Find the signal.

DavidAU/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF

All models are evaluated against the BF16 base model.

Models · 28 likes

DavidAU/Qwen3.8-Flash-Next-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF

All models are evaluated against the BF16 base model.

Models · 22 likes

realrebelai/FLUX-3-Image-Klein_GGUFs

Models · 17 likes

affaan-m/ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Tools · 1 145 stars / day · 282 556 total stars

xerj-org/xerj

XERJ is the new way for AI to search data. Its autoindex capability activates agents to know your data without the token waste of grep (1974 tool). One command indexes code, docs, logs and PDFs for search, RAG, security audits and agent memory, using 40x fewer tokens than grep. It’s durable and can replace ElasticSearch saving you x10 infra costs.

Tools · 1 160 stars / day · 7 843 total stars

MadsLorentzen/ai-job-search

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

Tools · 1 365 stars / day · 50 512 total stars

anthropics/claude-plugins-official

Official, Anthropic-managed directory of high quality Claude Code Plugins.

Tools · 1 397 stars / day · 41 822 total stars

debpalash/VoiceStudio

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

Tools · 2 125 stars / day · 73 480 total stars

K-Dense-AI/scientific-agent-skills

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

Tools · 878 stars / day · 52 281 total stars

stablyai/orca

Orca is the place for working with a fleet of agents (e.g. Grok Bot, Claude Code). Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

Tools · 830 stars / day · 95 480 total stars

HKUDS/CLI-Anything

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub:

Tools · 574 stars / day · 54 091 total stars

anomalyco/opencode

The open source coding agent.

Tools · 438 stars / day · 215 423 total stars

ruvnet/ruflo

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

Tools · 420 stars / day · 76 101 total stars

replicate/flux-3-klein-image-lora

Generate images from Flux 3 Klein Image using your own LoRA

Models · 78 total runs

akitaonrails/ai-memory

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Tools · 178 stars / day · 9 945 total stars

anthropics/claude-code

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

Tools · 179 stars / day · 151 796 total stars

DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF

— HELP MENU & Interactive Session

Models · 155 likes

Comfy-Org/MOSS-Image

Repackaged model files for ComfyUI.

Models · 127 likes

turboderp/GLM-5.3-Flash-exl3

2.05 bits per weight 3.05 bits per weight 4.05 bits per weight

Models · 60 likes

DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF

1.

Models · 27 likes

h2oai/h2o-lightning-4b-gguf

GGUF files of H2O Lightning 4B for llama.

Models · 16 likes

Meet Kyutai REKI: The 2.4B VLA Model Bringing Efficient Memory to Robot Manipulation

Kyutai, with Inria and École des Ponts, has released REKI, a 2.4B vision-language-action model (VLA) for robot manipulation. The REKI vision-language-action model is pretrained only on public data. It also carries a cheap memory of its recent past. On three out-of-distribution benchmarks, only models about twice its size beat it. All weights are live on Hugging Face today. TL;DR Size: 2.4B parameters (2.2B Qwen3.5-2B VLM + 0.2B flow-matching action expert). Memory covers the last 3 frames, 1 s apart. Runs on: Benchmarked on 1 NVIDIA H100. 21.8 ms per action chunk, compiled, from 2 cameras at 256×256. Weights ship in BF16.

Model release

Replit makes OpenAI its default over Anthropic, CEO says

Replit, the AI coding platform that has become a favorite of startup founders and developers, is no longer working with Anthropic, the company’s CEO and co-founder Amjad Masad said Thursday while onstage at TechCrunch Disrupt. Masad said the decision was made for a number of different reasons, including cost. Replit announced a partnership with OpenAI in August, but there was never any indication that it was no longer partnering with Anthropic. “I think ChatGPT is better now,” Masad said, adding that the company uses an internal benchmark to help assess metrics like performance.

Industry

Anthropic says its workforce has become less junior and is spending more time in meetings

The composition of Anthropic’s workforce and the type of work getting done have changed significantly in the past year, according to a report that the AI company published on Friday. Anthropic argues that its own workplace trends could be indicators of “how AI will shift work organization, hiring, and labor demand across the economy,” especially since the company “has thoroughly molded its workflows around AI.” But even if other organizations never embrace AI as thoroughly or in the exact same way as Anthropic, the report offers an intriguing glimpse at how the company currently operates.

Industry

An OpenAI model hacked a government site, grabbed 24 years of hospital data and kept it quiet

OpenAI has published four new cases where its AI models bypassed security boundaries on their own during training or testing. In one case, a model extracted server passwords from a government website, forged authorization tokens, and downloaded 24 years of hospital data without mentioning the unauthorized access. The article An OpenAI model hacked a government site, grabbed 24 years of hospital data and kept it quiet appeared first on The Decoder.

Industry