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
    reaAbout this entryReverse engineer anything with agents, from app behavior down to native binaries.
    morluto
    TypeScript
    397.9K starsMetric noteThe primary metric is 397.9K 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.
  2. 2
    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
    291K starsMetric noteThe primary metric is 291K 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
    hermes-agentAbout this entryThe agent that grows with you
    NousResearch
    Python
    257.8K starsMetric noteThe primary metric is 257.8K 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.
  4. 4
    firecrawlAbout this entrySupercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
    firecrawl
    TypeScript
    196.1K starsMetric noteThe primary metric is 196.1K 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.
  5. 5
    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
    187.8K starsMetric noteThe primary metric is 187.8K 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.
  6. 6
    ollamaAbout this entryGet up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
    ollama
    Go
    185K starsMetric noteThe primary metric is 185K 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
    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
    174.8K starsMetric noteThe primary metric is 174.8K 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.
  8. 8
    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
    168.3K starsMetric noteThe primary metric is 168.3K 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.
  9. 9
    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
    Python
    159.7K starsMetric noteThe primary metric is 159.7K 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.
  10. 10
    open-webuiAbout this entryUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
    open-webui
    Python
    157K starsMetric noteThe primary metric is 157K 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
    jev-1.13-20260917About this entryjev-1.13-20260917 is a model entry from typesafe appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    typesafe
    3093.5B tokens
    954.8M requestsMetric noteThe primary metric is 954.8M requests; the supporting metric is 3093.5B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  2. 2
    glm-5.3-flash-20260826About this entryglm-5.3-flash-20260826 is a model entry from z-ai appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    z-ai
    14130B tokens
    661.4M requestsMetric noteThe primary metric is 661.4M requests; the supporting metric is 14130B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  3. 3
    deepseek-v4.1-flash-20261017About this entrydeepseek-v4.1-flash-20261017 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
    37258.7B tokens
    Recording609.9M requestsMetric noteThe primary metric is 609.9M requests; the supporting metric is 37258.7B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  4. 4
    gpt-6-luna-20260922About this entrygpt-6-luna-20260922 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
    9239.5B tokens
    548.7M requestsMetric noteThe primary metric is 548.7M requests; the supporting metric is 9239.5B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  5. 5
    deepseek-v4.1-flash-20260910About this entrydeepseek-v4.1-flash-20260910 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
    17013.5B tokens
    506.8M requestsMetric noteThe primary metric is 506.8M requests; the supporting metric is 17013.5B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  6. 6
    jev-1.14-20261014About this entryjev-1.14-20261014 is a model entry from typesafe appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    typesafe
    1720.7B tokens
    Recording415.7M requestsMetric noteThe primary metric is 415.7M requests; the supporting metric is 1720.7B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  7. 7
    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
    2853.9B tokens
    374M requestsMetric noteThe primary metric is 374M requests; the supporting metric is 2853.9B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  8. 8
    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
    4067.3B tokens
    323.1M requestsMetric noteThe primary metric is 323.1M requests; the supporting metric is 4067.3B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  9. 9
    gemini-3.5-flash-lite-20260721About this entrygemini-3.5-flash-lite-20260721 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
    251.8B tokens
    Recording282.2M requestsMetric noteThe primary metric is 282.2M requests; the supporting metric is 251.8B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  10. 10
    claude-haiku-5.5-20261007About this entryclaude-haiku-5.5-20261007 is a model entry from anthropic appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    anthropic
    2930.4B tokens
    Recording200.9M requestsMetric noteThe primary metric is 200.9M requests; the supporting metric is 2930.4B 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-v4.1-flashAbout this entrydeepseek-v4.1-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
    3,951,026.38 usage indexMetric noteThe primary metric is 3,951,026.38 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
    muse-spark-1.3-contributorAbout this entrymuse-spark-1.3-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
    1,579,737.90 usage indexMetric noteThe primary metric is 1,579,737.90 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
    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
    1,025,539.75 usage indexMetric noteThe primary metric is 1,025,539.75 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
    mimo-v2.6-flashAbout this entrymimo-v2.6-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
    1,001,347.93 usage indexMetric noteThe primary metric is 1,001,347.93 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
    minimax-m3.1-flashAbout this entryminimax-m3.1-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
    934,642.93 usage indexMetric noteThe primary metric is 934,642.93 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
    gpt-6-lunaAbout this entrygpt-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
    769,068.00 usage indexMetric noteThe primary metric is 769,068.00 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
    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
    415,647.00 usage indexMetric noteThe primary metric is 415,647.00 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
    beam-1.0-501b-a23bAbout this entrybeam-1.0-501b-a23b 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
    189,959.08 usage indexMetric noteThe primary metric is 189,959.08 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-v4.1-flash-1017About this entrydeepseek-v4.1-flash-1017 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
    56,505.42 usage indexMetric noteThe primary metric is 56,505.42 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
    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
    25.49 usage indexMetric noteThe primary metric is 25.49 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
    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.
  2. 2
    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.
  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
    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.
  6. 6
    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.
  7. 7
    Claude 4.5 Opus (high)About this entryClaude 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
    Gemini 3 Flash (high)About this entryGemini 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
    MiniMax M2.5 (high)About this entryMiniMax 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
    DeepSeek-V4.1-Flash-1017About this entryDeepSeek-V4.1-Flash-1017 is a public model published by deepseek-ai on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    deepseek-ai
    3.3K likes
    Recording105.7K downloadsMetric noteThe primary metric is 105.7K downloads; the supporting metric is 3.3K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  2. 2
    flintAbout this entryflint is a public model published by RecursiveSI on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    RecursiveSI
    953 likes
    Recording10.6K downloadsMetric noteThe primary metric is 10.6K downloads; the supporting metric is 953 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  3. 3
    Nanbeige4.3-33BAbout this entryNanbeige4.3-33B is a public model published by Nanbeige on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    Nanbeige
    652 likes
    Recording4.8K downloadsMetric noteThe primary metric is 4.8K downloads; the supporting metric is 652 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  4. 4
    Spark-X2.6-4BAbout this entrySpark-X2.6-4B is a public model published by XHToken on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    XHToken
    776 likes
    Recording6.2K downloadsMetric noteThe primary metric is 6.2K downloads; the supporting metric is 776 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  5. 5
    flux-3-image-klein-comfyAbout this entryflux-3-image-klein-comfy is a public model published by black-forest-labs on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    black-forest-labs
    1.8K likes
    Recording750.7K downloadsMetric noteThe primary metric is 750.7K downloads; the supporting metric is 1.8K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  6. 6
    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
    9.5K likes
    2.2M downloadsMetric noteThe primary metric is 2.2M downloads; the supporting metric is 9.5K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  7. 7
    MiniMax-M3.1-FlashAbout this entryMiniMax-M3.1-Flash is a public model published by MiniMaxAI on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    MiniMaxAI
    406 likes
    Recording11.1K downloadsMetric noteThe primary metric is 11.1K downloads; the supporting metric is 406 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  8. 8
    DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUFAbout this entryDeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF is a public model published by ISTA-DASLab on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    ISTA-DASLab
    384 likes
    Recording1.1M downloadsMetric noteThe primary metric is 1.1M downloads; the supporting metric is 384 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  9. 9
    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
    18.5K likes
    7.5M downloadsMetric noteThe primary metric is 7.5M downloads; the supporting metric is 18.5K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  10. 10
    Sage-A1.5About this entrySage-A1.5 is a public model published by InternScience on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    InternScience
    329 likes
    Recording6.6K downloadsMetric noteThe primary metric is 6.6K downloads; the supporting metric is 329 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.