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
    Recording239.3K starsMetric noteThe primary metric is 239.3K 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.
  2. 2
    hermes-agentAbout this entryThe agent that grows with you
    NousResearch
    Python
    Recording228.7K starsMetric noteThe primary metric is 228.7K 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.
  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
    Recording186.5K starsMetric noteThe primary metric is 186.5K 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
    Recording178.2K starsMetric noteThe primary metric is 178.2K 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.
  5. 5
    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
    Recording167K starsMetric noteThe primary metric is 167K 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
    firecrawlAbout this entryThe context API to search, scrape, and interact with the web at scale. 🔥
    firecrawl
    TypeScript
    Recording165.4K starsMetric noteThe primary metric is 165.4K 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
    Recording163.6K starsMetric noteThe primary metric is 163.6K 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
    Recording152.1K starsMetric noteThe primary metric is 152.1K 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.
  9. 9
    open-webuiAbout this entryUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
    open-webui
    Python
    Recording148.4K starsMetric noteThe primary metric is 148.4K 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
    Recording143.9K starsMetric noteThe primary metric is 143.9K 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.

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
    5717.1B tokens
    Recording560.2M requestsMetric noteThe primary metric is 560.2M requests; the supporting metric is 5717.1B 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
    9387B tokens
    Recording271.5M requestsMetric noteThe primary metric is 271.5M requests; the supporting metric is 9387B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  3. 3
    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
    627.2B tokens
    Recording244.8M requestsMetric noteThe primary metric is 244.8M requests; the supporting metric is 627.2B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  4. 4
    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
    519.6B tokens
    Recording162.2M requestsMetric noteThe primary metric is 162.2M requests; the supporting metric is 519.6B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  5. 5
    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
    4670.5B tokens
    Recording143.2M requestsMetric noteThe primary metric is 143.2M requests; the supporting metric is 4670.5B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  6. 6
    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
    209.3B tokens
    110.8M requestsMetric noteThe primary metric is 110.8M requests; the supporting metric is 209.3B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  7. 7
    gemini-3-flash-preview-20251217About this entrygemini-3-flash-preview-20251217 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
    898.1B tokens
    Recording105.8M requestsMetric noteThe primary metric is 105.8M requests; the supporting metric is 898.1B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  8. 8
    hy3-20260706About this entryhy3-20260706 is a model entry from tencent appearing in OpenRouter's public routing rankings. Open the name link for its official model page, context limits, pricing, and provider availability.
    tencent
    8936.3B tokens
    Recording105.2M requestsMetric noteThe primary metric is 105.2M requests; the supporting metric is 8936.3B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  9. 9
    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
    413.8B tokens
    Recording101.8M requestsMetric noteThe primary metric is 101.8M requests; the supporting metric is 413.8B tokens. Data comes from OpenRouter's public weekly ranking, and the line shows the available recorded usage history.
  10. 10
    deepseek-v4-pro-20260423About this entrydeepseek-v4-pro-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
    2584.1B tokens
    Recording99.8M requestsMetric noteThe primary metric is 99.8M requests; the supporting metric is 2584.1B 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
    2,075,427.57 usage indexMetric noteThe primary metric is 2,075,427.57 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
    1,431,977.34 usage indexMetric noteThe primary metric is 1,431,977.34 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-5.2About this entryglm-5.2 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
    1,087,694.97 usage indexMetric noteThe primary metric is 1,087,694.97 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
    minimax-m3About this entryminimax-m3 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
    492,562.45 usage indexMetric noteThe primary metric is 492,562.45 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
    kimi-k2.7-codeAbout this entrykimi-k2.7-code 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
    368,108.23 usage indexMetric noteThe primary metric is 368,108.23 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
    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
    367,247.12 usage indexMetric noteThe primary metric is 367,247.12 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
    kimi-k3About this entrykimi-k3 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
    327,383.00 usage indexMetric noteThe primary metric is 327,383.00 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
    qwen3.7-plusAbout this entryqwen3.7-plus 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
    305,288.98 usage indexMetric noteThe primary metric is 305,288.98 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
    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
    126,070.88 usage indexMetric noteThe primary metric is 126,070.88 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
    mimo-v2.5-proAbout this entrymimo-v2.5-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
    2.17 usage indexMetric noteThe primary metric is 2.17 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
    Recording79.2% 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
    Recording79.2% 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
    Recording78.8% 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
    Recording77.4% 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
    Recording76.8% 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
    Recording76.8% 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
    Recording76.8% 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
    Recording76.4% 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
    Recording75.8% 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
    Recording75.8% 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
    MiniMax-H3About this entryMiniMax-H3 is a public model published by MiniMaxAI on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    MiniMaxAI
    3.4K likes
    Recording47.5K downloadsMetric noteThe primary metric is 47.5K downloads; the supporting metric is 3.4K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  2. 2
    DeepSeek-V4-Flash-0731About this entryDeepSeek-V4-Flash-0731 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
    3.1K likes
    Recording954.4K downloadsMetric noteThe primary metric is 954.4K downloads; the supporting metric is 3.1K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  3. 3
    Muse-Glimmer-30BAbout this entryMuse-Glimmer-30B is a public model published by meta-models on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    meta-models
    716 likes
    Recording0 downloadsMetric noteThe primary metric is 0 downloads; the supporting metric is 716 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  4. 4
    MiniMax-H3About this entryMiniMax-H3 is a public model published by Comfy-Org on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    Comfy-Org
    1.1K likes
    Recording6M downloadsMetric noteThe primary metric is 6M downloads; the supporting metric is 1.1K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  5. 5
    MiniMax-H3-Turbo-LoraAbout this entryMiniMax-H3-Turbo-Lora is a public model published by larryvrh on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    larryvrh
    599 likes
    Recording0 downloadsMetric noteThe primary metric is 0 downloads; the supporting metric is 599 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  6. 6
    Kimi-K3About this entryKimi-K3 is a public model published by moonshotai on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    moonshotai
    10.5K likes
    Recording1.5M downloadsMetric noteThe primary metric is 1.5M downloads; the supporting metric is 10.5K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  7. 7
    LFM2.5-2.6BAbout this entryLFM2.5-2.6B is a public model published by LiquidAI on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    LiquidAI
    490 likes
    Recording89.7K downloadsMetric noteThe primary metric is 89.7K downloads; the supporting metric is 490 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  8. 8
    Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUFAbout this entryQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF is a public model published by DavidAU on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    DavidAU
    1.9K likes
    Recording2.4M downloadsMetric noteThe primary metric is 2.4M downloads; the supporting metric is 1.9K likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  9. 9
    Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRotAbout this entryQwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRot is a public model published by ethanfel on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    ethanfel
    440 likes
    Recording0 downloadsMetric noteThe primary metric is 0 downloads; the supporting metric is 440 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.
  10. 10
    maple-previewAbout this entrymaple-preview is a public model published by deepgrove on Hugging Face. Open its model card to review intended tasks, files, license, and usage instructions.
    deepgrove
    312 likes
    Recording1.3K downloadsMetric noteThe primary metric is 1.3K downloads; the supporting metric is 312 likes. Data comes from the Hugging Face Hub API; the history line records changes observed by FXDST every 6 hours.