okamiops.com/produtos/

The software we use with clients, open for you to use too.

A coding agent, mission control for agents, AppSec maturity, AI quotas in your pocket and email on the Mac. It runs on your machine, doesn't send data out and doesn't lock you to a model vendor. The code that runs in our own projects is the same code that's on GitHub.

  • License
    7open-source · 1 App Store
  • Data
    localno telemetry
  • Platforms
    terminalweb · macOS · iOS
  • Organization
    github.com/OkamiOps
§01Featured · coding agentgithub.com/OkamiOps

The coding agent that does what it says.

Capability parity across LLMs, self-improvement through skills, persona and memory, and mandatory adherence to your design system. In the terminal, on Telegram, wherever you want.

Terminal

Okami Agent

License
MIT
Language
Python 3.11+ (uv)
Version
v0.15-beta (public beta)
Tests
4.081 passando
MITPython 3.11+v0.15-beta4.081 testesTUI · Telegram
okami-agent · session live
$ okami "refactor the auth module following the design system"
skills loaded: refactor · design-system · tests
model: claude-opus-4.8 → fallback gpt-5.6-luna
persona: senior engineer · memory: 3 relevant decisions
12 files changed · DS tokens respected
4,081 tests passing · diff ready for review
$ 

The products that carry the consulting

Eight published: seven open-source on GitHub and one iPhone app.

sort: featured
Terminal

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.

View productokamiagent.com
Web

Okami Monitor

Mission control for multi-agent environments: usage and cost per period, sessions, Kanban, logs, API keys and external runtime connections — in one cockpit.

View productos.okamiops.com
Desktop

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.

View productcode.okamiops.com
Web

Okami Maturity

OWASP SAMM v2 maturity assessment: 5 functions, 15 practices, 90 questions — with scorecard, radar, prioritized roadmap and a board-ready PDF report.

View productmaturity.okamiops.com
iOS · App Store

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.

View productApp Store
Local

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.

View productsentinel.okamiops.com
macOS

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.

View productGitHub releases
macOS

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.

View productuni.okamiops.com
§03In consultingAll services and plans

You don't pay for the software. You pay for whoever puts it to work.

The code that runs in our own projects is the same code that's on GitHub.

Seven public repositories with releases and open issues. If something doesn't work for you, we want to know.

github.com/OkamiOps
01

Okami Maturity in discovery

SAMM scorecard and a prioritized roadmap before you invest in execution.

02

Agent and Sentinel in the pipeline

Agents bound to the design system and governed security scans from the first commit.

03

Monitor in the retainer

Agent usage, cost and sessions visible every month, with an executive report.

§04Contact

Talk to the people who deliver

No SDR, no drawn-out qualification: whoever answers is whoever delivers.

Talk to usSee plansTechnical reply within 24 business hours.