AI Hippo

Hottest open-source projects in the last 24 hours

meta-llama/Llama-3.3-70B-Instruct · +1.2k ⭐ / 24h deepseek-ai/DeepSeek-V3 · HF 下载 +18% Qwen/Qwen2.5-72B-Instruct · Stars +890 open-webui/open-webui · +420 ⭐ hiyouga/LLaMA-Factory · +310 ⭐ unslothai/unsloth · Hugging Face 周下载 +22% meta-llama/Llama-3.3-70B-Instruct · +1.2k ⭐ / 24h deepseek-ai/DeepSeek-V3 · HF 下载 +18% Qwen/Qwen2.5-72B-Instruct · Stars +890 open-webui/open-webui · +420 ⭐ hiyouga/LLaMA-Factory · +310 ⭐ unslothai/unsloth · Hugging Face 周下载 +22%

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. Current data are placeholders; replace JSON after API/ETL integration and update the snapshot date.

Hot models

  • Qwen2.5-72B-Instruct

    Alibaba

    +4.2%
    VRAM
    ≥48GB
    License
    Apache-2.0
    HF
    Model card

    Apache-2.0

  • Llama-3.3-70B

    Meta

    +2.8%
    VRAM
    ≥40GB
    License
    Llama 3.3
    HF
    Model card

    Llama 3.3 Community

  • DeepSeek-V3

    DeepSeek

    +6.1%
    VRAM
    ≥80GB
    License
    MIT
    HF
    Model card

    MIT

  • Flux.1-dev

    Black Forest Labs

    +3.5%
    VRAM
    ≥24GB
    License
    FLUX.1 [dev] Non-Commercial
    HF
    Model card

    非商业许可

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 openclaw/openclaw 82.6 344,000 68,000 920 2,100 4,200 380
2 langchain-ai/langchain 47 106,000 16,800 412 4,100 2,100 98
3 Significant-Gravitas/AutoGPT 37.7 176,000 44,000 42 1,200 1,200 52
4 crewAIInc/crewAI 19 32,000 4,100 124 890 420 36
5 All-Hands-AI/OpenHands 18 52,000 5,800 132 460 1,400 72
6 hkuds/nanobot 17.2 37,400 4,100 156 180 890 42
7 langchain-ai/langgraph 17 11,800 1,900 198 420 680 45
8 webx-trend-demo/agent-slot-20 15 3,835 495 119 843 847 21
9 qwibitai/nanoclaw 15 26,600 2,800 112 95 410 28
10 sipeed/picoclaw 14.1 25,700 2,100 88 64 320 18
11 webx-trend-demo/agent-slot-19 13.3 3,813 473 97 821 825 84
12 webx-trend-demo/agent-slot-18 13.3 3,812 472 96 820 824 83
13 webx-trend-demo/agent-slot-17 13.3 3,811 471 95 819 823 82
14 webx-trend-demo/agent-slot-16 13.3 3,810 470 94 818 822 81
15 webx-trend-demo/agent-slot-15 13.2 3,809 469 93 817 821 80
16 webx-trend-demo/agent-slot-14 13.2 3,808 468 92 816 820 79
17 webx-trend-demo/agent-slot-13 13.2 3,807 467 91 815 819 78
18 webx-trend-demo/agent-slot-12 13.2 3,806 466 90 814 818 77
19 webx-trend-demo/agent-slot-11 13.1 3,805 465 89 813 817 76
20 Pythagora-io/gpt-pilot 13 33,000 3,000 36 130 520 24

Multi-agent

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 browser-use/browser-use 82.6 62,000 7,200 210 210 890 48
2 microsoft/autogen 63.5 42,000 6,100 86 512 540 34
3 geekan/MetaGPT 62.9 51,000 6,400 78 390 760 30
4 OpenInterpreter/open-interpreter 54 58,000 6,200 38 210 890 28
5 webx-trend-demo/multi_agent-slot-20 33.5 13,745 2,005 109 53 57 11
6 ag2ai/ag2 30.4 14,000 1,700 74 240 390 26
7 SWE-agent/SWE-agent 27.2 15,000 1,900 64 120 280 22
8 webx-trend-demo/multi_agent-slot-19 25 13,723 1,983 87 31 35 74
9 webx-trend-demo/multi_agent-slot-18 24.9 13,722 1,982 86 30 34 73
10 webx-trend-demo/multi_agent-slot-17 24.8 13,721 1,981 85 29 33 72
11 webx-trend-demo/multi_agent-slot-16 24.7 13,720 1,980 84 28 32 71
12 microsoft/JARVIS 24.6 22,000 2,700 10 72 210 5
13 webx-trend-demo/multi_agent-slot-15 24.6 13,719 1,979 83 27 31 70
14 webx-trend-demo/multi_agent-slot-14 24.5 13,718 1,978 82 26 30 69
15 webx-trend-demo/multi_agent-slot-13 24.4 13,717 1,977 81 25 29 68
16 webx-trend-demo/multi_agent-slot-12 24.3 13,716 1,976 80 24 28 67
17 webx-trend-demo/multi_agent-slot-11 24.2 13,715 1,975 79 23 27 66
18 langroid-ai/langroid 17.2 4,200 480 52 85 120 12
19 aorwall/moa 16.8 11,000 1,200 18 68 140 9
20 microsoft/TaskWeaver 16.6 7,600 860 28 96 150 8

Inference

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 vllm-project/vllm 76.4 48,000 8,200 380 920 2,100 180
2 ggerganov/llama.cpp 70.6 72,100 10,300 142 684 890 62
3 microsoft/onnxruntime 39.8 18,000 3,200 165 890 1,200 120
4 apache/tvm 30.2 14,000 3,200 88 760 980 85
5 sgl-project/sglang 27 12,000 1,500 210 210 890 95
6 Tencent/ncnn 25.6 21,000 4,800 48 320 680 42
7 pytorch/executorch 22.2 12,000 1,100 136 190 420 36
8 mlc-ai/mlc-llm 21.5 22,000 1,900 58 210 410 21
9 webx-trend-demo/inference-slot-20 16.9 1,527 987 91 335 339 23
10 NVIDIA/TensorRT-LLM 15.5 9,800 1,800 72 210 890 42
11 internlm/lmdeploy 15.2 7,600 920 86 150 320 30
12 webx-trend-demo/inference-slot-19 15.1 1,505 965 69 313 317 1
13 webx-trend-demo/inference-slot-18 12.7 1,504 964 68 312 316 85
14 webx-trend-demo/inference-slot-17 12.6 1,503 963 67 311 315 84
15 webx-trend-demo/inference-slot-16 12.5 1,502 962 66 310 314 83
16 webx-trend-demo/inference-slot-15 12.4 1,501 961 65 309 313 82
17 webx-trend-demo/inference-slot-14 12.3 1,500 960 64 308 312 81
18 webx-trend-demo/inference-slot-13 12.3 1,499 959 63 307 311 80
19 webx-trend-demo/inference-slot-12 12.2 1,498 958 62 306 310 79
20 webx-trend-demo/inference-slot-11 12.1 1,497 957 61 305 309 78

LLM library

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 huggingface/transformers 78.6 142,000 28,300 198 2,950 1,120 156
2 google-gemini/gemini-cli 39.1 18,000 2,100 320 210 890 48
3 BerriAI/litellm 30.5 17,000 2,100 220 260 640 52
4 unslothai/unsloth 27.6 42,000 3,200 165 85 1,200 62
5 OpenBMB/MiniCPM 17.2 18,000 1,400 62 130 320 16
6 ml-explore/mlx 15.7 21,000 1,500 42 120 280 28
7 QwenLM/Qwen 14.9 17,000 1,300 40 110 280 15
8 webx-trend-demo/llm_lib-slot-20 14.6 6,989 849 73 497 501 75
9 webx-trend-demo/llm_lib-slot-19 13.2 6,967 827 51 475 479 53
10 webx-trend-demo/llm_lib-slot-18 13.1 6,966 826 50 474 478 52
11 webx-trend-demo/llm_lib-slot-17 13.1 6,965 825 49 473 477 51
12 webx-trend-demo/llm_lib-slot-16 13 6,964 824 48 472 476 50
13 webx-trend-demo/llm_lib-slot-15 12.9 6,963 823 47 471 475 49
14 webx-trend-demo/llm_lib-slot-14 12.9 6,962 822 46 470 474 48
15 webx-trend-demo/llm_lib-slot-13 12.8 6,961 821 45 469 473 47
16 Lightning-AI/litgpt 12.8 13,000 1,400 26 170 310 20
17 webx-trend-demo/llm_lib-slot-12 12.7 6,960 820 44 468 472 46
18 webx-trend-demo/llm_lib-slot-11 12.7 6,959 819 43 467 471 45
19 LLaVA-VL/LLaVA-NeXT 12.5 15,000 1,200 18 90 240 12
20 mistralai/mistral-inference 10.5 8,900 920 8 42 120 8

Training framework

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 tensorflow/tensorflow 73.2 189,000 89,000 210 4,200 2,100 420
2 pytorch/pytorch 63.7 92,000 26,500 620 5,120 7,200 820
3 keras-team/keras 30.3 63,000 20,000 94 1,500 520 96
4 jax-ml/jax 24.2 32,000 3,100 180 890 1,200 120
5 tinygrad/tinygrad 24 38,000 3,900 170 460 880 74
6 PaddlePaddle/Paddle 21.1 24,000 5,400 140 980 1,600 150
7 mindspore-ai/mindspore 19.2 29,000 5,200 88 620 980 63
8 webx-trend-demo/framework-slot-20 15.2 12,146 406 70 554 558 17
9 apache/mxnet 14.8 21,000 6,800 12 890 1,800 42
10 facebookresearch/xformers 14.3 9,000 1,000 84 240 460 55
11 openxla/xla 13.8 3,600 420 92 210 380 44
12 webx-trend-demo/framework-slot-19 13.6 12,124 384 48 532 536 80
13 webx-trend-demo/framework-slot-18 13.6 12,123 383 47 531 535 79
14 webx-trend-demo/framework-slot-17 13.5 12,122 382 46 530 534 78
15 webx-trend-demo/framework-slot-16 13.5 12,121 381 45 529 533 77
16 webx-trend-demo/framework-slot-15 13.5 12,120 380 44 528 532 76
17 webx-trend-demo/framework-slot-14 13.4 12,119 379 43 527 531 75
18 webx-trend-demo/framework-slot-13 13.4 12,118 378 42 526 530 74
19 webx-trend-demo/framework-slot-12 13.3 12,117 377 41 525 529 73
20 webx-trend-demo/framework-slot-11 13.3 12,116 376 40 524 528 72

Serving

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 ollama/ollama 72.1 138,000 11,200 124 420 1,800 72
2 ray-project/ray 61.5 37,000 6,500 210 2,300 5,200 420
3 mudler/LocalAI 32.9 32,000 2,800 95 210 890 48
4 lm-sys/FastChat 25.7 39,000 4,600 16 240 780 18
5 skypilot-org/skypilot 23 6,800 520 84 125 210 24
6 huggingface/text-generation-inference 22.5 12,000 1,500 64 180 420 36
7 KServe/KServe 21.5 4,200 1,400 66 320 520 62
8 vllm-project/aibrix 19.3 1,300 120 72 60 90 10
9 triton-inference-server/server 18.8 8,900 2,100 42 120 680 28
10 webx-trend-demo/serving-slot-20 16.3 3,476 136 40 284 288 12
11 bentoml/OpenLLM 15 11,000 840 22 105 230 14
12 webx-trend-demo/serving-slot-19 12.1 3,454 114 18 262 266 75
13 webx-trend-demo/serving-slot-18 11.9 3,453 113 17 261 265 74
14 webx-trend-demo/serving-slot-17 11.8 3,452 112 16 260 264 73
15 webx-trend-demo/serving-slot-16 11.6 3,451 111 15 259 263 72
16 webx-trend-demo/serving-slot-15 11.5 3,450 110 14 258 262 71
17 webx-trend-demo/serving-slot-14 11.3 3,449 109 13 257 261 70
18 webx-trend-demo/serving-slot-13 11.2 3,448 108 12 256 260 69
19 webx-trend-demo/serving-slot-12 11.1 3,447 107 11 255 259 68
20 webx-trend-demo/serving-slot-11 10.9 3,446 106 10 254 258 67

Evaluation

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 openai/evals 64.8 15,000 2,500 14 310 640 24
2 explodinggradients/ragas 63.8 9,000 950 118 180 410 32
3 confident-ai/deepeval 58.2 9,400 780 96 160 330 20
4 webx-trend-demo/eval-slot-19 55.6 9,262 322 106 170 174 73
5 webx-trend-demo/eval-slot-18 55.4 9,261 321 105 169 173 72
6 webx-trend-demo/eval-slot-17 55.1 9,260 320 104 168 172 71
7 webx-trend-demo/eval-slot-16 54.9 9,259 319 103 167 171 70
8 webx-trend-demo/eval-slot-15 54.6 9,258 318 102 166 170 69
9 webx-trend-demo/eval-slot-14 54.4 9,257 317 101 165 169 68
10 webx-trend-demo/eval-slot-13 54.1 9,256 316 100 164 168 67
11 webx-trend-demo/eval-slot-12 53.9 9,255 315 99 163 167 66
12 webx-trend-demo/eval-slot-11 53.6 9,254 314 98 162 166 65
13 EleutherAI/lm-evaluation-harness 53.5 9,200 1,200 48 320 420 42
14 webx-trend-demo/eval-slot-20 34.8 9,284 344 8 192 196 10
15 open-compass/opencompass 32.2 4,800 480 52 120 280 18
16 RUC-NLPIR/FlashRAG 31.8 6,100 560 40 88 210 11
17 huggingface/lighteval 17.9 2,100 180 38 42 120 12
18 stanford-crfm/helm 15.4 2,800 320 12 85 180 8
19 lmarena/arena-hard-auto 14.9 2,200 240 20 55 96 7
20 prometheus-eval/prometheus-eval 11.6 1,900 160 14 42 70 6

RAG / vector search

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 langgenius/dify 83.4 82,000 12,000 260 980 3,100 160
2 run-llama/llama_index 55.3 42,000 6,200 165 890 1,200 85
3 FlowiseAI/Flowise 49 39,000 21,000 96 520 1,300 84
4 AnythingLLM/AnythingLLM 39.3 41,000 4,200 120 340 820 55
5 milvus-io/milvus 33.9 32,000 4,200 120 420 2,100 95
6 deepset-ai/haystack 26.5 19,800 2,600 72 420 470 28
7 qdrant/qdrant 26.4 24,000 1,500 95 210 420 42
8 vercel/ai-chatbot 19.6 17,000 3,400 54 160 240 22
9 webx-trend-demo/rag-slot-20 17.4 1,160 620 84 268 272 31
10 weaviate/weaviate 16.9 12,000 890 64 180 420 36
11 chroma-core/chroma 15.3 18,000 1,500 42 120 680 28
12 webx-trend-demo/rag-slot-19 14.7 1,138 598 62 246 250 9
13 webx-trend-demo/rag-slot-18 14.6 1,137 597 61 245 249 8
14 webx-trend-demo/rag-slot-17 14.4 1,136 596 60 244 248 7
15 webx-trend-demo/rag-slot-16 14.3 1,135 595 59 243 247 6
16 webx-trend-demo/rag-slot-15 14.2 1,134 594 58 242 246 5
17 webx-trend-demo/rag-slot-14 14.1 1,133 593 57 241 245 4
18 webx-trend-demo/rag-slot-13 14 1,132 592 56 240 244 3
19 webx-trend-demo/rag-slot-12 13.8 1,131 591 55 239 243 2
20 webx-trend-demo/rag-slot-11 13.7 1,130 590 54 238 242 1

Demo data—not live GitHub. Production: schedule REST/GraphQL ingestion, write JSON, then 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

Home