DeepSeek Harness (dsh) is the open-source agent harness from DeepSeek AI. Here, an agent is defined as a combination of a model and a harness, with each capability being a swappable plugin. It's all about flexibility and customization!
Meet Muse Code, your new terminal coding companion, enhanced by Muse Spark 1.2. It features persistent background agents, repository-scale execution, and built-in verification to streamline your coding experience.
Route, secure, and manage traffic to any LLMβcloud or localβwith one unified platform. Monitor usage, optimize costs, and keep your AI products online.
The universal remote for AI coding agents. Run the Mac agent, pair your phone, and control Claude Code, Codex, OpenCode, or Aider from anywhere β live transcript, approve directly from your phone. LAN + end-to-end encrypted relay.
Turn any codebase into an interactive knowledge graph that you can explore, search, and learn from.
PMB provides Claude Code, Cursor, Codex, and Zed with genuine memory. It stores decisions, lessons, and facts in a single SQLite file right on your disk. Enjoy the benefits of offline access without the need for API keys or cloud services.
Kane CLI lets you outline your testing scenarios, then it manages running them in an actual browser. It checks each step and provides a clear pass or fail outcome. Thereβs no need for frameworks or selectors, and you can begin using it for free.
With our free AI Manga Translator, you can easily translate manga into any language. Just upload your manga pages and start translating without any usage limits or the need to sign up.
CtrlOps is a local-first desktop app for managing Linux servers with an AI-assisted terminal, real-time monitoring, and SSH access. No agents. Free to start.
The memory layer your coding agent should have had from day one. 95.2% retrieval R@5. 92% fewer tokens. 0 external databases. Works with every agent.
Let coding agents diagnose and fix React codebases with deterministic static analysis.
Aximo is your go-to autonomous AI testing agent that effortlessly uses natural language and visual recognition to perform tests just like a real user. It navigates applications from start to finish, validating outcomes across all platforms, whether it's web, mobile, or desktop.