The AI landscape, ranked by evidence

Five source-attributed rankings bring project momentum, model usage, coding-agent performance, and open-model activity into one scan-friendly view.

Refreshed every 6 hoursPages use cached data for fast loading

GitHub AI Project Momentum

View Top 20
  1. 1
    ECCAbout this entryThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
    affaan-m
    JavaScript
    244.1K starsMetric noteThe primary metric is 244.1K stars, sourced from GitHub Search API. The history line is recorded by FXDST every 6 hours and shows Stars movement, not an official GitHub Trending rank.
  2. 2
    hermes-agentAbout this entryThe agent that grows with you
    NousResearch
    Python
    238K starsMetric noteThe primary metric is 238K stars, sourced from GitHub Search API. The history line is recorded by FXDST every 6 hours and shows Stars movement, not an official GitHub Trending rank.
  3. 3
    AutoGPTAbout this entryAutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
    Significant-Gravitas
    Python
    187K starsMetric noteThe primary metric is 187K stars, sourced from GitHub Search API. The history line is recorded by FXDST every 6 hours and shows Stars movement, not an official GitHub Trending rank.
  4. 4
    ollamaAbout this entryGet up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
    ollama
    Go
    179.7K starsMetric noteThe primary metric is 179.7K stars, sourced from GitHub Search API. The history line is recorded by FXDST every 6 hours and shows Stars movement, not an official GitHub Trending rank.
  5. 5
    firecrawlAbout this entryThe context API to search, scrape, and interact with the web at scale. 🔥
    firecrawl
    TypeScript
    173.9K starsMetric noteThe primary metric is 173.9K stars, sourced from GitHub Search API. The history line is recorded by FXDST every 6 hours and shows Stars movement, not an official GitHub Trending rank.
  6. 6
    prompts.chatAbout this entryf.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
    f
    HTML
    168.2K starsMetric noteThe primary metric is 168.2K stars, sourced from GitHub Search API. The history line is recorded by FXDST every 6 hours and shows Stars movement, not an official GitHub Trending rank.
  7. 7
    transformersAbout this entry🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
    huggingface
    Python
    164.6K starsMetric noteThe primary metric is 164.6K stars, sourced from GitHub Search API. The history line is recorded by FXDST every 6 hours and shows Stars movement, not an official GitHub Trending rank.
  8. 8
    difyAbout this entryBuild Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
    langgenius
    TypeScript
    153.8K starsMetric noteThe primary metric is 153.8K stars, sourced from GitHub Search API. The history line is recorded by FXDST every 6 hours and shows Stars movement, not an official GitHub Trending rank.
  9. 9
    open-webuiAbout this entryUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
    open-webui
    Python
    150.3K starsMetric noteThe primary metric is 150.3K stars, sourced from GitHub Search API. The history line is recorded by FXDST every 6 hours and shows Stars movement, not an official GitHub Trending rank.
  10. 10
    langchainAbout this entryThe agent engineering platform.
    langchain-ai
    Python
    145.2K starsMetric noteThe primary metric is 145.2K stars, sourced from GitHub Search API. The history line is recorded by FXDST every 6 hours and shows Stars movement, not an official GitHub Trending rank.

OpenRouter Model Usage Ranking

View Top 20
  1. 1
    deepseek-v4-flash-20260423About this entrydeepseek-v4-flash-20260423 is a model entry from deepseek appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    deepseek
    5422.1B tokens
    496.6M requestsMetric noteThe primary metric is 496.6M requests; the supporting metric is 5422.1B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  2. 2
    deepseek-v4-flash-20260731About this entrydeepseek-v4-flash-20260731 is a model entry from deepseek appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    deepseek
    12278B tokens
    434.4M requestsMetric noteThe primary metric is 434.4M requests; the supporting metric is 12278B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  3. 3
    ox-alphaAbout this entryox-alpha is a model entry from stealth appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    stealth
    25246.6B tokens
    316M requestsMetric noteThe primary metric is 316M requests; the supporting metric is 25246.6B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  4. 4
    gpt-5.6-luna-20260709About this entrygpt-5.6-luna-20260709 is a model entry from openai appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    openai
    6055.3B tokens
    313.2M requestsMetric noteThe primary metric is 313.2M requests; the supporting metric is 6055.3B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  5. 5
    gemini-2.5-flash-liteAbout this entrygemini-2.5-flash-lite is a model entry from google appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    google
    846.1B tokens
    291M requestsMetric noteThe primary metric is 291M requests; the supporting metric is 846.1B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  6. 6
    gpt-oss-120bAbout this entrygpt-oss-120b is a model entry from openai appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    openai
    525B tokens
    132.3M requestsMetric noteThe primary metric is 132.3M requests; the supporting metric is 525B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  7. 7
    mimo-v2.5-20260422About this entrymimo-v2.5-20260422 is a model entry from xiaomi appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    xiaomi
    10844.3B tokens
    129.1M requestsMetric noteThe primary metric is 129.1M requests; the supporting metric is 10844.3B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  8. 8
    gpt-4o-miniAbout this entrygpt-4o-mini is a model entry from openai appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    openai
    234.5B tokens
    123.2M requestsMetric noteThe primary metric is 123.2M requests; the supporting metric is 234.5B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  9. 9
    gemini-2.5-flashAbout this entrygemini-2.5-flash is a model entry from google appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    google
    429.1B tokens
    112.9M requestsMetric noteThe primary metric is 112.9M requests; the supporting metric is 429.1B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  10. 10
    text-embedding-3-smallAbout this entrytext-embedding-3-small is a model entry from openai appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    openai
    147.7B tokens
    111.2M requestsMetric noteThe primary metric is 111.2M requests; the supporting metric is 147.7B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.

OpenCode Coding Model Usage

View Top 20
  1. 1
    deepseek-v4-flashAbout this entrydeepseek-v4-flash is a model observed in the OpenCode usage dataset. This row compares its published usage signal with other models in the same OpenCode series.
    OpenCode
    OpenCode usage series
    3,729,050.16 usage indexMetric noteThe primary metric is 3,729,050.16 usage index; the supporting metric is OpenCode usage series. Data comes from OpenCode Data, and the line shows the published model-usage history.
  2. 2
    deepseek-v4-proAbout this entrydeepseek-v4-pro is a model observed in the OpenCode usage dataset. This row compares its published usage signal with other models in the same OpenCode series.
    OpenCode
    OpenCode usage series
    1,548,518.84 usage indexMetric noteThe primary metric is 1,548,518.84 usage index; the supporting metric is OpenCode usage series. Data comes from OpenCode Data, and the line shows the published model-usage history.
  3. 3
    mimo-v2.5About this entrymimo-v2.5 is a model observed in the OpenCode usage dataset. This row compares its published usage signal with other models in the same OpenCode series.
    OpenCode
    OpenCode usage series
    1,071,684.42 usage indexMetric noteThe primary metric is 1,071,684.42 usage index; the supporting metric is OpenCode usage series. Data comes from OpenCode Data, and the line shows the published model-usage history.
  4. 4
    glm-5.3-flashAbout this entryglm-5.3-flash is a model observed in the OpenCode usage dataset. This row compares its published usage signal with other models in the same OpenCode series.
    OpenCode
    OpenCode usage series
    547,946.89 usage indexMetric noteThe primary metric is 547,946.89 usage index; the supporting metric is OpenCode usage series. Data comes from OpenCode Data, and the line shows the published model-usage history.
  5. 5
    gpt-5.6-lunaAbout this entrygpt-5.6-luna is a model observed in the OpenCode usage dataset. This row compares its published usage signal with other models in the same OpenCode series.
    OpenCode
    OpenCode usage series
    411,593.00 usage indexMetric noteThe primary metric is 411,593.00 usage index; the supporting metric is OpenCode usage series. Data comes from OpenCode Data, and the line shows the published model-usage history.
  6. 6
    hy3About this entryhy3 is a model observed in the OpenCode usage dataset. This row compares its published usage signal with other models in the same OpenCode series.
    OpenCode
    OpenCode usage series
    314,039.41 usage indexMetric noteThe primary metric is 314,039.41 usage index; the supporting metric is OpenCode usage series. Data comes from OpenCode Data, and the line shows the published model-usage history.
  7. 7
    muse-spark-1.2-contributorAbout this entrymuse-spark-1.2-contributor is a model observed in the OpenCode usage dataset. This row compares its published usage signal with other models in the same OpenCode series.
    OpenCode
    OpenCode usage series
    210,760.89 usage indexMetric noteThe primary metric is 210,760.89 usage index; the supporting metric is OpenCode usage series. Data comes from OpenCode Data, and the line shows the published model-usage history.
  8. 8
    nemotron-3-ultraAbout this entrynemotron-3-ultra is a model observed in the OpenCode usage dataset. This row compares its published usage signal with other models in the same OpenCode series.
    OpenCode
    OpenCode usage series
    197,640.00 usage indexMetric noteThe primary metric is 197,640.00 usage index; the supporting metric is OpenCode usage series. Data comes from OpenCode Data, and the line shows the published model-usage history.
  9. 9
    deepseek-v4-flash-vision-expAbout this entrydeepseek-v4-flash-vision-exp is a model observed in the OpenCode usage dataset. This row compares its published usage signal with other models in the same OpenCode series.
    OpenCode
    OpenCode usage series
    104,298.92 usage indexMetric noteThe primary metric is 104,298.92 usage index; the supporting metric is OpenCode usage series. Data comes from OpenCode Data, and the line shows the published model-usage history.
  10. 10
    deepseek-v4-flash-0731About this entrydeepseek-v4-flash-0731 is a model observed in the OpenCode usage dataset. This row compares its published usage signal with other models in the same OpenCode series.
    OpenCode
    OpenCode usage series
    2.22 usage indexMetric noteThe primary metric is 2.22 usage index; the supporting metric is OpenCode usage series. Data comes from OpenCode Data, and the line shows the published model-usage history.

AI Coding Agent Benchmark

View Top 20
  1. 1
    live-SWE-agent + Claude 4.5 Opus medium (20251101)About this entrylive-SWE-agent + Claude 4.5 Opus medium (20251101) is an Agent or coding system evaluated on SWE-bench Verified. This row represents benchmark performance, not general popularity or production usage.
    UIUC
    live-SWE-agent
    79.2% resolvedMetric noteThe primary metric is 79.2% resolved, sourced from the SWE-bench public benchmark. It is a benchmark resolution rate, not real-world Agent usage volume.
  2. 2
    Sonar Foundation Agent + Claude 4.5 OpusAbout this entrySonar Foundation Agent + Claude 4.5 Opus is an Agent or coding system evaluated on SWE-bench Verified. This row represents benchmark performance, not general popularity or production usage.
    Sonar
    Sonar Foundation Agent
    79.2% resolvedMetric noteThe primary metric is 79.2% resolved, sourced from the SWE-bench public benchmark. It is a benchmark resolution rate, not real-world Agent usage volume.
  3. 3
    TRAE + Doubao-Seed-CodeAbout this entryTRAE + Doubao-Seed-Code is an Agent or coding system evaluated on SWE-bench Verified. This row represents benchmark performance, not general popularity or production usage.
    ByteDance
    TRAE
    78.8% resolvedMetric noteThe primary metric is 78.8% resolved, sourced from the SWE-bench public benchmark. It is a benchmark resolution rate, not real-world Agent usage volume.
  4. 4
    live-SWE-agent + Gemini 3 Pro Preview (2025-11-18)About this entrylive-SWE-agent + Gemini 3 Pro Preview (2025-11-18) is an Agent or coding system evaluated on SWE-bench Verified. This row represents benchmark performance, not general popularity or production usage.
    UIUC
    live-SWE-agent
    77.4% resolvedMetric noteThe primary metric is 77.4% resolved, sourced from the SWE-bench public benchmark. It is a benchmark resolution rate, not real-world Agent usage volume.
  5. 5
    Atlassian Rovo Dev (2025-09-02)About this entryAtlassian Rovo Dev (2025-09-02) is an Agent or coding system evaluated on SWE-bench Verified. This row represents benchmark performance, not general popularity or production usage.
    Atlassian
    Atlassian Rovo Dev
    76.8% resolvedMetric noteThe primary metric is 76.8% resolved, sourced from the SWE-bench public benchmark. It is a benchmark resolution rate, not real-world Agent usage volume.
  6. 6
    EPAM AI/Run Developer Agent v20250719 + Claude 4 SonnetAbout this entryEPAM AI/Run Developer Agent v20250719 + Claude 4 Sonnet is an Agent or coding system evaluated on SWE-bench Verified. This row represents benchmark performance, not general popularity or production usage.
    EPAM Systems, Inc.
    EPAM AI/Run Developer Agent
    76.8% resolvedMetric noteThe primary metric is 76.8% resolved, sourced from the SWE-bench public benchmark. It is a benchmark resolution rate, not real-world Agent usage volume.
  7. 7
    mini-SWE-agent + Claude 4.5 Opus (high)About this entrymini-SWE-agent + Claude 4.5 Opus (high) is an Agent or coding system evaluated on SWE-bench Verified. This row represents benchmark performance, not general popularity or production usage.
    SWE-agent
    mini-SWE-agent
    76.8% resolvedMetric noteThe primary metric is 76.8% resolved, sourced from the SWE-bench public benchmark. It is a benchmark resolution rate, not real-world Agent usage volume.
  8. 8
    ACoderAbout this entryACoder is an Agent or coding system evaluated on SWE-bench Verified. This row represents benchmark performance, not general popularity or production usage.
    ACoder
    ACoder
    76.4% resolvedMetric noteThe primary metric is 76.4% resolved, sourced from the SWE-bench public benchmark. It is a benchmark resolution rate, not real-world Agent usage volume.
  9. 9
    mini-SWE-agent + Gemini 3 Flash (high)About this entrymini-SWE-agent + Gemini 3 Flash (high) is an Agent or coding system evaluated on SWE-bench Verified. This row represents benchmark performance, not general popularity or production usage.
    SWE-agent
    mini-SWE-agent
    75.8% resolvedMetric noteThe primary metric is 75.8% resolved, sourced from the SWE-bench public benchmark. It is a benchmark resolution rate, not real-world Agent usage volume.
  10. 10
    mini-SWE-agent + MiniMax M2.5 (high)About this entrymini-SWE-agent + MiniMax M2.5 (high) is an Agent or coding system evaluated on SWE-bench Verified. This row represents benchmark performance, not general popularity or production usage.
    SWE-agent
    mini-SWE-agent
    75.8% resolvedMetric noteThe primary metric is 75.8% resolved, sourced from the SWE-bench public benchmark. It is a benchmark resolution rate, not real-world Agent usage volume.

Hugging Face Open Model Trends

View Top 20
  1. 1
    Qwen3.8-Flash-NextAbout this entryQwen3.8-Flash-Next is a public model published by Qwen on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    Qwen
    4.2K likes
    52.3K downloadsMetric noteThe primary metric is 52.3K downloads; the supporting metric is 4.2K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  2. 2
    GLM-5.3-FlashAbout this entryGLM-5.3-Flash is a public model published by zai-org on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    zai-org
    1.6K likes
    189.8K downloadsMetric noteThe primary metric is 189.8K downloads; the supporting metric is 1.6K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  3. 3
    GLM-5.3About this entryGLM-5.3 is a public model published by zai-org on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    zai-org
    1.2K likes
    8.8K downloadsMetric noteThe primary metric is 8.8K downloads; the supporting metric is 1.2K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  4. 4
    Qwen3.8-27BAbout this entryQwen3.8-27B is a public model published by Qwen on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    Qwen
    13.2K likes
    4M downloadsMetric noteThe primary metric is 4M downloads; the supporting metric is 13.2K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  5. 5
    Qwen3.8-Flash-Next-GGUFAbout this entryQwen3.8-Flash-Next-GGUF is a public model published by unsloth on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    unsloth
    539 likes
    188.1K downloadsMetric noteThe primary metric is 188.1K downloads; the supporting metric is 539 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  6. 6
    Qwen3.8-27B-GGUFAbout this entryQwen3.8-27B-GGUF is a public model published by unsloth on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    unsloth
    3.2K likes
    8.4M downloadsMetric noteThe primary metric is 8.4M downloads; the supporting metric is 3.2K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  7. 7
    Qwen3.8-27B-OBLITERATEDAbout this entryQwen3.8-27B-OBLITERATED is a public model published by OBLITERATUS on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    OBLITERATUS
    891 likes
    645.6K downloadsMetric noteThe primary metric is 645.6K downloads; the supporting metric is 891 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  8. 8
    LTX-2.5About this entryLTX-2.5 is a public model published by Lightricks on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    Lightricks
    2.1K likes
    1M downloadsMetric noteThe primary metric is 1M downloads; the supporting metric is 2.1K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  9. 9
    Qwen3.8-27B-Uncensored-MLXAbout this entryQwen3.8-27B-Uncensored-MLX is a public model published by orcarouter on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    orcarouter
    1.2K likes
    97.5K downloadsMetric noteThe primary metric is 97.5K downloads; the supporting metric is 1.2K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  10. 10
    Hy4-previewAbout this entryHy4-preview is a public model published by tencent on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    tencent
    263 likes
    1.4K downloadsMetric noteThe primary metric is 1.4K downloads; the supporting metric is 263 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.