Running on Zero
Agents
Featured
145
YuE2-3B Music Generator
🎵
Generate songs and covers from style prompts and lyrics.
Spaces of the week
21 Sep 2026
Running
Featured
82
MiniCPM5-2B WebGPU Pi
🥧
A coding agent running entirely in your browser
Running
Agents
Featured
96
StepAudio 3 Music Studio
🎵
Create songs, arrange vocals, and remix music with StepFun
Running on Zero
Agents
Featured
95
Marigold V2
🌼
Depth, surface normals, and albedo from a single image
Running on Zero
Agents
Featured
96
AuK
🎙
Unified speech generation and editing with AuK
Running
Featured
64
How to turn a game into an RL environment
🌍
From an idea to a trained 4B, with the dead ends left in
Running
Featured
79
A Hitchhiker's Guide to the 3D Ecosystem
💡
An interactive guide to 3D representations.
Running
Featured
37
Join the Agent Swarm
⚡
Collaborative, lossless enwik8 compression research
All running apps, trending first
24 24 Spaces
Running
1
AsyncTensorRLHF
⚡
Explore RLHF reward simulation and benchmark visualizations
Running
2
DeepSeekPapers
🧠
Deep Seek Papers Deep Dive
Running
Agents
80
Mistral OCR 3
🌆
Try out Mistral's latest OCR with pdfs and images
Build error
Agents
Picture Feature Extract
🐠
Extract and redact text from images and PDFs
Runtime error
Agents
Mistral OCR
🌆
Try out Mistral's latest OCR with pdfs and images
Runtime error
Agents
Mistral OCR 3
🌆
Try out Mistral's latest OCR with pdfs and images
Runtime error
Agents
Mistral OCR 3
🌆
Try out Mistral's latest OCR with pdfs and images
Runtime error
Agents
Mistral OCR 3
🌆
Try out Mistral's latest OCR with pdfs and images
Sleeping
Agents
DocuRAG - Document PDF RAG with OCR (No LangChain)
📄
Ask questions about PDFs and get cited answers
Paused
RL
1
WatchDog Environment
🐕
Interact with an AI environment via actions and view results
Paused
RL
WatchDog Environment
🐕
Control and monitor an AI environment with custom actions
Runtime error
Agents
Llmz
🏃
llmz
Sleeping
Agents
Mistral OCR 3
🌆
Try out Mistral's latest OCR with pdfs and images
Sleeping
RL
WatchDog Environment
🐕
Interact with a watchdog agentic environment
Sleeping
RL
WatchDog Environment
🐕
Interact with a watchdog environment via custom actions
Paused
Animetix Brain
🧠
Check service status via fallback API
Running
RL
ToolOrchestratorEnv Blog
💰
Cost-Aware Tool Orchestration via RL — AgentBeats Phase 2
Sleeping
Agents
Post Training Guide
📚
Explore a complete guide to post‑training large language models
Running
SMB Ad Manager
🎯
Simulate Meta Ads campaign management for RL agents
Runtime error
verifiable-rl-coder
🤖
GRPO-trained Qwen-1.5B coder with sandboxed test execution
Running
1
[DRAFT] Thought Injection & Recursive Cognitive Self-Correction
📝
View the draft paper on Thought Injection and Recursive Self‑Correction
Sleeping
Agents
Mistral OCR 3
🌆
Try out Mistral's latest OCR with pdfs and images
Sleeping
Agents
Mistral OCR 3
🌆
Try out Mistral's latest OCR with pdfs and images
Running
1
Repro - Does Your Reasoning Model Implicitly Know When to Stop Thinking?
🔬
ICML 2026 Paper 651 reproduction (arXiv 2602.08354)