phinn/KinetAios

English | 简体中文
> 🌐 **Website → https://phinn.github.io/KinetAios/**
*Real session: parallel conversations across projects, engine badge per session (Direct / Claude Code / Codex), file & Git & rules tabs, token-cost accounting per turn.*
A **local-first AI agent dashboard** for **Windows 11 and macOS — both first-class platforms** (the "Win" folder name is historical; the repo is phinn/KinetAios). Platform differences (cmd.exe vs /bin/sh, hotkey, tray) are routed at runtime; features are aligned on both sides. Run multiple agent sessions concurrently with streaming answers, shell/file/search/MCP tools, SQLite history with long-term memory, a global hotkey, and a per-session model. **No account, no relay server — your own LLM API key is the only credential.**
**The 30-second version:**
- 🔀 **Four engines, one window** — Direct (in-house ReAct) + Claude Code + Codex + DeepSeek Harness; switch per session, hand off context via Pipeline
- 🧠 **Long-term memory on local SQLite** — auto-extracted facts shared across all engines, survives restarts
- 🔒 **Local-first, no account** — your API key is the only credential; nothing goes through a relay
- 🛠 **30+ built-in tools + MCP client/server + plugins** — shell, files, web, screenshots, computer use out of the box
- ⌨️ **Global-hotkey quick panel** — Spotlight for AI agents, summon from anywhere
- 📊 **Benchmarked on a real 400k-row business task** — in-house engine **9.2** vs Claude Code **7.0** (full report)
- 🖥 **Windows 11 & macOS — both first-class**
> ⭐ If KinetAios saves you time, **a Star is the loudest thank-you** for a solo open-source project.
---
Why KinetAios?
Most AI clients lock you into one provider, drop context when you switch engines, and route your conversations through a relay. KinetAios runs **four engines in one window**, keeps long-term memory across all of them, and **never asks for an account**.
| | KinetAios | Claude Desktop | Cherry Studio | Cursor | Codex Desktop |
|---|---|---|---|---|---|
| Four engines (Direct V1/V2/V3 + Claude Code + Codex + DeepSeek Harness) | ✅ | — | — | — | — |
| Local SQLite + automatic long-term memory | ✅ | — | — | — | — |
| Cross-engine memory (one user profile shared by all engines) | ✅ | — | — | — | — |
| Multiple parallel sessions | ✅ | — | ✅ | — | ✅ |
| Global hotkey + quick panel | ✅ | — | — | — | — |
| Auto-scan MCP / Skills / Agents | ✅ | ✅ | — | — | — |
| Project rules (AGENTS / CLAUDE / KINET) | ✅ | — | — | ✅ | ✅ |
| Built-in MCP Server (remote agent control) | ✅ | — | — | — | — |
| Plugin system (tools / panels / slash commands) | ✅ | — | — | — | — |
| Multimodal (image input + voice + screenshots) | ✅ | ✅ | — | — | — |
| Session branching + cross-engine Pipeline orchestration | ✅ | — | — | — | — |
| Local-first, no account | ✅ | ✅ | ✅ | — | — |
Install
Grab the latest release:
- **Windows** — Download KinetAios-Setup- .exe (NSIS installer, current: 4.0.0; install → launch → paste your API key)
- **macOS** — Download the latest .dmg (drag to Applications, same three steps)
> Unsigned builds → Windows SmartScreen / macOS Gatekeeper will warn; allow it manually.
**First launch**: click the ⚙ in the top right → paste your **API Key** (+ base URL / model, defaults to GLM/Zhipu) → hit **Test Connection**, then send your first task.
> 🐋 **One key for every model?** Pick the **OrcaRouter** preset — an OpenAI-compatible gateway with 200+ models, adaptive routing, zero markup. Sign up with this link to support the project (5% referral credit).
Built-in OrcaRouter preset:
From source
Requires **Node.js 18+** and a network connection (the better-sqlite3 native module needs compiling).
---
Highlights
Four engines, switchable per session
- **Direct V1 (Kaios)** — built-in ReAct loop with a dual-protocol provider (OpenAI-compatible & Anthropic, both directions of SSE streaming), tool-level concurrency, sub-agents, context compaction and retries.
- **Direct V2** — next-gen ReAct on a Plan-Execute-Verify-Judge architecture, streaming tool calls, step-by-step task lists rendered live in the chat as checklist cards, plus a unified execution loop shared by plan and replan (retry / verification / checkpointing / compaction behave identically on both paths).