Shogo
Tap a star to rate
What it is
Shogo is an open-source AI agent platform for founders and small teams who would rather describe what they need than assemble it. The home page puts it as "Shogo replaces your AI assistant, your coding agent, your app builder, and your automation stack. One open-source platform." It lines itself up against ChatGPT, Claude Code, Lovable, and OpenClaw, and the tagline for the build experience is "Type a sentence. Your company builds itself."
For the chatbot-builder reader, the distinction the company draws is useful. Its no-code guide says an AI agent "is not a chatbot": a chatbot responds when you talk to it, while an agent runs in the background, takes actions on your behalf, and produces outputs that do things. The site does not say where the company is based.
What you build and how
You build in Shogo Studio, the web workspace, by writing a prompt. In the company's guide, you click "New Agent" and describe the job "the same way you'd explain it to a smart intern". The example is a GitHub triage agent: every morning at 9am, check your repositories for pull requests open more than 24 hours without a review, and list them by repo with the title, author, and hours open. The guide says you can then pause, edit, or delete the agent at any time. Scheduled agents appear in a dashboard with their last run time and next scheduled run, and every agent has a run log showing what it did, what it read, and what it sent.
That is the agent side. The home page describes 3 more surfaces, which is how Shogo ends up in several of our categories.
Code is an agent-native IDE and CLI that "writes, refactors, and reviews code in your repo". Interfaces generate "full-stack interfaces, screens, data, auth" from a prompt, without leaving the conversation. Workflows are automations that connect "1000+ tools" and let your agents reshape the workflow as the work changes. The company contrasts this with SaaS tools, raw AI agents, and internal-tool builders such as Retool and Notion in a comparison table, where its own column is labeled "Self-evolving agents" and says that agents modify the software, with setup in "Minutes. Just talk."
The home page shows example builds rather than a template count. A sales example covers next actions, CRM sync, and weekly briefs. A support command center covers ticket triage, escalation paths, customer history, Slack alerts, and dashboards. An operations tracker has custom intake forms, approvals, dashboards, and automated handoffs. A customer onboarding portal has milestones, owner assignments, status updates, document collection, and automated follow-ups. A field service workspace covers job scheduling, technician notes, customer updates, inventory checks, and mobile-first workflows. An internal knowledge app offers searchable answers, source-linked policies, and role-specific guidance.
The founders guide on the blog lists smaller agents with a "Deploy this" button and a stated 5 minutes to set up. One checks a HubSpot pipeline each morning at 8am for deals with no activity in 7 days and posts a ranked list to a Slack channel. Another is a revenue agent that connects to Stripe, tracks MRR, ARR, new revenue, and churn, and builds a live dashboard you can share as a link. Others route inbound leads and watch Slack channels for keywords and send a daily digest. The no-code guide suggests follow-on agents: a Standup Generator after a GitHub triage agent, an Inbound Lead Qualifier after a pipeline monitor, an Invoice Manager after a revenue tracker, and a Meeting Prep agent that pulls Notion context before calls.
On logic, the guide says the vast majority of workflows are configured through natural language. Some power users write custom JavaScript inside agents for advanced transformations, which it calls entirely optional. For a service without a pre-built integration, Shogo supports custom webhooks and HTTP requests, which "does require slightly more configuration but still no traditional coding".
Where the finished thing runs: the home page lists iOS, Android, macOS, Windows, Web, Slack, Discord, Telegram, and an API. It says you can "talk to Shogo from chat on mobile" and open the company your agents built as a full workspace on desktop. Team collaboration is covered by team plans, which let multiple people share agent workspaces, collaborate on configurations, and see each other's running agents.
Evidence from the pages
Pricing is unusually specific, and comes from the company's own blog. The no-code guide says: "Free tier is $0.50 of usage/day (up to $3/month)", which it describes as enough to explore and run basic automations. "Paid plans start at $8/month (Basic), with Pro at $20/seat/month and Business at $40/seat/month for higher volume teams." The founders guide adds that each seat includes a matching pool of monthly AI usage, and recommends Pro or Business for running multiple agents in production. The guide also states that "every request bills at raw provider cost plus a flat 20% markup". Separately, the answer about using it for a whole team says team plans start at $149/month. The pages do not reconcile the per-seat prices with that team figure, so confirm on the pricing page before you budget. The home page says "Get started free" and "Free to start", and the guide says no credit card is needed.
On openness, the home page repeats "Open source" beside "One platform", links "View on GitHub", and offers a Shogo Studio link. It names no license, and the held text says nothing about self-hosting.
On integrations the home page claims "1000+ bridges to the tools your team still uses", and the guides name HubSpot, Slack, GitHub, Stripe, Notion, and Gmail-style email in their examples. No complete list appears in the held text.
On safety and support, the founders guide says each agent run has a log, and that issues are usually a missing permission or a prompt that needs to be more specific. It says an agent will not take certain write actions, such as modifying records, "unless you've explicitly configured that". The home page mentions human-in-the-loop on every escalation in an example. The held pages state no compliance certification, hosting region, or support channel beyond a Contact Sales link. The no-code guide is marked "Last reviewed: March 12, 2026".
Who it suits and who it does not
Shogo suits a founder or a small operations team that wants working automations quickly and is comfortable describing them in a sentence. The cost model fits experimentation: you can start on the free tier, then pay $8 a month for Basic if you outgrow it. The agent framing also helps a support or sales lead who has outgrown a scripted chatbot and wants something that acts, such as triaging tickets or posting a pipeline digest to Slack. Developers get an unusual extra: the same product includes an IDE and CLI for working in a repo, plus optional JavaScript in agents.
It is a weaker fit if you want a fixed, visual flow editor with branded chat widgets, because the pages describe prompts, not a canvas. Billing at provider cost plus 20% means a busy agent's bill depends on usage rather than a flat fee, and the free allowance is small. A regulated enterprise will find no certifications named in the held text and should ask before committing. And the claim that one platform replaces 4 categories of tools is the company's own, so test your most important workflow on the free tier first.