AIAIAny
  • Search
  • Collection
  • Category
  • Tag
  • Daily AI
AIAIAny

Discover the Best AI Resources

Curated essentials, no noise — just what matters

AIAIAny

Curated AI Resources for Everyone

[email protected]

Powered by airss.app

Product
  • Search
  • Collection
  • Category
  • Tag
Resources
  • Blog
Company
  • Privacy Policy
  • Terms of Service
  • Sitemap
Copyright © 2026 All Rights Reserved.

Contents

GitHub
MCP Server·2026
Icon for item

Flint: A Visualization Language for the AI Era (flint-chart)

Microsoft Research, IDEAS Lab, Renmin University of China

Lets AI agents produce expressive, polished charts from compact, human-editable semantic specs; the compiler infers layout, scales, and labels and emits Vega-Lite, ECharts, or Chart.js outputs, with an MCP server for agent-driven chart creation and rendering.

#mcp-server#mcp#agent-skills#javascript#typescript+5
GitHub
AI Coding·2026
Icon for item

i-have-adhd

Applies an "ADHD-friendly" output style to coding assistants so answers lead with the next action, present numbered steps, and avoid burying results. Packaged as a reusable skill/plugin for coding-agent workflows (examples: Claude Code, Codex) and guided by a 10-rule style set.

#plugin#agent-skills#skillkit#claude-code#codex+4
Hugging Face
AI Model·2026
Icon for item

NemoStation/Marlin-2B

NemoStation

Converts video inputs into text outputs — supports captioning, temporal grounding, and video-text-to-text queries using a Qwen-3.5-2B finetuned multimodal backbone. Suited for prototyping video understanding and caption-generation pipelines.

#huggingface#transformers#multimodal#video#ai-video+3
Hugging Face
AI Dataset·2026
Icon for item

i1-captions (zlab-princeton)

Boya Zeng, Tianze Luo +5·Princeton University

Provides the full caption corpus used to train and ablate the i1 text-to-image model: 12 curated subsets with multiple caption variants (long/short, VLM-generated, rendered text) to enable reproducible training and captioning experiments.

#huggingface#ai-image#image#multimodal#diffusers+1
Hugging Face
AI Model·2026
Icon for item

Nandi-Mini-600M-Early-Checkpoint

FrontiersMind

Early pretraining checkpoint of a compact multilingual causal LM aimed at low-memory deployment and Indic language support. Explores a Shared KV cache mode that can cut KV-cache memory by ~50% for inference; results are provisional (not a final, fully trained model).

#transformers#llm#multilingual#huggingface#nlp+3
GitHub
AI Agent·2026
Icon for item

reverse-skill

Routes code-based AI agents through repeatable reverse-engineering and pentesting workflows and orchestrates local and remote tools (jadx, Frida, IDA, BurpSuite) so agents can triage APKs, binaries, JS, firmware, and CTFs without guessing the toolchain. Includes master routing rules, tool-index detection, MCP integration, and a field-journal for reusable lessons.

#agent-skills#mcp#mcp-server#mcp-client#ai-agent+12
GitHub
AI Agent·2026
Icon for item

TradingAgents-Astock

Simon Lin

An A‑share–specialized fork of TradingAgents that runs a seven‑analyst multi‑agent investment research pipeline for China stocks, integrating free A‑share data connectors and LLM providers. Key features: mootdx/東財 data integrations, A‑share trading rules (T+1, limits), Streamlit UI, and Apache‑2.0 license.

#finance#LLM#ai-agent#agent-skills#python+3
Hugging Face
AI Dataset·2026
Icon for item

CUA-Gym

xlangai, CUA-Gym Team

Pairs natural-language instructions with executable setup artifacts and Python reward functions to create verifiable computer-use agent tasks. Provides a Parquet task table for fast filtering plus a compressed archive of runnable task bundles; several web task endpoints are placeholders that require a local CUA-Gym-Hub deployment.

#huggingface#RL#agent-skills#pandas#python+1
GitHub
AI Infra·2026
Icon for item

Agent Substrate

Runs a Kubernetes-native runtime that multiplexes many stateful agent-like actors onto a small pool of sandboxed worker pods via full-state snapshots and pre-warmed workers, enabling sub-second suspend/resume and 30x+ oversubscription.

#kubernetes#ai-agent#ai-deploy#mLOps#go+5
Hugging Face
AI Dataset·2026
Icon for item

Claude Mythos Distilled 25K

WithinUsAI

25,000 chat-formatted synthetic SFT examples distilled to emulate the reasoning style and agentic behavior of Anthropic's Claude Mythos, focused on cybersecurity, advanced coding, mathematical reasoning, and long-horizon agent tasks. Includes metadata for targeted curriculum fine-tuning and is Apache-2.0 licensed.

#huggingface#claude#anthropic#security#llm+4
Hugging Face
AI Dataset·2026
Icon for item

L2P: Unlocking Latent Potential for Pixel Generation

zhen-nan

Transfers pretrained latent diffusion priors into pixel space to train pixel-space diffusion models using only synthetic images from LDMs. Trains shallow pixel layers while freezing most LDM internals, reducing data and compute needs and enabling native 4K generation without a VAE.

#huggingface#ai-image#image#foundation-model#paper+1
Hugging Face
AI Model·2026
Icon for item

Ring-2.6-1T

inclusionAI

A trillion-parameter reasoning model aimed at long-horizon, multi-step agent workflows and tool collaboration. Offers adjustable Reasoning Effort modes (high, xhigh), async RL training (IcePop), and very long context (128K→256K) for complex production scenarios.

#foundation-model#transformers#llm#huggingface#ai-agent+4
  • Previous
  • 1
  • More pages
  • 137
  • 138
  • 139
  • More pages
  • 259
  • Next