Discover the Best AI Resources
Curated essentials, no noise — just what matters
Turns natural-language directions into end-to-end video editing workflows: LLM-powered planning, media search/organization, ASR rough-cut, and reusable Style Skills for consistent storytelling. Integrates agent Skills (OpenClaw/Claude Code) and optional AIGC transitions.
Provides L3 refined synthetic training data by converting high-quality web corpora into Q&A pairs and multi-style rewrites; supplies 400B+ English and 200B+ Chinese tokens for late-stage LLM pretraining and decay-phase training.
A TypeScript framework for building programmable, headless autonomous agents with a harness-centric runtime. Includes an SDK and CLI, virtual sandboxes (just-bash) with optional full container sandboxes, provider-agnostic model settings, and connectors for CI/Daytona/MCP—suited for deployable agent runtimes.
Generates high‑fidelity, expressive speech and environmental sounds from text. The MOSS‑TTS Family provides specialized models for long‑form TTS, multi‑speaker dialogue, voice design and realtime streaming, plus torch‑free inference paths (llama.cpp / ONNX) and Hugging Face releases.
Local integration layer that lets AI agents discover and securely call OpenAPI, MCP, GraphQL, or custom JavaScript functions. Centralizes a shared tool catalog, auth, and policy surface across multiple agents, with a local web UI and CLI for runtime control.
Provides a minimal web and desktop GUI for coding agents (Codex and Claude), letting you run LLM-driven code workflows through a lightweight interface. Emphasizes quick provider switching, desktop packaging, and an opinionated minimal UX; early-stage project, expect bugs.
Provides cross-platform semantic memory for AI coding agents by turning human-editable Markdown logs into a rebuildable Milvus “shadow” index and syncing memories across plugins (Claude Code, OpenClaw, OpenCode, Codex). Supports progressive retrieval, hybrid dense+BM25+RRF search, smart deduplication, live sync, and local ONNX embeddings.
Provides multi-task long-speech evaluation data for eight speech-understanding tasks (ASR, summarization, QA, translation, emotion, speaker counting, content separation, language detection). Includes 101,822 long audio files and ~204,881 annotated examples with JSONL task splits for easy loading.
Runs a local-first, full AI stack—LLM inference, chat UI, voice, agents, workflows, RAG, and image generation—deployable with one command. Auto-detects hardware and bootstraps a small model for instant chat while larger models download; supports Linux, Windows, macOS and optional cloud/hybrid modes.
A fast, local document parser that extracts spatial text with bounding boxes from PDFs and other formats. Bundles Tesseract OCR and supports HTTP OCR servers, multi-language bindings (Rust, Node, Python, WASM) and screenshot generation; best for lightweight local pipelines but less suited to very complex or heavily scanned documents.
A challenge repository for training the best language model that fits inside a 16,000,000‑byte (16MB) submission artifact; provides baseline training code, FineWeb bpb evaluation, a public leaderboard, and compute-grant instructions for short 8×H100 runs.
Autonomous white-box AI pentester for web apps and APIs. It reads your source code, maps the running app, then runs specialized agents that fire real proof-of-concept exploits for injection, XSS, SSRF, and auth flaws — reporting only what it can exploit.