Desktop-first agent client that composes LLM-driven agents into document-centric, multi-session workflows; it wires APIs, MCPs and local tools into shareable sessions, supports multiple LLM providers, and exposes a headless server + CLI for automation.
A curated, security-first registry of verified, tested skills you can install into AI coding agents. Each skill is human-curated, scanned (Snyk/static analysis), and integrity-locked; delivered via a CLI and optional MCP server to multiple agents (Claude Code, Cursor, Copilot, etc.).
Desktop + CLI agent-native client for managing multi-session conversations, connecting to multiple LLM providers and external data sources, and creating shareable agent skills and automations without editing code.
Exposes the Claude Code SDK as a local Anthropic/OpenAI-compatible HTTP proxy so third-party tools can use Claude Max. Adds session management, streaming, multi-profile routing and OpenAI-format endpoints while respecting Anthropic's SDK auth, rate limits and prompt caching.
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.
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.
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.
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.
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.
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.
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.