AI Hippo

Hottest open-source projects in the last 24 hours

codecrafters-io/build-your-own-x · ⭐ 534,272 public-apis/public-apis · ⭐ 454,024 freeCodeCamp/freeCodeCamp · ⭐ 453,334 EbookFoundation/free-programming-books · ⭐ 393,527 openclaw/openclaw · ⭐ 384,870 nilbuild/developer-roadmap · ⭐ 363,361 vinta/awesome-python · ⭐ 311,652 awesome-selfhosted/awesome-selfhosted · ⭐ 310,064 codecrafters-io/build-your-own-x · ⭐ 534,272 public-apis/public-apis · ⭐ 454,024 freeCodeCamp/freeCodeCamp · ⭐ 453,334 EbookFoundation/free-programming-books · ⭐ 393,527 openclaw/openclaw · ⭐ 384,870 nilbuild/developer-roadmap · ⭐ 363,361 vinta/awesome-python · ⭐ 311,652 awesome-selfhosted/awesome-selfhosted · ⭐ 310,064

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

Open source · Live · GitHub + HF

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).

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:

Data sources & methodology

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 96.2 384,870 80,878 11,854 3,041 5,625 2
2 NousResearch/hermes-agent 49.3 223,971 43,252 5,815 2,493 26,599 5
3 langchain-ai/langchain 31.6 143,200 23,854 131 3,700 463 71
4 affaan-m/ECC 30 236,888 36,015 104 303 117 83
5 Significant-Gravitas/AutoGPT 27.8 185,758 46,053 107 838 525 221
6 Shubhamsaboo/awesome-llm-apps 14.6 129,679 19,132 122 99 22 11
7 firecrawl/firecrawl 13.3 159,206 9,042 171 167 468 419
8 langflow-ai/langflow 11.3 152,735 9,747 194 368 972 756
9 browser-use/browser-use 10 107,542 11,821 131 334 340 252
10 farion1231/cc-switch 7.7 123,374 8,348 182 202 2,100 647

Multi-agent

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 lobehub/lobehub 79.5 81,076 15,742 820 350 655 416
2 TauricResearch/TradingAgents 51.1 95,282 18,416 14 20 328 163
3 FoundationAgents/MetaGPT 36.9 69,622 8,873 0 148 139 117
4 zhayujie/CowAgent 35.6 46,267 10,289 168 136 30 12
5 danny-avila/LibreChat 33.8 41,550 8,557 177 385 649 318
6 openai/openai-agents-python 31 28,336 4,426 219 325 50 28
7 Yeachan-Heo/oh-my-claudecode 22.5 38,246 3,442 83 137 2 0
8 wshobson/agents 18.5 38,429 4,113 22 79 11 6
9 OpenBMB/ChatDev 12.7 33,890 4,235 3 19 70 24
10 agentscope-ai/agentscope 11.6 28,481 3,281 60 90 321 96

Inference

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 ggml-org/llama.cpp 74.2 122,381 21,232 366 1,866 1,919 1
2 BerriAI/litellm 66.6 55,316 10,260 1,796 1,553 4,696 3
3 sgl-project/sglang 48.4 31,074 7,582 1,158 1,698 4,888 4
4 earendil-works/pi 46.4 82,092 10,148 514 260 90 22
5 microsoft/onnxruntime 19.8 21,252 4,091 200 962 1,474 659
6 k2-fsa/sherpa-onnx 13.2 13,920 1,603 59 225 617 54
7 GeeeekExplorer/nano-vllm 11.9 14,758 2,386 0 15 80 50
8 h2oai/h2ogpt 10.7 11,979 1,301 0 78 328 36
9 abetlen/llama-cpp-python 10.7 10,522 1,440 4 194 683 84
10 niedev/RTranslator 10 10,299 937 0 12 26 1

LLM library

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 huggingface/transformers 78.1 163,237 34,088 271 4,058 2,318 1
2 unslothai/unsloth 41.7 69,371 6,262 542 264 983 266
3 langfuse/langfuse 34.1 32,298 3,469 621 193 709 427
4 sickn33/antigravity-awesome-skills 31.7 44,287 6,515 339 310 0 0
5 router-for-me/CLIProxyAPI 27.6 45,927 7,130 337 230 373 305
6 fighting41love/funNLP 27 82,192 15,266 0 13 52 9
7 asgeirtj/system_prompts_leaks 24 61,899 10,115 90 25 48 32
8 labmlai/annotated_deep_learning_paper_implementations 19.6 67,256 6,749 0 42 34 6
9 ComposioHQ/awesome-claude-skills 18.9 71,580 8,054 2 29 1,151 1
10 huggingface/pytorch-image-models 13.2 37,034 5,183 19 197 63 20

Training framework

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 pytorch/pytorch 70.6 102,120 28,640 1,602 6,792 18,381 2
2 AUTOMATIC1111/stable-diffusion-webui 48.7 164,340 30,491 0 638 2,499 77
3 vllm-project/vllm 48.2 87,913 20,159 1,073 3,111 6,211 4
4 tensorflow/models 30.1 77,666 44,933 9 959 1,277 199
5 Comfy-Org/ComfyUI 28 123,169 14,549 155 332 4,384 422
6 rasbt/LLMs-from-scratch 24.7 100,334 15,432 4 68 2 0
7 keras-team/keras 20 64,216 19,746 75 1,545 208 74
8 ultralytics/ultralytics 19.1 60,116 11,498 429 416 152 107
9 ultralytics/yolov5 14.6 57,781 17,467 33 349 41 11
10 CorentinJ/Real-Time-Voice-Cloning 10.5 60,068 9,405 0 20 176 8

Serving

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 open-webui/open-webui 93.1 147,571 21,440 617 863 402 153
2 Mintplex-Labs/anything-llm 32.9 64,223 7,052 141 222 315 23
3 AlexsJones/llmfit 23.8 31,053 1,896 225 84 68 31
4 chatchat-space/Langchain-Chatchat 20.1 38,494 6,256 0 173 24 19
5 1Panel-dev/1Panel 19.9 36,401 3,277 86 126 264 7
6 janhq/jan 19.7 43,808 2,940 102 181 432 85
7 PDFMathTranslate/PDFMathTranslate 14.4 35,896 3,204 0 57 142 22
8 lm-sys/FastChat 11.5 39,508 4,786 0 246 1,036 144
9 lss233/kirara-ai 10.6 18,882 1,833 0 48 4 0
10 Zackriya-Solutions/meetily 7.6 27,897 2,880 0 12 321 114

Evaluation

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 confident-ai/deepeval 65 17,327 1,745 130 326 418 188
2 bitnami/charts 58 10,391 10,349 13 2,767 4 2
3 prometheus-community/helm-charts 48.4 6,164 5,379 85 1,792 200 94
4 open-compass/opencompass 27.8 7,256 819 57 183 357 73
5 helmfile/helmfile 23.1 5,169 356 33 392 23 10
6 komodorio/helm-dashboard 14.3 5,739 359 0 56 44 26
7 stackrox/kube-linter 13.6 3,492 270 18 94 88 11
8 omerbsezer/Fast-Kubernetes 11.8 3,583 1,332 0 5 4 3
9 helm/chartmuseum 9.6 3,835 407 0 88 118 27
10 roboll/helmfile 7.5 4,034 552 0 224 527 11

RAG / vector search

Rank Repository Score Stars Forks Commits (30d) Contributors Open issues Open PRs
1 milvus-io/milvus 85.6 45,460 4,153 247 364 1,210 318
2 langchain4j/langchain4j 45.7 12,758 2,413 137 453 831 226
3 chroma-core/chroma 41 28,921 2,421 79 190 763 431
4 qdrant/qdrant 38.6 33,716 2,546 2 173 665 187
5 simdjson/simdjson 32.9 24,104 1,264 15 188 138 15
6 Tencent/APIJSON 28.7 18,390 2,273 19 96 242 3
7 datawhalechina/all-in-rag 26.9 9,987 4,986 3 11 21 5
8 svcvit/Awesome-Dify-Workflow 14 10,723 1,077 0 2 24 6
9 gka/chroma.js 13.2 10,575 551 0 43 76 15
10 std-microblock/chromatic 10 8,359 392 0 1 3 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

For the week ending August 2, 2026, this Hugging Face hot list tracks 50 entries. By 24-hour growth, standouts include "Ternary-Bonsai-27B-gguf", "Kimi-K2.7-Code", "Kimi-K3", "s2-pro", "Qwen3.5-9B-The-Defiant-Fable-Uncensored-Here…". Organizations appearing most often near the top include unsloth, deepseek-ai, DavidAU, microsoft—a sign that releases, forks, and task pipelines remain fast-moving.

About 49 row(s) are flagged as newly listed in this snapshot, which usually means fresh weights, quant formats, or pipeline tags entering the cohort.

On tokens / hosting: Hacker News highlights “OpenAI's work on Git for large repositories”; Hacker News highlights “OpenAI Usage Reset 4th time in 7d”; Hacker News highlights “Why one of the best mathematicians is joining OpenAI”. 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).

Home