AI Hippo

Last updated:

Hottest open-source projects in the last 24 hours

sindresorhus/awesome · ⭐ 469,273 freeCodeCamp/freeCodeCamp · ⭐ 445,331 public-apis/public-apis · ⭐ 436,736 EbookFoundation/free-programming-books · ⭐ 388,775 openclaw/openclaw · ⭐ 374,110 nilbuild/developer-roadmap · ⭐ 355,302 vinta/awesome-python · ⭐ 299,174 awesome-selfhosted/awesome-selfhosted · ⭐ 294,726 sindresorhus/awesome · ⭐ 469,273 freeCodeCamp/freeCodeCamp · ⭐ 445,331 public-apis/public-apis · ⭐ 436,736 EbookFoundation/free-programming-books · ⭐ 388,775 openclaw/openclaw · ⭐ 374,110 nilbuild/developer-roadmap · ⭐ 355,302 vinta/awesome-python · ⭐ 299,174 awesome-selfhosted/awesome-selfhosted · ⭐ 294,726

Open source · Live · GitHub + HF

GitHub open-source trends

Repositories are grouped by type (Agent, multi-agent, inference, LLM libraries, etc.) with in-group comparison of stars, forks, commits, contributors, and open issues/PRs. Data comes from scheduled ingestion snapshots with explicit snapshot dates.

Snapshot
Live source: HF Trending Snapshot source: GitHub grouped snapshot Estimated: Heat / VRAM

Hot models

24h Δ

Default order follows the Hugging Face trending list (7-day likes).

  • Lance

    bytedance-research

    24h Δ +37%
    License — Other Vision
    VRAM
    —
    HF task
    any-to-any
    HF
    Model card
    Hippo Heat 59

    See model card

  • Hy-MT2-1.8B

    tencent

    24h Δ +41%
    License — Other LLM
    VRAM
    —
    HF task
    translation
    HF
    Model card
    Hippo Heat 65

    See model card

  • supertonic-3

    Supertone

    24h Δ +55%
    License — Other Audio
    VRAM
    —
    HF task
    text-to-speech
    HF
    Model card
    Hippo Heat 84

    See model card

  • MiniCPM-V-4.6 Hot

    openbmb

    24h Δ +65%
    License — Other Vision
    VRAM
    —
    HF task
    image-text-to-text
    HF
    Model card
    Hippo Heat 95

    See model card

  • Marlin-2B

    NemoStation

    24h Δ +45%
    License — Other Vision
    VRAM
    —
    HF task
    video-text-to-text
    HF
    Model card
    Hippo Heat 71

    See model card

  • HRM-Text-1B Hot

    sapientinc

    24h Δ +59%
    License — Other LLM
    VRAM
    —
    HF task
    text-generation
    HF
    Model card
    Hippo Heat 89

    See model card

Grouped repository comparison

Each section lists repositories of the same class (e.g., Agent: OpenClaw, NanoBot, PicoClaw). Column meanings are consistent across groups. “Commits (30d)” follows the scraper’s rolling window.

Snapshot:

Public formula (within each group): Score = 100 × [0.30·Stars + 0.15·Forks + 0.30·Commits30d + 0.15·Contributors + 0.05·(1-Issues) + 0.05·(1-PRs)], after per-group min-max normalization.

Agent

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 Significant-Gravitas/AutoGPT 64 184,472 46,229 174 819 428 258
2 langchain-ai/langchain 59.2 137,461 22,741 260 3,686 583 416
3 ruvnet/ruflo 34.4 54,321 6,159 523 26 564 414
4 langflow-ai/langflow 31.9 148,690 9,099 78 342 947 243
5 Shubhamsaboo/awesome-llm-apps 29.1 111,546 16,558 26 82 8 2
6 crewAIInc/crewAI 15.8 52,007 7,208 111 299 354 36
7 dair-ai/Prompt-Engineering-Guide 14 74,893 8,113 0 212 265 175
8 mem0ai/mem0 12.2 56,491 6,439 53 313 409 130
9 FlowiseAI/Flowise 11.6 53,017 24,384 50 332 872 649
10 microsoft/autogen 6 58,312 8,807 0 533 850 525

Multi-agent

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 lobehub/lobehub 95.9 77,586 15,269 788 327 325 65
2 TauricResearch/TradingAgents 52.8 78,779 15,356 45 20 367 210
3 bytedance/deer-flow 50.7 69,257 9,285 207 253 866 532
4 FoundationAgents/MetaGPT 45.8 68,231 8,694 0 148 125 22
5 danny-avila/LibreChat 39.8 37,365 7,692 215 346 452 272
6 zhayujie/CowAgent 33 44,737 10,123 106 115 326 286
7 Yeachan-Heo/oh-my-claudecode 31.1 34,629 3,169 319 112 1 1
8 openai/openai-agents-python 29.9 26,594 4,078 208 276 105 43
9 wshobson/agents 19.6 35,828 3,890 35 62 4 1
10 OpenBMB/ChatDev 14.5 33,167 4,111 5 16 56 37

Inference

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 ggml-org/llama.cpp 72.8 112,439 18,640 392 1,703 1,730 700
2 BerriAI/litellm 61 48,007 8,282 1,526 1,526 3,329 1,387
3 sgl-project/sglang 47.5 28,151 6,077 1,148 1,426 3,478 651
4 earendil-works/pi 39.6 53,215 6,369 539 213 35 28
5 microsoft/onnxruntime 23.1 20,599 3,939 225 920 1,400 843
6 GeeeekExplorer/nano-vllm 12.1 13,557 2,123 5 15 69 26
7 k2-fsa/sherpa-onnx 10.9 12,420 1,405 34 207 571 526
8 h2oai/h2ogpt 10.1 11,987 1,312 0 78 329 292
9 niedev/RTranslator 10 10,015 923 1 11 26 24
10 abetlen/llama-cpp-python 9.3 10,336 1,408 23 180 716 603

LLM library

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 huggingface/transformers 65.4 160,904 33,300 211 3,943 2,385 1,041
2 nexu-io/open-design 42.3 50,342 5,727 1,362 236 326 164
3 google-gemini/gemini-cli 31.7 104,515 13,813 310 680 1,538 1,231
4 fighting41love/funNLP 25.2 80,822 15,221 0 13 45 38
5 safishamsi/graphify 19.4 52,228 5,584 326 51 274 116
6 farion1231/cc-switch 17.8 78,759 5,135 152 122 1,036 817
7 labmlai/annotated_deep_learning_paper_implementations 17.3 66,798 6,707 0 42 32 29
8 unslothai/unsloth 16.6 65,012 5,762 302 184 1,286 1,084
9 ComposioHQ/awesome-claude-skills 14.7 61,348 6,682 20 29 667 103
10 asgeirtj/system_prompts_leaks 13.3 40,652 6,753 109 21 22 0

Training framework

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 pytorch/pytorch 64.9 100,123 27,859 1,986 6,571 18,522 15,947
2 AUTOMATIC1111/stable-diffusion-webui 48.8 163,229 30,357 0 639 2,487 2,416
3 vllm-project/vllm 37.2 80,794 17,132 869 2,695 5,004 2,001
4 tensorflow/models 32.3 77,661 45,081 7 957 1,288 1,083
5 Comfy-Org/ComfyUI 29.5 114,116 13,360 220 315 4,026 3,689
6 rasbt/LLMs-from-scratch 23.2 95,432 14,619 7 64 4 3
7 keras-team/keras 21.3 64,084 19,774 115 1,518 189 151
8 ultralytics/yolov5 14.3 57,417 17,470 12 347 42 37
9 ultralytics/ultralytics 13.2 57,483 11,041 120 359 311 90
10 CorentinJ/Real-Time-Voice-Cloning 10.6 59,765 9,407 0 20 170 161

Serving

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 open-webui/open-webui 97.8 138,334 19,783 199 826 279 155
2 Mintplex-Labs/anything-llm 32.1 60,504 6,551 50 198 345 310
3 1Panel-dev/1Panel 30.4 35,552 3,179 113 116 397 393
4 AlexsJones/llmfit 23.7 26,545 1,597 74 66 56 46
5 janhq/jan 22 42,632 2,877 38 172 394 340
6 chatchat-space/Langchain-Chatchat 21.5 38,070 6,210 0 173 27 13
7 langbot-app/LangBot 20.3 16,094 1,424 72 84 119 111
8 PDFMathTranslate/PDFMathTranslate 14.8 33,963 3,052 1 57 124 111
9 lm-sys/FastChat 12.3 39,480 4,792 0 246 1,033 876
10 lss233/kirara-ai 11 18,759 1,838 0 49 3 1

Evaluation

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 confident-ai/deepeval 68.5 15,649 1,460 262 288 270 212
2 bitnami/charts 58.4 10,345 10,365 12 2,757 9 3
3 prometheus-community/helm-charts 37.8 6,105 5,367 64 1,771 217 123
4 helmfile/helmfile 20.6 5,108 346 45 385 42 33
5 komodorio/helm-dashboard 15.5 5,699 355 1 55 25 18
6 open-compass/opencompass 12.7 7,020 779 4 165 459 377
7 databus23/helm-diff 11.1 3,430 322 13 121 54 47
8 stackrox/kube-linter 10.2 3,450 264 11 91 79 73
9 helm/chartmuseum 10.1 3,827 405 5 88 115 91
10 roboll/helmfile 2.9 4,041 554 0 223 529 518

RAG / vector search

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 milvus-io/milvus 71.9 44,415 4,016 190 356 914 691
2 qdrant/qdrant 67.4 31,519 2,290 413 169 554 419
3 chroma-core/chroma 41.6 28,061 2,268 83 186 632 293
4 langchain4j/langchain4j 38.6 12,072 2,251 152 407 755 599
5 simdjson/simdjson 33.5 23,776 1,256 24 184 134 123
6 Tencent/APIJSON 27.3 18,404 2,271 9 91 243 238
7 svcvit/Awesome-Dify-Workflow 14.6 10,513 1,058 0 2 22 18
8 gka/chroma.js 13.5 10,563 547 0 43 64 60
9 zilliztech/GPTCache 11.3 8,036 582 0 43 88 74
10 std-microblock/chromatic 10.2 8,291 388 0 1 0 0

Snapshot data, not live GitHub streaming. Updates run through scheduled REST/GraphQL ingestion, JSON write, and rebuild.

GitHub-centric signals

Repositories, stars, forks, issues/PRs, release cadence, and topic tags are primary inputs; aggregate by organization, language, or topics for comparison.

Browse projects on GitHub Explore

Metrics

Grouped tables above list stars, forks, commits (30d), contributors, and open issues/PRs. Additional metrics may include star velocity, discussion volume, release cadence, or security signals—by day, week, or month.

Ingestion and refresh

GitHub REST/GraphQL, public datasets, or aggregators such as RSSHub; scheduled Actions to fetch, normalize, and write JSON or read-only stores, then ship static pages or read-only edge APIs.

Types and domains

  • LLM / inference stacks (serving, kernels, quantization-related repositories)
  • Agents, multi-agent frameworks, tool use, orchestration
  • Evaluations, benchmarks, datasets, reproducible leaderboards
  • Training, fine-tuning, alignment, engineering toolchains
  • Local deployment, inference services, edge stacks
  • Data, RAG, retrieval, vector-store ecosystems

Common misreadings

  • Equating stars with model quality—hype may diverge from benchmark strength.
  • Relying on short windows only—spikes may reflect campaigns; longer commit curves carry more signal.
  • Ignoring issues/PRs—healthy projects often show dense maintenance beyond stars.
  • Mixing personal and organization repositories—governance and release cadence may differ materially.
  • Treating GitHub as the entire ecosystem—important work may be closed-source or hosted elsewhere.

Further reading

Weekly AI industry brief (auto-generated)

For the week ending May 23, 2026, this Hugging Face hot list tracks 8 entries. By 24-hour growth, standouts include "Qwen3.6-27B-MTP-GGUF", "MiniCPM-V-4.6", "HRM-Text-1B", "supertonic-3", "Marlin-2B". Organizations appearing most often near the top include tencent, bytedance-research, Supertone, openbmb—a sign that releases, forks, and task pipelines remain fast-moving.

This snapshot skews toward established high-traffic cards; pair it with the “fastest growing today” rail to separate spikes from sustained interest.

On tokens / hosting: Hacker News highlights “OpenAI Codex: Increase in users hitting Codex rate limits”; Hacker News highlights “An interactive linear algebra primer aimed at LLM readers”; Hacker News highlights “AI Visibility Engineering Glossary – AEO, Geo, LLM Retrieval”. These cues tie to pricing, regions, and rollout cadence for hosted inference.

The grouped GitHub comparison below spans 8 ecosystem segments so you can contrast model buzz with engineering activity (stars, commits, issues/PRs). This text is auto-generated from the same snapshot as the tables and is for research context only—not financial or legal advice.

Home