KinetAios is a local-first AI agent dashboard. Run multiple sessions in parallel, switch between a built-in ReAct agent, Claude Code and Codex, bring your own model (OpenAI-compatible / Anthropic), plug in any MCP server, and keep everything on your machine — SQLite history, long-term memory, no account required.

Hi Product Hunt! 👋 I built KinetAios because I kept juggling Claude Code, Codex and custom agents in separate terminals — losing context, history, and any clear view of cost. KinetAios puts them in **one local dashboard**: each session picks its own engine and model, MCP servers plug in automatically, every reply streams with token / $ totals, and there's a built-in agent with shell / grep / edit / memory tools when you don't want to leave the app. Everything stays on your machine — SQLite + FTS5 history, auto-extracted long-term memory, API key encrypted in the OS keychain. No account, no cloud. It's bring-your-own-everything: your API key, any OpenAI-compatible or Anthropic endpoint, and any MCP server you already use. Cross-platform (Windows 11 + macOS). Would love your feedback — **what agent or tool would you want wired in next?**

Local-first setup sounds great, especially the no-account and SQLite history bits. One thing that would really help me as a daily user is a diff view for the ReAct agent's tool calls, so I can quickly see exactly what files or commands it touched before it finishes a run. Right now I have to scroll through raw logs to reconstruct what happened. A side panel that shows the diff in real time and lets me approve or reject each step would make long sessions way less anxiety-inducing.

Love that the SQLite history and long-term memory stay fully local without forcing an account signup, makes parallel sessions actually feel private instead of performative.

Kinet Aios

One dashboard for Claude Code, Codex & a built-in agent

One dashboard for Claude Code, Codex & a built-in agent