Dryade AI's profile on Product Hunt

About

Dryade is a local-first AI workspace and agent control plane. It lets individuals and organizations run AI agents on their own infrastructure, connect them to tools and business plugins, observe every execution, and keep full control over data, models, workflows, and audit trails. Where Claude Code is a harness around Claude, Dryade is the harness you run on your own hardware — around any model, any agent framework (CrewAI, LangChain, LangGraph, ADK, A2A, raw MCP), and any LLM provider (Ollama, vLLM, OpenAI, Anthropic, Google). Your conversations, your data, and your models never leave your infrastructure. No telemetry. No cloud dependency. No vendor lock-in.

Links

Twitter

Badges

Tastemaker

Gone streaking

Gone streaking 5

Maker History

DryadeRun, audit, and replay any AI agents, on any model, locally.
Jun 2026

🎉

Joined Product HuntApril 26th, 2026

Forums

•

4h ago

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

p/claude

•

5d ago

Claude Opus 4.8 just dropped — who’s tried it yet?

Claude Opus 4.8 just dropped who s tried it yet?

Anthropic released Claude Opus 4.8 yesterday, and from the announcement it looks like a solid upgrade over 4.7. Here s what stood out to me:

Better judgment on agentic tasks early testers say it catches its own mistakes, pushes back on bad plans, and flags uncertainties instead of bulldozing through
~4x less likely to let code flaws pass unremarked compared to Opus 4.7
Dynamic Workflows in Claude Code can now orchestrate hundreds of parallel subagents for codebase-scale migrations
Effort control you can now choose how hard the model thinks on each response (from fast/light to max effort)
Fast mode is 3x cheaper than it was for previous models
Same pricing as Opus 4.7: $5/M input, $25/M output

p/producthunt

•

1mo ago

Featured

🚨 Miss the YC deadline? There's still a shot

We've teamed up with @Y Combinator or to give builders one more chance.

Launch on Product Hunt this Friday, tag your post "YC application" @gustaf will personally review the top launches. One or more will walk away with a YC interview, even though the official deadline has passed.