Trending repos

Trending research repos by velocity

Official code repositories from CS/AI/ML papers, ranked by 7-day GitHub star velocity — not total size. Framework giants are excluded and stars are only a credibility gate, so this surfaces the mid-tier work builders are adopting right now, not last year's canon. Every repo is the paper's own, backlink-verified implementation.

Updated Jun 9, 2026 · refreshed daily

1
huawei-csl/KVarNSpiking
13.1KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
382Last commit Jun 9, 2026 · active
+381/wk
2
pat-jj/harness-1Spiking
42.5Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
344Last commit Jun 8, 2026 · active
+339/wk
3
k2-fsa/OmniVoiceSpiking
48.6OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models
7.3kLast commit May 28, 2026 · active
+328/wk
4
unilabsim/UniLab
57.8A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms
685Last commit Jun 9, 2026 · active
+308/wk
5
AMAP-ML/SkillClawSpiking
49.8SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
1.8kLast commit Jun 2, 2026 · active
+216/wk
6
DeusData/codebase-memory-mcp
19.1Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP
3.1kLast commit Jun 9, 2026 · active
+196/wk
7
skyllwt/AutoSci↓ cooling
34.1AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle
1.2kLast commit Jun 6, 2026 · active
+157/wk↓ cooling
8
Xiangyue-Zhang/auto-deep-researcher-24x7↓ cooling
23.3Deep Researcher Agent: An Autonomous Framework for 24/7 Deep Learning Experimentation with Zero-Cost Monitoring
1.2kLast commit Jun 3, 2026 · active
+122/wk↓ cooling
9
starVLA/starVLA
59.9StarVLA-$α$: Reducing Complexity in Vision-Language-Action Systems
Show all 2 papers
- 59.9StarVLA-$α$: Reducing Complexity in Vision-Language-Action Systems
- 16.7StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
2.8kLast commit Jun 8, 2026 · active
+109/wk
10
visinf/INSID3Spiking
39.6INSID3: Training-Free In-Context Segmentation with DINOv3
448Last commit May 29, 2026 · active
+90/wk
11
XMUDeepLIT/MemGraphRAGSpiking
20.7MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation
87Last commit Jun 7, 2026 · active
+82/wk
12
shengshu-ai/minWM↓ cooling
45.9minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
565Last commit Jun 9, 2026 · active
+81/wk↓ cooling
13
Orchestra-Research/Agent-Native-Research-Artifact
55.4The Last Human-Written Paper: Agent-Native Research Artifacts
267Last commit Jun 8, 2026 · active
+65/wk
14
AMAPVOICE/PilotTTS↓ cooling
38.1PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis
156Last commit Jun 2, 2026 · active
+64/wk↓ cooling
15
zai-org/GLM-OCR↓ cooling
58.4GLM-OCR Technical Report
6.9kLast commit Apr 21, 2026
+62/wk↓ cooling
16
nv-tlabs/kimodo
81.2Kimodo: Scaling Controllable Human Motion Generation
2.5kLast commit Jun 8, 2026 · active
+59/wk
17
Mengqi-Lei/count-anything
32.2Count Anything
73Last commit Jun 4, 2026 · active
+53/wk
18
ant-research/Drift↓ cooling
40.4Reinforcement Learning from Denoising Feedback
128Last commit May 31, 2026 · active
+47/wk↓ cooling