AI Infra2026
Filters and compresses CLI command outputs before they reach an LLM, typically reducing token consumption by 60–90%. Single Rust binary with zero runtime dependencies, supports 100+ dev commands and integrates via a Bash hook into common AI coding tools.
AI Agent2026
Provides a manifest-driven marketplace of official Cursor plugins for developer workflows and agent integrations. Each plugin lives in its own directory with a .cursor-plugin manifest; examples include agent skills, PR review canvases, SDK integrations, CI/team tooling, and orchestration for parallel agent work.
MCP Client2026
Fetches multi-source content (webpages, YouTube, PDFs, WeChat, paywalled articles, podcasts), uploads it to Google NotebookLM, and generates outputs such as podcasts, PPTs, mind maps, or quizzes. Differentiators: automatic paywall-bypass pipeline, Claude Code Skill integration, and CLI + MCP components for WeChat and document scraping.
AI API2026
A transparent proxy that lets Claude Code CLI and the VSCode extension run without an Anthropic API key by routing requests to NVIDIA NIM, OpenRouter, LM Studio, or llama.cpp; supports per-model mapping, thinking-token parsing, and messaging integration.
AI Coding2026
Renders Mermaid source synchronously to themeable SVG or ASCII/Unicode art for UIs and terminals. Includes 15 built-in themes, Shiki theme extraction, mono mode and zero-DOM dependencies so diagrams render instantly in React, CLIs, or chat/agent UIs.
AI Client2026
Native Windows companion suite for OpenClaw that provides a system tray app, shared gateway libraries, and CLI utilities for quick chat, node control, diagnostics, and gateway pairing/observability.
AI Infra2026
Self-hosted coding assistant that runs frozen local LLMs with constraint-driven planning, energy-based verification, and self-verified repair to produce verified code. Emphasizes offline inference (no cloud), Docker/bare-metal deployment, and requires a 16GB+ GPU.
AI Agent2026
Self-hosted personal AI agent runtime that runs chats, tools, automations and long-term memory for persistent workflows. Small, readable core with a bundled WebUI, multi-chat integrations, an OpenAI-compatible API and a Python SDK for easy extension and deployment.
AI Agent2026
Provides a workflow layer for OpenAI Codex CLI to bootstrap stronger Codex sessions, add reusable agent roles/skills, and manage durable project state under .omx. Includes team runtime, canonical skills, and monitoring surfaces.
AI Agent2026
Automates decompiling APK/AAR/JAR and extracting HTTP APIs — Retrofit endpoints, OkHttp calls, hardcoded URLs, and auth patterns — so you can document and reproduce an app's network surface without source code. Integrates jadx/Vineflower/Fernflower and scripts for call-flow tracing.
AI Agent2026
Collection of small, composable agent skills that extend LLM-based agents for planning, development, and tooling — installable via npx and designed to turn higher-level tasks (PRDs, TDD, refactors, triage) into reproducible agent actions.
AI Infra2026
Runs untrusted code (LLM outputs, plugins, and third‑party tools) inside cross‑platform, policy‑driven sandboxes. Provides a unified JSON schema and a TypeScript SDK that sit on multiple containment backends (process sandboxes, LXC/Bubblewrap, microVMs). Early preview with known permissive profiles — not yet a security boundary.