Discover the Best AI Resources

obsidian-skills

Provides a set of Agent Skills that let LLM agents read, edit, and manipulate Obsidian files (Markdown, Bases, JSON Canvas) and interact with Obsidian via the CLI. Implements the Agent Skills spec for use with Claude Code, Codex CLI, and OpenCode, enabling automated note workflows and RAG over an Obsidian vault.

Webnovel Writer

A Claude Code plugin for long-form serial fiction that keeps characters, timeline, and world rules consistent across hundreds of chapters. Facts are committed to a versioned state store, and review gates flag contradictions before each chapter.

Claude HUD

Displays live session status inside Claude Code — token-accurate context bar, usage, active tools, running agents, and todo progress in a compact statusline. Uses Claude Code's native statusline API and is configurable for terminal workflows.

ClawHub

Registry where OpenClaw agents publish, version, and vector-search text-based skills — each a SKILL.md plus supporting files. Adds a CLI with install pinning and moderation, plus a unified catalog that lists native code and bundle plugins beside skills.

LTX-2

Provides a DiT-based audio–video foundation model plus an official Python inference and LoRA trainer. Ships multiple production-ready pipelines (text/image/audio→video), checkpoints, and performance optimizations (FP8, distilled pipelines) for high-fidelity synchronized audio–video generation.

Planning with Files

Implements a Manus-style, file-backed planning workflow for AI agents using a three-file Markdown pattern (task_plan.md, findings.md, progress.md) to persist plans, findings and session logs—reducing context drift and enabling session recovery. Adds IDE/CLI hooks to re-read plans and verify completion.

Hister

Indexes full text of visited web pages and local files on a self‑hosted server so you can search your personal knowledge from a web UI, terminal, CLI, or an AI assistant. Runs without mandatory telemetry, offers a browser extension for automatic capture, and supports optional semantic search via a configurable embeddings endpoint.

DFlash: Block Diffusion for Flash Speculative Decoding

Enables parallel speculative decoding by using a lightweight block-diffusion draft model to produce multi-token drafts for faster, high-quality generation. Integrates with vLLM, SGLang and Transformers backends and ships draft models on Hugging Face.

9Router

Routes CLI coding-tool requests to many AI providers with built-in tool-output compression (saves ~20–40% tokens), real-time quota tracking, and automatic subscription→cheap→free fallback for zero-downtime coding.

Provides a Python API, CLI, and agent skill to programmatically access Google NotebookLM — exposing features the web UI omits (batch imports/exports, PPTX slides, mind‑map JSON) and integrating with LLM agents like Claude Code and Codex.

jcode

Terminal-first coding agent harness for multi-session LLM workflows, offering session memory, provider integrations, browser automation, and swarm collaboration. Tuned for low RAM and very fast startup to support many concurrent sessions.

PersonaPlex

Real‑time full‑duplex speech‑to‑speech system that controls conversational role via text prompts and voice timbre via audio-conditioned embeddings. Built on Moshi; optimized for low-latency, persona-consistent spoken interactions.