Dryade - Run, audit, and replay any AI agents, on any model, locally.

Dryade puts AI agents to work for you. Researching, drafting, organizing, automating -- all running on your own machine, never someone else's cloud. Simple enough to start in a click, powerful enough for teams and serious industrial work. You stay in control of your data, and you can see exactly what every agent did. Dryade supports any agent framework, from markdown skills to ADK, CrewAI and LangChain on the model you choose. Then publish and set your price Your AI, Your hardware, Your data

👋 Maker here, Marc from Dryade. Two convictions led to Dryade: First, capable AI shouldn't cost you control of your data. Every time agents got genuinely useful, the price was handing your work to someone else's cloud — so we built the version that runs on your own machine instead. Agents that you can actually run in sealed bundle to audit, trace and replay every action. Second, the one I'm most excited about: building AI agents shouldn't be only for engineers! If you're great at something, law, finance, ops, research, content creation,...(whatever you know cold) Dryade lets you turn that expertise into an agent and sell it on the marketplace: 🧰 Build it from the MIT dryade-plugins-sdk. 💵 Set your price. 💰 Keep most of what you earn. A developer can do it, sure but so should a lawyer or an analyst, just as easily. That's what for everyone" actually means to me. 🌍 What it does is up top 👆 — what I'd love from you: • What expertise would you package into an agent and sell? • Does running it all on your own machine matter to you — or has cloud convenience already won? • Any feedback on the project Tear it apart, ask me anything — here all day. 🌳

Dryade - Run, audit, and replay any AI agents, on any model, locally.

Replies