Discover the Best AI Resources

ERNIE-Image

An open text-to-image generation model built on an 8B Diffusion Transformer that focuses on layout-sensitive, text-heavy, and instruction-following image synthesis. Notable for accurate text rendering, structured/compositional generation (posters, comics), and ability to run on consumer 24GB GPUs when paired with prompt enhancement.

claude-obsidian

Turns source documents into a linked, source-cited Obsidian wiki for grounded Q&A and research. Local-first vault workflows with content-addressed capture, provenance ledgers, BM25 retrieval, and Claude Code / Agent Skills integration.

transcribe.cpp

Runs local speech-to-text inference for a wide range of ASR model families using GGUF models on the ggml runtime. Supports Metal, Vulkan, and CUDA GPU backends plus a tinyBLAS-accelerated CPU path, prebuilt GGUFs on Hugging Face, and a quantization tool.

AI Berkshire

An AI-agent value-investing research framework for Claude Code/Codex that encodes Buffett/Munger/Duan Yongping/Lilu methodologies into multi-agent skills — enforces decisive buy/sell outputs, multi-source financial rigor, and reproducible research workflows for investment decision-making.

OCR-Synthetic-Multilingual-v1

Provides 12.26M synthetically generated multilingual OCR samples (en/ja/ko/ru/zh) with word/line/paragraph bounding boxes and reading-order graphs, packaged as HDF5 shards for training detection, recognition, and layout models; licensed CC BY 4.0.

Provides a CLI and skill suite that lets coding assistants scaffold, evaluate, and deploy ADK-based AI agents on Google Cloud. Integrates eval pipelines (generate/grade), deployment infra and CI/CD scaffolds, observability, and Gemini Enterprise publishing workflows.

LLM Wiki

Turns your documents into a persistent, interlinked personal wiki by incrementally reading sources, generating wiki pages, and keeping knowledge up to date. Features two-step chain-of-thought ingest, graph-based relevance with Louvain clustering, optional embedding search (LanceDB), and a local HTTP API for agent integration.

ParseBench

Benchmarks document-parsing systems on real-world enterprise PDFs and images—evaluates tables, charts, content faithfulness, semantic formatting, and visual grounding with human-verified, rule-level tests. Ships with ~2,000 pages, ~169K test rules, and an open evaluation framework for end-to-end pipeline scoring.

MiniMax-M2.7

Text-generation LLM designed for agentic workflows: supports multi-agent 'Agent Teams', skill stacks and model self-evolution. Ships on Hugging Face with deployment guides (vLLM, Transformers, SGLang) and is positioned for engineering, tool-calling and productivity use cases.

VoiceStudio

Local-first voice workflows for cloning, multi-engine TTS/ASR, video dubbing, dictation, transcription and audiobook production across 646 languages. Desktop app with a local OpenAI-compatible API, engine catalogue (TTS/ASR/LLM), and explicit opt-ins for remote features to keep audio and projects on-device.

OmniVoice Studio

Desktop app for local voice cloning, real-time dictation, and end-to-end video dubbing using zero-shot TTS across 600+ languages; features multi-engine TTS/ASR, speaker diarization, vocal isolation, batch pipelines, and invisible audio watermarking — all run fully offline.

HY-World 2.0

Generates and reconstructs navigable, editable 3D worlds from text, single images, multi-view photos, or video; outputs meshes and Gaussian Splatting assets and includes WorldMirror 2.0 for fast multi-view reconstruction. Suited for research and production pipelines that import assets into engines; requires substantial GPU resources.