Agenten stärken
Installation vom Herausgeber. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
Noch kein paketiertes Release in der Registry. Folgen Sie der README des Repositorys.
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
Starten

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:
⭐ If KinetAios saves you time, a Star is the loudest thank-you for a solo open-source project.
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.
Grab the latest release:
KinetAios-Setup-<version>.exe (NSIS installer, current: 4.0.3; install → launch → paste your API key).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:
provider: orcarouter # Settings → Presets → OrcaRouter (multi-model routing)
protocol: openai # OpenAI-compatible
base_url: https://api.orcarouter.ai/v1
api_key: sk-orca-... # create in the OrcaRouter console
model: orcarouter/auto # adaptive routing, or pin a vendor/model e.g. anthropic/claude-opus-4.8
Requires Node.js 18+ and a network connection (the better-sqlite3 native module needs compiling).
git clone https://github.com/phinn/KinetAios.git
cd KinetAios
npm install # includes postinstall: rebuild better-sqlite3 for Electron
npm run build
npm start
fast / standard / deep per query; the deep path builds tool calls into a dependency DAG and executes it in parallel — real speedups on multi-step tasks.claude -p --output-format stream-json, parses NDJSON, resumes with --resume.codex exec --json, parses JSONL, resumes.dsh CLI over OpenAI-compatible SSE with built-in OpenAI / Pi-AI providers, retries and token billing. Switchable per session like every other engine.shell (confirm before running; focus guard — if a command steals the foreground it's handed back automatically), read_file, write_file, edit_file (exact replace), grep, glob, web_fetch (SSRF guard + Jina Reader fallback), web_search (Bing → DuckDuckGo fallback), recall_memory, git_diff (read-only, no confirm), remember_fact / recall_fact (session anchors), memory_replace / memory_append (core memory blocks), dispatch_agent (read-only sub-agent with its own context), spawn_team / team_broadcast / team_send / team_close (multi-agent teams), video_gen (MiniMax H3 text-to-video), todo_write (shared task list, rendered live as checklist cards), and more.
screenshot (with hide_self — the agent's own window turns transparent during the shot, zero focus stealing), screenshot_window (capture any window by title — even occluded/background ones, no desktop switching).mouse_click / mouse_scroll / mouse_drag, keyboard_type / keyboard_key — coordinates are converted from the last screenshot's pixel space to the platform's action space (DPI / window-origin aware, with staleness expiry).open is mechanically rewritten to open -gj — the agent never steals your foreground.~/.claude.json, ~/.codex/config.toml, Claude Desktop). stdio transport, auto-reconnect after unexpected drops. The 🔌 button shows connected servers/tools.run_agent tool — remote machines can invoke your local full agent. Token auth (constant-time compare), 5-minute timeout, zombie-connection detection./ menu or the ⚡ button.KINET-CONTEXT.md.<webview> preview (HTML/SVG/PNG/JPG/PDF) + editor. Multi-tab. The address bar accepts file:// / http(s):// / localhost:<port>.git status (left) + git log (right). Click a changed file → side-by-side diff; click a commit → unified git show.KinetAios.md in the cwd (project-level rules, injected into the system prompt).Chain multiple stages, each with its own engine + prompt. The previous stage's output is prepended to the next stage's prompt. 2-minute per-stage timeout polling, abort on failure.
[REDACTED]).directHistory array (JSON editor).image_url or Anthropic base64 format.Ctrl/Cmd+K overlays a search across all sessions — matching prompt text, answer text, and tool output.
@path references to cwd files.KinetAios.md / AGENTS.md / CLAUDE.md — rule files in the cwd are auto-injected into the system prompt.Ctrl/Cmd+Alt+Space → quick panel.brand.json), encrypted API key storage (safeStorage: macOS Keychain / Windows DPAPI).The same 400k-row medical-device CRM cross-analysis (multi-sheet × hospital tier × time window, producing an interactive ECharts report) — four engines, identical prompt, zero human intervention:
The most valuable finding: 7.5% of API calls burned 63% of the budget. The root cause wasn't the model — it was tool design. The agent read the same large file 16 times sequentially, resending full history each pass. Switching to a streaming reader zeroed that cost.
Full report: methodology + per-dimension scores + step-by-step traces — includes all the gory details of our own engine's 3.5.
recall_memory full-text search + embedding semantic recall).KinetAios/ # repo root (the "Win" dir name is historical — it's the cross-platform repo now)
brand.json # branding config (product name etc., read at startup)
package.json
src/
shared/types.ts # types + applyEvent (shared by main/renderer, single source of truth)
shared/i18n.ts # four-language string table + t()
main/
main.ts # windows / tray / hotkey / IPC / shell-confirm bridge
TaskManager.ts # session management + engine dispatch + memory extraction
engines.ts # Engine interface + Direct/ClaudeCode/Codex + cross-platform CLI spawn
AgentLoop.ts # ReAct loop (Direct) + history compaction + auto-shrink
V3/ # Direct V3: intent router + fast/deep paths (deep = DAG parallel)
glm.ts # providers + OpenAI/Anthropic SSE streaming + retries
updater.ts # GitHub Releases update check
tools.ts # 30+ built-in tools + computer-use glue + focus guard
computer-use.ts # screenshot / mouse / keyboard (native APIs)
mcp.ts # MCP client (scan + stdio + reconnect)
mcp-server.ts # MCP server (HTTP+SSE, run_agent, token auth)
skills.ts # skills/commands/agents/plugin scanning
plugins.ts # plugin loader (SDK v3: tools/slash commands/hooks/panels)
store.ts # better-sqlite3 + FTS5
settings.ts # config (encrypted API key, lang, embedding)
preload/preload.ts # narrow contextBridge API
renderer/
index.html quick.html styles.css
app.ts # dashboard logic (chat, sidebar, tabs, context inspector)
quick.ts # quick panel logic
dashboard.ts # cost/token dashboard window
arena.ts # deep-analysis dashboard
memory-graph.ts # memory graph SVG visualization
town.ts # Town view (remote-node visualization)
files-pane.ts # file browsing + webview preview + editor
code-editor.ts # code editor (syntax highlighting)
file-drawer.ts # file drawer UI
nexus.ts # Nexus view
focus-manager.ts # focus / focus-trap management
highlight.ts # chat code-block syntax highlighting
markdown.ts # mini markdown renderer
plugins/ # 20 built-in plugins (SDK v3)
npm run build # tsc (main/preload/shared) + esbuild (renderer) + copy brand.json
npm run typecheck # typecheck both halves, no emit
npm start # launch (requires a prior build)
npm run dev # build + start
npm run dist # default target for the current platform
release\KinetAios Setup <ver>.exe (NSIS). Must be built on Windows (cross-building Windows + native modules from macOS is unreliable).npx electron-builder --mac (requires a Mac toolchain).better-sqlite3 against Electron's ABI automatically; asar: false avoids native-module-in-asar loading errors.build/icon.ico (256×256) on Windows, build/icon.icns on macOS.windows-latest runner, and dmgs on a Mac (native-module rebuild needs the target toolchain).KinetAios is part of the Kinet family:
Local-first multi-engine AI agent dashboard — Claude Code, Codex & built-in ReAct in one window. MCP support, skills auto-loading, long-term memory. No account, no relay.
Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
KinetAios läuft lokal über stdio.
Zuletzt geprüft: 2026-11-16. Local-first multi-engine AI agent dashboard — Claude Code, Codex & built-in ReAct in one window. MCP support, skills auto-loading, long-term memory. No account, no relay.