One cockpit for operating your agents.
A dashboard for operating multi-agent environments: usage and cost per period, sessions, Kanban, logs, API keys and external runtime connections. Fourteen modules in one panel, with real state collected over SSH — not telemetry shipped to someone else's cloud.
- LicenseMIT
- StackReact 19 · Vite 7 · Phaser 4
- BackendNode · Express · SSH
- Modules14
Why a mission control is missing
The moment you run more than one agent, “what's running now, what did it cost and where did it fail?” has no single answer. It lives in open terminals, scattered logs and invoices that only arrive at month's end.
Monitor collects that state straight from the source over SSH — state.db, kanban.db, logs, sessions, skills and config files — and shows it in a single panel, without requiring you to export sensitive data to a SaaS.
What Okami Monitor does
14 modules in one panel
Overview, Usage, Kanban, Office, Pixel, Profiles, Sessions, Cron, Agents, Skills, Logs, Apps, CLIs and Docs — the command deck is real-time operation, not a historical report.
Tokens per period
Overview recalculates token totals for 1h, 24h, 7d and 30d from one consistent aggregation source — no numbers disagreeing between screens.
Own and external agents
Supports the main agent, OpenClaw, OpenHuman, Claude Code, Codex and external runtimes like OpenCode, AutoGen, CrewAI and LangGraph — without requiring everything to be from one family.
Connect without copy-pasting keys
“Connect agent” creates the API key, stores the secret in the server's encrypted vault and tries to apply .okami.env to the remote workspace. Manual key tools stay under advanced access.
Encrypted secrets, keys stored as hashes
The server/.data directory uses restricted permissions, SSH and API secrets are encrypted, and API keys are stored only as hashes — never in plain text.
Demo mode without a server
With no server or token, createDemoMissionControl() provides variable demo data and the full UI contract — you can evaluate the tool before connecting anything real.
Spec sheet and when to use it
- License
- MIT
- Stack
- React 19 · Vite 7 · Phaser 4
- Backend
- Node · Express · SSH
- Modules
- 14
- UI languages
- EN · PT-BR
- Storage
- server/.data (cifrado)
Running several agents at once
See what each runtime is doing now, what failed and how much it consumed — without opening five terminals and cross-reading logs by hand.
Controlling cost before the invoice
Tracking consumption per time window lets you act on day 3, instead of discovering on day 30 that an automation was looping.
Environment with sensitive data
Because state is collected over SSH and stored locally encrypted, you can operate without shipping logs or configuration to a third-party SaaS.
Okami Monitor FAQ
Do I need a server to try it?
No. There's a demo mode that provides variable data and the full interface contract with no server or token. For real data, the Node server collects over SSH.
Does it work with non-Okami agents?
Yes. Beyond the main agent, it supports Claude Code, Codex, OpenClaw, OpenHuman and external runtimes like OpenCode, AutoGen, CrewAI and LangGraph.
Where are the API keys stored?
API keys are stored only as hashes; SSH and API secrets are encrypted in the server/.data directory, which uses restricted permissions.
The products that carry the consulting
Okami Agent
Sovereign AI coding agent: capability parity across LLMs, self-improvement (skills, persona, memory) and mandatory design-system adherence. In the terminal, on Telegram, wherever you want.
OkamiCode
Local-first desktop cockpit for AI coding CLIs: folder-bound projects, native sessions per provider, chat, email, Kanban, usage/cost analytics and durable memory — without paying a second API bill.
Okami Maturity
OWASP SAMM v2 maturity assessment: 5 functions, 15 practices, 90 questions — with scorecard, radar, prioritized roadmap and a board-ready PDF report.
Okami Tally
An iPhone panel for your AI subscription quotas — Claude, Codex, Grok, Cursor, Minimax, MiMo and any service with a JSON endpoint. In the app, in widgets, on the Lock Screen and in the Dynamic Island. No backend, no telemetry.
Okami Sentinel
Local workbench for OpenAI Codex Security scans: run, inspect, compare up to six runs and gate changes with versioned guardrails — evidence, cost and context preserved in a local workspace.
OkTally
Every AI coding subscription quota in your macOS menu bar — Claude Code, Codex, Cursor, OpenRouter and more. Colored pins, a popover with the full picture and a notification before you hit the limit. All local, no telemetry.
OkamiUNI
Email and calendar together on the Mac. Unified inbox, macOS calendars and AI to summarize threads, draft replies and turn emails into appointments. Local data, your choice of AI provider.
Want Okami Monitor running in your context?
The product is open and you can run it yourself. Rolling it out in your environment, with design-system integration and a documented hand-off, is the consulting.