AI BriefingAI Briefing
KO
Sign in

Trending AI open source

  • AllFeed, trending, and board
  • FeedLatest news
  • TrendingOpen source and releases
  • BoardBlogs and showcases
  • TagsBrowse by topic

AI Briefing

Privacy PolicyTerms of ServiceContactAboutSourcesRSSSupport us
  • Home
  • Trending
  • Tags
  • Settings
All
GitHub
HuggingFace
Releases
transformers
codex
langchain-core
ollama
vllm
pytorch
74 items

caveman: Local proxy that reduces input tokens by 33.2%

·2026.08.20 19:00

agent-skills: 25 Skills Injecting Senior Engineer Workflows into AI Agents

·2026.08.30 05:00

taste-skill: How to Validate Boring AI-Generated Landing Pages in a Real Browser

·2026.09.03 20:00

skills: Grilling sessions to reduce agent chatter and align requirements

·2026.08.20 09:00

ZONOS3-Mini: Real-time voice cloning in 43 languages with 100M parameters

·2026.11.12 09:00

uptime-kuma: Monitoring at 20-second intervals, 90 notification channels

·2026.11.13 22:00

claude-quickstarts: 15 Reference Implementations: From Agents to Automation with the Claude API

·2026.11.08 21:00

kiri: 2.5ms container startup, 80x faster than Docker Desktop

·2026.11.15 01:00

Inkling-2-Small: 383B MoE multimodal model deployed at 8-bit precision

·2026.11.13 19:00

sure: Personal finance app with $1 million in development costs is now open source

·2026.11.10 21:00

knowledge-work-plugins: Claude Plugins for 11 Job Roles, Data Integration via MCP

·2026.09.16 23:00

graphify: Graph-based exploration that understands code structure without LLMs

·2026.08.31 20:00

Qwen3.8-27B-GGUF: Run Qwen3.8-27B Locally Without Cloud APIs

·2026.08.20 09:00

dsh-Go: Run DeepSeek Harness Locally on Android 8.0

·2026.10.30 21:00

flux-3-image-klein-comfy: Control image layout with coordinate boxes in prompts

·2026.10.16 06:00

cleanyourtv: Turn Android TV into Apple TV over Wi-Fi

·2026.10.19 21:00

Edge0-145B-NVFP4: 145B MoE model, running locally with NVFP4 quantization

·2026.11.14 16:00

Qwen3.8-27B-DSpine-b16: DSpine Draft Model Boosts Qwen3.8-27B Inference Speed by 3.8x

·2026.11.10 06:00

Qwen-Image-2.1-Uncensored-Omni-Quantized: Running Qwen-Image 2.1 on 4GB VRAM

·2026.11.14 13:00

superpowers: Coding Agent: Starts with Questions Before Writing Code

·2026.08.20 09:00
  • Previous
  • 1
  • 2
  • 3
  • 4
  • Next
  • Previous
  • 1
  • 2
  • 3
  • 4
  • Next

Editor's picks

#1
1 / 2
  1. 1Meta's 8 Years of Expertise: A Design System Built for AI AgentsGitHub2026.11.07 21:49
  2. 2A Rust engine that analyzes and recreates websites and games with AIGitHub2026.11.02 12:42
  3. 3AI Agent Framework for Creating Videos with HTMLGitHub2026.09.07 11:29
  4. 4Track from text to video across 270,000 conceptsHuggingFace2026.10.11 21:11
  5. 5DeepSeek-V4.1-Flash-1017: Enhanced Agent Performance with 1M Context and FP8 Quantization SupportHuggingFace2026.10.17 18:22