | 2023-06-15 | |
Voxtral Mini | Mistral AI | ๐ INTL | apache-2.0 | 112K | 2025-07-28 | |
qwen3-asr-arabic-uae | Vadim Belsky | ๐ฆ๐ช AE | apache-2.0 | 80K | 2026-04-04 | |
muaalem model v3 2 | obadx | ๐ INTL | mit | 77K | 2025-09-04 | |
QwenCleo-ASR | Mohammed Aly | ๐ช๐ฌ EG | apache-2.0 | 45K | 2026-06-17 | |
wav2vec2 large xlsr 53 arabic quran v final | rabah2026 | ๐ INTL | apache-2.0 | 10K | 2025-12-21 | |
whisper-tiny-ar-quran | Tarteel AI | ๐ INTL | apache-2.0 | 5K | 2022-12-14 | |
whisper-large-v3-turbo-ar-quran | Naazim | ๐ INTL | apache-2.0 | 5K | 2025-12-08 | |
NVIDIA FastConformer Arabic (Diacritics) | NVIDIA | ๐ INTL | cc-by-4.0 | 3K | 2025-10-21 | |
wav2vec2-large-xlsr-moroccan-darija | Boumehdi | ๐ฒ๐ฆ MA | apache-2.0 | 3K | 2024-04-12 | |
Audar ASR V1 Turbo | Audar AI | ๐ INTL | other | 3K | 2026-08-20 | |
whisper-large-v3-turbo-darija | Anas Zil | ๐ฒ๐ฆ MA | mit | 3K | 2025-11-09 | |
wav2vec2-arabic-phoneme-asr | Mostafa Maroof | ๐ INTL | apache-2.0 | 2K | 2026-07-06 |
๐ Text-to-Speech
Showing 20 of 85 ยท see all 85 on the interactive map ยท full table
Name | Org | Country | License | โฌ Downloads | Updated | Links |
XTTS-v2 | Coqui | ๐ INTL | coqui-public-model-license | 6.1M | 2023-12-11 | |
Multilingual Chatterbox | Resemble AI | ๐ INTL | mit | 2.1M | 2026-06-10 | |
f5tts-algerian-darja | Touati Kamel | ๐ฉ๐ฟ DZ | apache-2.0 | 5K | 2026-09-23 | |
facebook/mms-tts-ara | Meta | ๐ INTL | cc-by-nc-4.0 | 5K | 2023-09-01 | |
Audar TTS V1 Turbo | Audar AI | ๐ INTL | other | 3K | 2026-07-07 | |
Arabic-TTS-Spark | IbrahimSalah | ๐ INTL | fair-noncommercial-research-license | 2K | 2025-11-27 | |
arabic-emirati-female-piper | Vadim Belsky | ๐ฆ๐ช AE | mit | 1K | 2025-12-01 | |
SILMA TTS v1 | SILMA AI | ๐ INTL | apache-2.0 | 1K | 2026-08-23 |
|
Audar TTS V1 Flash | Audar AI | ๐ INTL | other | 1K | 2026-07-07 | |
Nabra-82M-v0.1 | oddadmix | ๐ช๐ฌ EG | apache-2.0 | 1K | 2026-07-03 | |
NAMAA-Saudi-TTS-V2 | NAMAA-Space | ๐ธ๐ฆ SA | cc-by-nc-sa-4.0 | 1K | 2026-04-21 | |
Lahgtna OmniVoice v2 | oddadmix | ๐ช๐ฌ EG | unknown | 1K | 2026-06-15 | |
habibi-tts-doda-darija | Jip7e | ๐ฒ๐ฆ MA | apache-2.0 | 1K | 2026-08-29 | |
DarijaTTS-v0.1-500M | Kandir Research | ๐ฒ๐ฆ MA | apache-2.0 | 872 | 2025-11-26 | |
KasbahTTS-V0 | MenaVoice | ๐ INTL | mit | 488 | 2026-07-10 | |
Nabra 7M Distill | oddadmix | ๐ช๐ฌ EG | apache-2.0 | 274 | 2026-09-16 | |
NAMAA-Saudi-TTS | NAMAA-Space | ๐ธ๐ฆ SA | mit | 241 | 2026-01-29 | |
qwen3 TTS KSA | Vadim Belsky | ๐ฆ๐ช AE | apache-2.0 | 233 | 2026-03-17 | |
kemetone | Rabe3 | ๐ INTL | apache-2.0 | 232 | 2026-08-27 | |
speecht5_tts_clartts_ar | MBZUAI | ๐ฆ๐ช AE | cc-by-nc-4.0 | 214 | 2025-09-10 |
๐ OCR
Showing 20 of 51 ยท see all 51 on the interactive map ยท full table
Name | Org | Country | License | โฌ Downloads | Updated | Links |
Qari-OCR-v0.3-VL-2B-Instruct | NAMAA-Space | ๐ธ๐ฆ SA | apache-2.0 | 130K | 2025-06-10 | |
Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v2 | sherif1313 | ๐ INTL | apache-2.0 | 12K | 2025-12-29 | |
arabic_PP-OCRv5_mobile_rec | PaddlePaddle | ๐ INTL | apache-2.0 | 4K | 2025-10-16 | |
Arabic-English-handwritten-OCR-v3 | sherif1313 | ๐ INTL | apache-2.0 | 1K | 2025-12-29 | |
Qari OCR 0.2.2.1 VL 2B Instruct | NAMAA-Space | ๐ธ๐ฆ SA | apache-2.0 | 1K | 2025-06-07 | |
Qari-OCR-0.4.0-VL-4B-Instruct | NAMAA-Space | ๐ธ๐ฆ SA | apache-2.0 | 1K | 2026-02-01 | |
arabic PP OCRv3 mobile rec | PaddlePaddle | ๐ INTL | apache-2.0 | 977 | 2025-07-22 | |
Baseer Nakba | Misraj AI | ๐ธ๐ฆ SA | cc-by-nc-sa-4.0 | 791 | 2026-08-18 |
|
Qwen3-VL-2B-Persian-Arabic-Ocr-v1.0 | Mohajesmaeili | ๐ INTL | apache-2.0 | 480 | 2025-12-23 | |
Arabic-Qwen3.5-OCR-v4 | sherif1313 | ๐ INTL | apache-2.0 | 438 | 2026-03-24 | |
unlimited ocr quran uthmani | AyoubChLin | ๐ INTL | mit | 292 | 2026-07-02 | |
Arabic-GLM-OCR-v2 | sherif1313 | ๐ INTL | apache-2.0 | 239 | 2026-05-27 | |
waqf ocr hand written v1 | Waqf AI | ๐ช๐ฌ EG | apache-2.0 | 230 | 2026-06-09 | |
Qari-OCR-0.1-VL-2B-Instruct | NAMAA-Space | ๐ธ๐ฆ SA | apache-2.0 | 217 | 2025-06-10 | |
Katib-Qwen3.5-0.8B-0.1 | oddadmix | ๐ช๐ฌ EG | apache-2.0 | 203 | 2026-10-15 | |
arabic-legal-documents-ocr-1.0 | Bakrianoo | ๐ช๐ฌ EG | gemma | 195 | 2026-02-04 | |
Mubsir Qwen 2B VL | Hatim2221 | ๐ INTL | apache-2.0 | 194 | 2026-08-24 | |
Arabic GLM OCR v1 | sherif1313 | ๐ INTL | apache-2.0 | 183 | 2026-03-29 | |
Arabic OCR Qwen2.5 VL 7B Vision | loay | ๐ INTL | apache-2.0 | 116 | 2025-07-18 | |
Ketaba-OCR-LoRA | HassanB4 | ๐ INTL | apache-2.0 | 111 | 2026-03-05 |
๐ค Embeddings
Showing 20 of 66 ยท see all 66 on the interactive map ยท full table
Name | Org | Country | License | โฌ Downloads | Updated | Links |
Arabic SBERT 100K | akhooli | ๐ INTL | unknown | 16K | 2024-07-27 | |
asafaya/bert-base-arabic | asafaya | ๐ INTL | unknown | 8K | 2023-03-17 | |
Arabic-STS-Matryoshka-V2 | Omar Elshehy | ๐ช๐ฌ EG | unknown | 5K | 2024-12-29 | |
GATE-AraBert-v1 | Omartificial-Intelligence-Space | ๐ธ๐ฆ SA | apache-2.0 | 4K | 2025-09-07 | |
Arabic-Triplet-Matryoshka-V2 | Omartificial-Intelligence-Space | ๐ธ๐ฆ SA | apache-2.0 | 3K | 2026-10-29 | |
Arabic-Retrieval-v1.0 | Omar Elshehy | ๐ช๐ฌ EG | apache-2.0 | 2K | 2024-12-19 | |
ARA-Reranker-V1 | Omartificial-Intelligence-Space | ๐ธ๐ฆ SA | apache-2.0 | 2K | 2025-04-03 | |
silma-embedding-matryoshka-v0.1 | SILMA AI | ๐ INTL | apache-2.0 | 2K | 2025-05-15 | |
Mizan Rerank V2 | ALJIACHI | ๐ INTL | apache-2.0 | 2K | 2026-10-10 | |
arabic english bge m3 | sayed0am | ๐ INTL | mit | 1K | 2025-10-25 | |
bojji | NAMAA-Space | ๐ธ๐ฆ SA | mit | 841 | 2025-06-16 | |
GATE-Reranker-V1 | NAMAA-Space | ๐ธ๐ฆ SA | apache-2.0 | 574 | 2025-04-03 | |
Arabert all nli triplet Matryoshka | Omartificial-Intelligence-Space | ๐ธ๐ฆ SA | apache-2.0 | 514 | 2025-01-23 | |
Marbert all nli triplet Matryoshka | Omartificial-Intelligence-Space | ๐ธ๐ฆ SA | apache-2.0 | 497 | 2025-01-10 | |
Arabic-MiniLM-L12-v2-all-nli-triplet | Omartificial-Intelligence-Space | ๐ธ๐ฆ SA | apache-2.0 | 376 | 2025-06-10 | |
Arabic-labse-Matryoshka | Omartificial-Intelligence-Space | ๐ธ๐ฆ SA | apache-2.0 | 343 | 2025-01-10 | |
Arabic mpnet base all nli triplet | Omartificial-Intelligence-Space | ๐ธ๐ฆ SA | apache-2.0 | 307 | 2025-01-23 | |
Arabic-all-nli-triplet-Matryoshka | Omartificial-Intelligence-Space | ๐ธ๐ฆ SA | apache-2.0 | 269 | 2025-01-23 | |
Muffakir Embedding V2 | mohamed2811 | ๐ INTL | unknown | 229 | 2025-05-24 | |
bge m3 law | mhaseeb1604 | ๐ INTL | unknown | 206 | 2024-10-09 |
๐ Datasets
Showing 20 of 1163 ยท see all 1163 on the interactive map ยท full table
Name | Org | Country | Size | License | โฌ | Updated | Links |
prophet mosque library | ieasybooks | ๐ INTL | 10Kโ100K rows | mit | 433K | 2025-05-14 | |
Waqfeya Library | ieasybooks | ๐ INTL | 10K-100K books | mit | 147K | 2025-05-14 | |
shamela waqfeya library | ieasybooks | ๐ INTL | 1Kโ10K rows | mit | 139K | 2025-05-14 | |
Quranic Recitation Data | zaibihassan | ๐ INTL | 100K-1M clips | apache-2.0 | 48K | 2026-11-06 | |
XNLI | Facebook AI Research | ๐ INTL | 7,500 sentences | cc-by-nc-4.0 | 40K | 2024-01-05 |
|
wikiann | Rensselaer Polytechnic Institute | ๐ INTL | 185,000 tokens | unknown | 26K | 2024-02-22 |
|
Aya Dataset | Cohere For AI Community | ๐ INTL | 14,250 sentences | apache-2.0 | 24K | 2025-04-15 |
|
MIRACL | unknown | ๐ INTL | 2,061,414 documents | apache-2.0 | 22K | 2023-01-05 | |
TYDIQA | Google Research | ๐ INTL | 25,893 sentences | apache-2.0 | 20K | 2024-08-08 |
|
MMMLU | OpenAI | ๐ INTL | 14,000 sentences | mit | 18K | 2024-10-16 | |
Shamela4 Full DB | AuthenticIlm | ๐ INTL | 10Mโ100M rows | mit | 17K | 2026-05-19 | |
Quranic Translation Audio Data | zaibihassan | ๐ INTL | 1Kโ10K rows | apache-2.0 | 16K | 2026-10-22 | |
Global-MMLU Lite | Cohere For AI | ๐ INTL | 685 sentences | apache-2.0 | 15K | 2026-06-08 |
|
Arabic Books | MohamedRashad | ๐ INTL | 8.5k books | gpl-3.0 | 10K | 2024-11-28 | |
arwiki | CALM | ๐ INTL | 10Mโ100M rows | ['unknown'] | 10K | 2022-08-01 | |
SARD | riotu-lab | ๐ธ๐ฆ SA | โ | cc-by-nc-nd-4.0 | 10K | 2026-05-20 | |
prophet mosque library compressed | ieasybooks | ๐ INTL | 10Kโ100K rows | mit | 9K | 2025-05-08 | |
XStoryCloze | MetaAI | ๐ INTL | 1,870 sentences | cc-by-sa-4.0 | 9K | 2025-07-23 |
|
MedQA-Darija-MultiLingual | Williamsanderson | ๐ INTL | 100Kโ1M rows | cc-by-4.0 | 9K | 2026-05-06 | |
waqfeya library compressed | ieasybooks | ๐ INTL | 10Kโ100K rows | mit | 8K | 2025-04-25 |
๐ง Tools
Showing 20 of 313 ยท see all 313 on the interactive map ยท full table
Name | Org | Country | License | Links | Notes |
voxlect-arabic-dialect-whisper-large-v3 | tiantiaf (USC) | ๐ INTL | openrail | Whisper-large-v3 Arabic dialect classifier from the Voxlect benchmark. | |
flair-arabic-dialects-codeswitch-egy-lev | megantosh | ๐ INTL | apache-2.0 | Flair and fastText part-of-speech tagger for Egyptian and Levantine code-switched Arabic. | |
OSMAN readability metric | Lancaster University | ๐ INTL | unknown |
| Arabic readability metric analogous to Flesch, with parallel Arabic-English corpus. |
hassaniya-punctuation-restoration | Emin009 | ๐ INTL | apache-2.0 | Open-source punctuation-restoration model for Hassaniya Arabic. | |
Agentic-AI-Design-Patterns | Muhannad-Khaled | ๐ INTL | mit | The 21 agentic AI design patterns from Antonio Gulli's book, explained in Egyptian Arabic โ with framework-free, runnable Python examples. | |
Ai-Quran-Video-Composer | WalidZein | ๐ INTL | unknown | What if you can generate a a video with cinematic backgrounds behind the majestic verses of the Quran. | |
ai-rtl-resolver | miladniroee | ๐ INTL | mit |
| Ai Chatbot RTL Resolver |
Al Kindi AI | Alpha to Digits | ๐ฆ๐ช AE | proprietary | Arabic social listening intelligence product built on the Arabic.AI LLM. | |
AL-Khatma | oaokm | ๐ INTL | mit | A library Specialized About Islamic | |
Al-Munir | zedsalim | ๐ INTL | unknown |
| ุงูู ููุฑ: ููุงุณุชู ุงุน ููุฑุงุกุฉ ุงููุฑุขู ุงููุฑูู ู ุน ุงูุชูุณูุฑ ูุชุณููู ุงูุญูุธ ูุงูููู ูุงูู ุฑุงุฌุนุฉ |
al_quran_v3 | IsmailHosenIsmailJames | ๐ INTL | other | A Flutter application for reading the Holy Quran, tracking prayer times, and managing Islamic practices. | |
albitaqat_quran | rn0x | ๐ INTL | unknown |
| Complete data for 114 Quran surahs (Al-Bitaqat). |
Alfanous | Alfanous team | ๐ INTL | lgpl-3.0 | Arabic search engine API for the Quran with simple and advanced queries. | |
algeria_69_wilayas | Mohamed-gp | ๐ INTL | mit |
| ๐ฉ๐ฟ All 69 Algerian wilayas + 1,541 communes as free JSON โ official numbering, Arabic names, coordinates, dairas. |
Alkhalil Morpho Sys | unknown | ๐ INTL | unknown | A morphosyntactic parser for Arabic words that can process both vocalized and non-vocalized texts | |
all-words-in-all-languages | eymenefealtun | ๐ INTL | unknown | This repository contains all the words from every language that exists in the universe. | |
ALLAM based Retrieval Augmented Generation Arabic Conversational Alzheimer Assistance | ShahadAljohani | ๐ INTL | cc-by-4.0 | ALLAM-RAG: Saudi Arabic conversational RAG system combining retrieval with the ALLaM LLM to support Alzheimer's patients and caregivers. | |
alpinejs-i18n | rehhouari | ๐ INTL | mit |
| Easy i18n (Internationalization) for Alpine.js! |
alquranalkareem | alheekmahlib | ๐ INTL | unknown |
| ุงูุชุทุจูู ุงูุฃู ุซู ููุฑุงุกุฉ ุงููุฑุขู ุงููุฑูู |
Alyahmor | linuxscout | ๐ฉ๐ฟ DZ | gpl-3.0 | Arabic flexional morphology generator; maintainer is Algerian. |
๐ Benchmarks
Showing 20 of 165 ยท see all 165 on the interactive map ยท full table
Name | Org | Country | License | Links | Notes |
Global-MMLU | Cohere For AI | ๐ INTL | apache-2.0 |
| Multilingual MMLU-style benchmark of 42 languages (Arabic included) with culturally sensitive and culturally agnostic subsets. |
xquad | HiTZ Center | ๐ INTL | cc-by-sa-4.0 |
| Cross-lingual QA benchmark of 240 SQuAD paragraphs and 1190 question-answer pairs translated into ten languages including Arabic. |
ArabicMMLU | MBZUAI | ๐ฆ๐ช AE | cc-by-nc-4.0 | Multi-task language understanding from school exams | |
ArAD | SpeechAntiSpoofingBenchmarks | ๐ INTL | odc-by | Benchmark-ready packaging of the test split of the Arabic Audio Deepfake (ArAD) dataset: binary anti-spoofing on Arabic (primarily Levantine dialect) speech. | |
Belebele-Fleurs | University of Wรผrzburg | ๐ INTL | cc-by-sa-4.0 |
| Belebele-Fleurs extends BeleBele into a spoken SLU benchmark with multilingual multiple-choice listening comprehension QA from speech. |
FLORES-101 | Facebook AI Research | ๐ INTL | cc-by-sa-4.0 |
| Low-resource machine translation benchmark of 101 languages, with Arabic as one of them. |
MMCQA-SemEval27 | QCRI | ๐ถ๐ฆ QA | cc-by-nc-4.0 | This is the dataset for MMCultureQA, the SemEval 2027 shared task on culturally grounded visual question answering in English and Arabic. | |
DarijaMMLU | MBZUAI-Paris Lab | ๐ฆ๐ช AE | mit |
| MMLU translated into Moroccan Darija, 22k+ multiple-choice questions. |
MIRACL-VISION | NVIDIA | ๐ INTL | cc-by-sa-4.0 |
| Multilingual visual document retrieval benchmark extending MIRACL with Wikipedia page images for 18 languages. |
MMLU Arabic (FreedomIntelligence) | FreedomIntelligence | ๐ INTL | mit | MMLU translated into Arabic by gpt-3.5-turbo. | |
AlGhafa Arabic LLM Benchmark (Native) | Open Arabic LLM Leaderboard (OALL) | ๐ INTL | unknown | Native-Arabic multiple-choice evaluation tasks used as OALL leaderboard tasks. | |
TunisianMMLU | LINAGORA | ๐ INTL | cc-by-nc-sa-4.0 | MMLU translated into Tunisian Derja, LINAGORA (France); evaluated with lighteval. | |
Arabic EXAMS (OALL) | Open Arabic LLM Leaderboard (OALL) | ๐ INTL | unknown | Arabic subset of the EXAMS multilingual school-exam benchmark, an OALL task. | |
ARCD | Mozannar et al. | ๐ INTL | mit | Arabic Reading Comprehension Dataset of 1,395 Wikipedia-based questions from the SOQAL paper. | |
Human-Translated Arabic MMLU | MBZUAI | ๐ฆ๐ช AE | unknown | Human-translated MMLU into Arabic from MBZUAI, companion to ArabicMMLU. | |
EgyMMLU | UBC-NLP | ๐ INTL | unknown | MMLU translated into Egyptian Arabic from UBC (Canada), released with NileChat. | |
IdiomX | aymansharara | ๐ INTL | mit | Dataset: 190K+ examples โข 12K+ idioms โข 3 languages โข 4 benchmark tasks It supports four benchmark tasks: 1. | |
nn auto bench ds | nanonets | ๐ INTL | mit | nn-auto-bench-ds is a dataset designed for key information extraction (KIE) and serves as a benchmark dataset for nn-auto-bench. | |
OALL Arabic MMLU | Open Arabic LLM Leaderboard (OALL) | ๐ INTL | unknown | GPT-translated Arabic MMLU copy from FreedomIntelligence, used as an OALL v1 task. | |
fa en ar handwritten ocr v1 | saeid1999 | ๐ INTL | cc-by-4.0 | A large, clean, augmentation-rich synthetic handwriting dataset for training and benchmarking OCR / HTR models on Persian (fa), Arabic (ar) and English (en). |
๐ Papers
Showing 20 of 732 ยท see all 732 on the interactive map ยท full table
Title | Venue | Year | Topic | Links |
Systematic Review and Meta-Analysis of 2024โ2025 Studies on AI Arabic Translation, Linguistics and Pedagogy | Frontiers in Computer Science and Artificial Intelligence | 2026 | survey, translation | |
A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Model | BIGSCIENCE | 2026 | pretraining, evaluation | |
A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition | arXiv 2026 | 2026 | asr, diacritization, pretraining, speech, quran | |
A Corpus-Aligned Uthmani-to-Standard Quranic Word Mapping and a Deterministic Recitation Validator | arXiv 2026 | 2026 | asr, evaluation, quran | |
A Human-in-the-Loop Label Error Detection Framework Applied to Arabic-Script HTR Datasets | arXiv 2026 | 2026 | asr, ocr, evaluation | |
Abjad-Kids: An Arabic Speech Classification Dataset for Primary Education | arXiv 2026 | 2026 | evaluation, speech | |
ADAB: Arabic Dataset for Automated Politeness Benchmarking -- A Large-Scale Resource for Computational Sociopragmatics | arXiv 2026 | 2026 | evaluation | |
AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes | arXiv 2026 | 2026 | evaluation, vision | |
Alexandria: A Multi-Domain Dialectal Arabic Machine Translation Dataset for Culturally Inclusive and Linguistically Diverse LLMs | arXiv 2026 | 2026 | chat, translation, evaluation, vision |
|
AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation | arXiv 2026 | 2026 | chat, embedding, translation, evaluation |
|
Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models | arXiv 2026 | 2026 | evaluation, vision |
|
Almieyar: A Culturally Grounded Benchmark for Multi-Dialect Arabic Speech Recognition | arXiv 2026 | 2026 | asr, evaluation, speech, vision | |
An End-to-End Hybrid Framework for Rumour Detection in Low-Resources Algerian Dialect | arXiv 2026 | 2026 | embedding, pretraining, evaluation | |
ArabDiscrim: A Decade-Long Arabic Facebook Corpus on Racism and Discrimination | arXiv 2026 | 2026 | vision | |
Arabic Prompts with English Tools: A Benchmark | arXiv 2026 | 2026 | pretraining, evaluation | |
ArabicDialectHub: A Cross-Dialectal Arabic Learning Resource and Platform | arXiv 2026 | 2026 | translation |
|
ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification | arXiv 2026 | 2026 | safety, dialects, classification | |
AraDetox: A Multi-Dialect Arabic Detoxification Dataset | arXiv 2026 | 2026 | sentiment, evaluation |
|
ARAFA: An LLM-Generated Arabic Fact-Checking Dataset | arXiv 2026 | 2026 | evaluation | |
AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task | arXiv 2026 | 2026 | evaluation |
๐ข Organizations
Showing 20 of 125 ยท see all 125 on the interactive map ยท full table
Name | Country | Focus | Links |
King Saud University | ๐ธ๐ฆ SA | SaudiBERT, Saudi dialect corpora (STMC, SFC) | |
AIDA Lab (PSU) | ๐ธ๐ฆ SA | AI and Data Analytics lab at Prince Sultan University, Riyadh. | |
AIM Lab (NU-Q) | ๐ถ๐ฆ QA | AI and media research lab at Northwestern University in Qatar. | |
Ain Shams University | ๐ช๐ฌ EG | Arabic NLP, sentiment analysis, NER research | |
AlooChat | ๐ด๐ฒ OM | AI customer support chat agents for WhatsApp, Instagram, web and email, found via an Arabic conversational AI search in Oman. | |
AlQari | ๐ธ๐ฆ SA | Arabic-first document intelligence turning Arabic and English documents into structured, validated data. | |
Applied Innovation Center (AIC) | ๐ช๐ฌ EG | Egyptian MCIT AI center; builds the Karnak LLM family and publishes models on Hugging Face (Applied-Innovation-Center). | |
Arabic.AI (Tarjama) | ๐ฆ๐ช AE | Arabic-first autonomous AI - Pronoia Arabic LLM, Agentic AI platform | |
Arabot | ๐ฆ๐ช AE | Conversational AI for Arabic - Arabic NLP chatbot engine | |
Aramco Digital | ๐ธ๐ฆ SA | Aramco digital arm, behind Metabrain generative AI assistant and AI partnerships. | |
ARBML | ๐ธ๐ฆ SA | Democratizing Arabic NLP - masader, klaam, tkseem | |
ASAS AI | ๐ INTL | Saudi AI company offering Arabic models, automation and in-Kingdom infrastructure. | |
Astra Tech (Botim) | ๐ฆ๐ช AE | Abu Dhabi tech group behind Botim, building AI assistant products. | |
AtlasIA | ๐ฒ๐ฆ MA | Behind AL Atlas Moroccan Darija models | |
AUB MIND Lab | ๐ฑ๐ง LB | Foundational Arabic NLP models - AraBERT, AraGPT2, AraELECTRA | |
Calfa | ๐ INTL | OCR service extracting printed and handwritten text from scanned documents, including Arabic script. | |
CAMeL Lab (NYU Abu Dhabi) | ๐ฆ๐ช AE | CAMeLBERT, camel_tools, morphological analysis | |
CAMeL Lab, NYUAD | ๐ฆ๐ช AE | Arabic NLP tools and models - CAMeLBERT, camel_tools | |
Clusterlab AI | ๐ INTL | Behind 101 Billion Arabic Words Dataset and InstAr-500k | |
Cohere | ๐ INTL | Multilingual LLMs - Command R Arabic, RAG optimization |
๐งฉ Arabic Agent Skills
Skills shipped in this repo:
Skill | What it does | Install |
arabic-ai-advisor | Use when choosing an Arabic LLM, ASR, TTS, OCR, embedding model, dataset or tool โ recommends ranked options from the Arabic AI Atlas with licenses, dialect coverage and on-device fit. |
|
arabic-dialect-prompts | Use when writing system prompts or few-shot examples for an Arabic-speaking agent in a specific dialect, or when a model answers in formal Arabic (MSA) instead of the requested dialect. |
|
arabic-token-cost | Use when estimating or comparing how many tokens Arabic text costs across LLM tokenizers, or when Arabic prompts seem expensive, truncated or slow compared with English. |
|
rtl-bidi-lint | Use when reviewing or generating Arabic text, UI strings, HTML or Markdown that mixes RTL with LTR content, to catch digit mixing, unbalanced bidi isolates, stray LTR marks and hardcoded dir="ltr". |
|
tashkeel-check | Use when Arabic text may need diacritics (tashkeel) added or stripped, for TTS input, learner material, Quran or poetry, or when diacritization looks partial or inconsistent. |
|
Other Arabic agent skills in the wild:
Showing 20 of 35 ยท see all 35 on the interactive map ยท full table
Name | Org | Notes | Links |
ArabAgentSkills | ArabAgentSkills | Public source-backed Arab-world agent skills covering APIs, marketing, sales, support and localization. | |
ArabGuard | d12o6aa | Python SDK protecting LLMs and chatbots from prompt injection in Arabic text. | |
Arabic Content Studio | smeseik-ai | Claude Skills for Arabic content teams covering production, culture, SEO and brand voice. | |
Arabic Dict MCP | arnizamani | MCP server for grounded Arabic dictionary lookup wrapping arramooz (MSA verbs and nouns). | |
Arabic Scholar MCP Server | EngDawood | MCP server for searching Arabic academic research, articles and dissertations across sources. | |
Arabic Video Subtitles Skill | EngDawood | Skill with Netflix-style Arabic subtitling guidelines and an SRT/VTT checker. | |
Arabic Word Production Skill | Bannovich | Deterministic agent skill and plugin for Arabic-first and bilingual Word DOCX production. | |
arabic-bidi-engineering | MosaabGalmod | Agent skill for correct Arabic RTL/BiDi in chat, terminal and documents | |
arabic-pii-py | Aajil Labs | Local-first reversible PII tokenization for Arabic and Gulf data before it reaches an LLM. | |
ArabiMaak MCP | deepdiver4ai | Gulf Arabic language MCP server for word, phrase and cultural-context lookup. | |
awesome-arabic-claude-skills | EngDawood | Curated library of open-source Arabic skills for Claude Code and agents | |
Azan MCP | Ahmed Eltaher | Lightweight MCP library for Islamic prayer times and Qibla for AI agents; not Arabic-language specific. | |
Claude Adhkar | nosseralaa7-rgb | Shows Arabic-script adhkar in the Claude Code spinner with a terminal font that renders Arabic. | |
Claude Arabic Writing | Ahmed Dabak | Claude Agent Skill for natural, grammatically correct Arabic writing and translation. | |
Claude Code RTL Extension | yechielby | VS Code and Cursor extension adding RTL support for Hebrew and Arabic in Claude Code. | |
Claude Desktop RTL Patch (macOS) | toboly | Adds auto-detected Hebrew and Arabic RTL support to Claude Desktop on macOS. | |
Dorar Hadith MCP | ibnsaleem29 | Claude extension and MCP server for Hadith research including isnad and takhrij via Dorar. | |
Fanar MCP Server | danijeun | MCP server exposing Fanar API tools such as Islamic RAG and image generation. | |
Hadith MCP (ovehbe) | ovehbe | MCP server for searchable, citation-safe hadith text. | |
Hurmoz | Moshe-ship | Collection of 63 Arabic skills for the Hermes Agent framework. |
๐ฏ Most Wanted
Gaps nobody has filled yet. Add an entry that matches a rule and it moves to Recently filled. Rules live in data/wanted.yaml.
Gap | Why | Rule |
No openly licensed text-to-speech model with a Kuwaiti or Qatari voice is listed. |
| |
The only Moroccan OCR dataset listed has no clear license, so no openly licensed one is available. |
| |
A Sudanese ASR model exists, but no Sudanese speech dataset to train or test one is listed. |
| |
Mauritania has no listed model, dataset, or tool of any kind. |
| |
No openly licensed Yemeni dataset for speech recognition or synthesis is listed. |
| |
No Arabic embedding model targets the Sudanese, Yemeni, or Iraqi dialects. |
| |
The only TTS covering Iraqi has no clear license, so no openly licensed one is available. |
| |
No dataset from or about Libya is listed. |
| |
No openly licensed dataset of Syrian Levantine Arabic is listed. |
| |
No speech recognition model from Palestine is listed. |
| |
Omani datasets are listed, but none has a clear open license. |
| |
The only Kuwaiti dataset listed has no clear license. |
| |
The only Bahraini dataset listed is non-commercial, so no openly licensed one is available. |
| |
Nothing from Comoros, Djibouti, or Somalia is listed. |
| |
No openly licensed benchmark covers Arabic handwriting recognition. |
|
๐ณ Family tree
385 models with known lineage ยท explore the tree ยท add a base model with the base_model field (CONTRIBUTING)
Base family | Models | Most downloaded |
Qwen ยท ูููู | 65 | qwen3-asr-arabic-uae (80K โฌ) |
BERT ยท ุจูุฑุช | 58 | AraBERTv02 (544K โฌ) |
Whisper ยท ููุณุจุฑ | 56 | whisper-large-v3-turbo (5.1M โฌ) |
Gemma ยท ุฌูู ุง | 24 | Fanar-1-9B (4K โฌ) |
From scratch ยท ู ู ุงูุตูุฑ | 19 | ALLaM (94K โฌ) |
Llama ยท ูุงู ุง | 15 | Llama 3.3 (353K โฌ) |
Cohere | 9 | cohere-transcribe-arabic-07-2026 (233K โฌ) |
T5 ยท ุชู 5 | 9 | AraT5v2-base-1024 (1K โฌ) |
XTTS | 7 | XTTS-v2 (6.1M โฌ) |
BGE | 4 | arabic english bge m3 (1K โฌ) |
F5-TTS | 4 | f5tts-algerian-darja (5K โฌ) |
XLS-R ยท ุฅูุณ ุฅู ุฅุณ-ุขุฑ | 4 | wav2vec2-large-xlsr-moroccan-darija (3K โฌ) |
NLLB | 3 | darija to english 2 (25 โฌ) |
SeamlessM4T | 2 | SeamlessM4T v2 (293K โฌ) |
wav2vec ยท ูุงู ุชู ููู | 2 | wav2vec2 quran phonetics (255K โฌ) |
BLOOM ยท ุจููู | 1 | darija text generation (26 โฌ) |
E5 | 1 | algerianME5 (84 โฌ) |
Falcon ยท ูุงูููู | 1 | Falcon Arabic (10K โฌ) |
Mistral ยท ู ูุณุชุฑุงู | 1 | Mistral 7B v0.1 arabic (21 โฌ) |
MMS ยท ุฅู ุฅู ุฅุณ | 1 | mms 300m arabic dialect identifier (2K โฌ) |
Other ยท ุฃุฎุฑู | 99 | Multilingual Chatterbox (2.1M โฌ) |
๐ค Contributing
Edit the YAML in
data/.Run
uv run python scripts/build.py build(it uses the committed Hugging Face cache; the nightly job refreshes metrics).Open a PR.
Never hand-edit README.md, docs/tables/, assets/, dist/ or data/.cache/: the build and the nightly job write them, and CI rejects drift.
๐ License
Code: MIT. Data: CC BY 4.0.
๐ Sister project
Awesome Arabic NLP, the curated reading list this atlas grew alongside.
Generated 2026-11-10 from 3302 entries. Do not edit README.md by hand.
Available Tools
3 toolsgetA
Fetch one full Arabic AI Atlas entry by its id (e.g. "jais-30b"), including links and metrics.
Returns {"error": "unknown id", "id": ...} when no entry has that id. Use search to find ids.
Example: get(id="jais-30b")
Inputs: id (required).
recommendA
Recommend entries from the Arabic AI Atlas for a task, ranked with an explanation.
Score = 3 if the task is in the entry's tasks, +2 if the dialect matches, +1 if the task
word appears in its notes; zero-score entries are dropped. Each result carries score
and why. Ties go to models (llm, asr, tts, ocr, embedding) over datasets, benchmarks,
tools and orgs, then to downloads.
task: e.g. chat, tts, asr, ocr, embedding, translation. dialect: msa, egy, gulf, lev, magh, iraqi, sudanese, yemeni, classical, mixed (optional; entries lacking dialect data still match on task). on_device: true keeps only entries marked on-device (phone or laptop CPU); false drops those; omit for no filter. license_filter: "open" excludes proprietary/unknown licenses; any other string must equal the license exactly (optional). type: exact entry type, e.g. "tts" to get models only, "dataset" for training data (optional).
Example: recommend(task="tts", type="tts", on_device=true, license_filter="open")
Inputs: task (required), type, limit, dialect, +2 more. Returns: result
searchA
Search the Arabic AI Atlas, a curated catalogue of Arabic models, datasets, benchmarks, tools and organizations with Hugging Face download metrics.
Case-insensitive substring match over name, org, notes, tasks and tags; the optional type/country/modality filters are exact. Results are ordered by downloads, most first.
Valid values: type: llm, asr, tts, ocr, embedding, dataset, benchmark, tool, agent-skill, org country: SA, AE, EG, QA, MA, JO, TN, LB, KW, OM, BH, INTL modality: text, speech, vision, multimodal, none
Example: search(query="speech", type="asr", limit=5)
Inputs: query (required), type, limit, country, +1 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 3 tools
The three tools have clearly distinct purposes: `search` does substring matching with exact filters, `recommend` does task/dialect ranked scoring with explanations, and `get` fetches a single entry by id. The descriptions even cross-reference each other (get says 'use search to find ids'), leaving no realistic selection ambiguity.
All three names are single lowercase verbs (search, recommend, get) in a uniform style with no mixing of conventions. The pattern is predictable and readable.
Three tools is on the thin side, but for a read-only catalogue the discovery/ranking/retrieval split earns each tool's place. Nothing redundant or missing at the surface level.
The read-only domain is well covered: broad search with filters, semantic-ish task recommendations, and full-detail retrieval. Minor gaps exist (no way to list all entries, browse by organization, or enumerate valid filter values beyond the examples), but agents can work around these via search.
Maintenance
Related MCP Connectors
Find the right MCPs, tools and skills for any AI task - discovery over a 14k+ resource catalog.
Search and fetch curated AI agent skills, prompts and MCP servers.
Search agent-ready open source repos by task, interface, ecosystem and OG score.
Search a curated directory of agent tools, MCP servers, APIs, protocols and skills. No auth.
Related MCP Servers
- AlicenseAqualityBmaintenanceSearch and discover AI agents, skills, prompts, bundles and MCP connectors from the Spark catalog. Seven tools: search assets, get asset details and raw content, list popular assets and categories, check API key usage, and report the outcome of applying fetched content. No API key needed.520 npm4MIT
- AlicenseNot gradedqualityNot gradedmaintenanceSearch and discover 500+ tools, APIs, and services for AI agents. Browse 15 categories, get recommendations, and access structured metadata including auth methods, free tiers, and example calls.1-
- AlicenseAqualityDmaintenanceEnables AI agents to search, browse, and recommend tools from the Hermes Agent ecosystem directory with zero configuration.813 npmMIT
- AlicenseAqualityDmaintenanceEnables AI assistants to search, discover, and get recommendations from 20,000+ skills, tools, agents, rules, and MCP servers.529 npm1MIT