
Your tireless AI operator. He runs the agent, you run the day.
Every Theo Agent is operated by Theo. He reads your flow, picks the right capability for each step, reasons about the data, and pauses for you when something important needs a human. He never sleeps, and he tells you exactly what he is about to do before he does it.
Five categories. Endless agents.
Every step in a Theo Agent is one of these five things. Mix and match to build the agent you want.
Triggers
How and when your agent starts.
Theo Processing
AI decisions, summarisation, and reasoning by Theo.
Connectors
Real services like Stripe, HubSpot, Slack, Google Sheets, and more.
Output
Real deliverables, not just messages.
Human Gates
Pause for review. Approve from your phone.
Four steps from sketch to running agent
Design
Build a flowchart in the OpenCharts Designer. Label each node in plain English so Theo understands what it should do.
Deploy
Click Run with Theo at the top of the canvas. A cinematic transition takes you to the live Execution Canvas.
Set up
Theo reads your labels and infers the right capability for each step. Click Set up my flow to auto-configure, or override manually.
Run
Each node lights up in real time: yellow while running, green when done, red if failed, blue if waiting on you.
Workflow when you know the path. Autonomous when you don't.
The same draft can be flipped between modes from the agent header, so you can try both during design and keep the one that fits.
Workflow agents
Deterministic step graphs.
You decide the shape of the work in the Designer and the agent follows that path every run. Best when the shape is known in advance, such as fetch, transform, post, notify.
- Drag-and-drop step graph in the Designer
- Same path every run, easy to audit
- Pause at approval gates by default
- Great for ops, CRM hygiene, and reporting
Autonomous agents
Goal-driven by Theo.
You state the goal, grant Theo a tool surface, and Theo composes the steps at runtime to reach the goal. Best when the shape of the work changes from run to run.
- Theo plans the steps live, inside your tool surface
- Credit-guarded with a daily autonomous budget
- Auto-pause after repeated skips or failures
- Great for research, briefing, and creative production
Every agent on one screen, watched by Theo.
The same cards you'll see inside the OpenCharts dashboard. Each one shows Theo's last seven runs, the next run countdown, and a switch to pause without leaving the screen.
Monday Industry Brief
Every Monday at 8am, Theo researches your industry and emails a structured brief.
Daily KPI Telegram
Every weekday at 9am, Theo pulls the daily numbers and pings Telegram with a one-glance summary.
Social Content Calendar
Weekly research plus a 14-day social calendar shipped to your Notes archive every Sunday night.
The Verified badge unlocks org-wide install and chat dispatch. Theo only shares verified agents with your teammates.
A focused canvas. Built only for the agent.
The Designer drops the global sidebar and dashboard chrome so the agent is the only thing on screen. Add steps from a drag-and-drop library, or ask the Theo Builder rail in plain English ("add a step that summarises last week's Stripe payments and posts to Slack") and watch the canvas update.
action
Hit a connector (Stripe, HubSpot, Slack, Sheets, and friends).
theo_action
Ask Theo to decide, summarise, classify, or generate something.
theo_autonomous
Hand Theo a goal and a tool surface. Theo plans the substeps.
path
Branch into parallel lanes that rejoin after they finish.
approval
Pause for a human Accept or Reject over Telegram.
delay / loop / call_agent
Wait, repeat, or dispatch another Theo Agent inside this one.
Theo Agents DesignerDraftTheo Builder rail: "add a step that thanks the customer".
Real deliverables. Not just messages.
Most automation tools end with sending a Slack message. A Theo Agent ends with a finished artifact.
Run on demand. Run on a schedule. Run from anywhere.
Manual
Click Run on the Execution Canvas any time.
Schedule
Cron-based: every Monday at 8am, every 2 hours, you pick.
Webhook
Triggered by an external HTTP request, like a form submit or a Stripe event.
Event
Fired by an in-platform signal: a new task, a share accepted, an overdue reminder.
Telegram
Tell the Theo bot "Run my lead flow" from your phone.
Plug into the tools you already use
OAuth or API key. Connect once, use across every Theo Agent. Each connector ships with a setup wizard and explicit read and write scopes.
Plus custom HTTP, GraphQL, and your own API keys. New connectors ship regularly.
Pause for review. Approve from your phone.
Drop a Wait for Approval node anywhere in your agent. When Theo reaches it, the node turns blue, the run pauses, and you get a Telegram notification with a one-tap Accept or Reject. No dashboard, no logging in.
Sensitive actions stay reviewable
Refunds, sends, deletes never auto-fire.
Every approval is logged
Run history shows who approved what, when.
Theo summarises the data first
See the why before you tap Accept.
Theo
Theo Agent approval needed
Waiting for approval
Send onboarding deck to Acme Corp?
Lead score 87/100. Plan: Unlimited. MRR: $249. Theo prepared a 12-slide welcome deck with their brand colors.
Monday Industry Brief
Every Monday at 8am, Theo researches your industry and emails a structured brief.
Built one Theo Agent? Share it with the team.
Set an agent's visibility to Org and it shows up in your team's Library. Teammates install a personal fork in one click. Re-installs are idempotent, so nobody ends up with three copies. An admin can flip the Verified badge to unlock chat dispatch and cross-agent calls.
Verified badge
Only verified agents are routable from chat or installable from the Library.
Sub-agent dispatch
A Theo Agent can call another Theo Agent in the same org with the call_agent step.
Same-org only by design
Cross-org dispatch is refused. The runtime tracks every ancestor on the call stack.
Chat-side dispatch
Mention @your-agent in Theo Chat and Theo routes the request to it.
{
"version": "1.0",
"trigger": {
"type": "webhook"
},
"steps": [
{ "id": "n1", "skill": "theo_decide" },
{ "id": "n2", "skill": "send_email" }
]
}Your Theo Agents aren't locked in.
Every Theo Agent exports as a portable theo-agent.json file containing the graph, skill bindings, trigger config, and metadata. The format is open. Any compatible runtime can run these files.
Export anywhere
Download the full agent definition with one click.
Import and remix
Load shared agents or your own backups.
Version-control friendly
Plain JSON. Diff it in Git like any other code.
Visual. AI-native. Honest.
Other agent platforms are powerful, but they hide behind JSON configs, one-step zaps, or proprietary builders. We made Theo Agents look like the diagrams you already draw.
We're honest where the competition wins. Zapier's 5,000+ connector catalog is bigger than ours today, and n8n is excellent if you want self-hosted node-based automation. Theo Agents win on visual flowchart-native authoring, AI at every step, real deliverables, and built-in human approval.
What you can ship in an afternoon
Daily lead summary
Every morning at 8am, Theo summarises new leads and pings you with a one-line briefing.
New paid customer onboarding
When Stripe fires a webhook, Theo scores the lead, asks for approval, then ships a branded welcome deck and email.
Weekly content calendar
Every Monday, Theo researches your niche, builds an interactive content calendar, and drops it in your Telegram.
Quarterly strategy report
Once a quarter, Theo runs a deep research pass and produces a downloadable strategy report for the leadership team.
Topic to flashcards for the team
Drop a topic into the agent, and Theo researches it, generates a flashcard set, and pushes it to the team's Notes archive.
Inbound support triage
Every new Typeform submission flows into Theo, who tags the priority, creates a Linear issue, and replies with an ETA.
Every step tells you exactly what it's doing
Build it. Borrow it. Or hand it to Theo.
Pick the path that fits how you like to work. Switch later, no rebuild required.

Start from a template
12 curated starters, from Monday Industry Brief to Daily KPI Telegram.
Browse templates
Install from your Library
Pick a verified agent your team has already shipped and install your own copy.
Open the LibraryFrequently asked questions
What is a Theo Agent?
A Theo Agent is a persistent AI worker that lives inside OpenCharts. You sketch the flow as a chain of steps, tell Theo what you want each step to do, and Theo runs the agent on a trigger of your choice. Every node maps to a real capability such as analysing data, scoring a lead, sending an email, or generating a presentation, and Theo executes them in order while passing data between steps in real time.
How is this different from Google Vertex AI Agent Builder, Zapier, or n8n?
Most agent and automation tools force you to write JSON, drag steps in a sidebar, or learn a custom DSL. Theo Agents is the only one where you literally draw the agent like a flowchart and click Run with Theo. It is AI-native (every node can use Theo), it ships with human approval gates by default, and it produces real deliverables such as presentations, podcasts, videos, research reports, and code apps. Flows export as portable JSON so they aren't locked in.
What can a Theo Agent do?
A Theo Agent can be triggered manually, on a schedule, by a webhook, or by a Telegram message. Once running it can call Theo for AI decisions or summaries, hit external services through connectors (Stripe, HubSpot, Slack, Google Sheets, Discord, Airtable, Calendly, Apollo, Typeform, Monday, and more), pause for human approval over Telegram, and produce deliverables: emails, slide decks, notes, podcasts, videos, code projects, content calendars, flashcards, and research documents.
What is the difference between Workflow and Autonomous mode?
Workflow agents are deterministic step-by-step pipelines. You decide the shape of the work in the Designer and the agent follows that path every run. Autonomous agents are goal-driven. You state the goal, grant Theo a tool surface (the Designer, the connectors you trust, and the deliverables you want), and Theo composes the steps at runtime to reach the goal. A single agent can be switched between the two modes from the header toggle, so the same draft is reusable in both styles during design.
Do I need to code?
No. You design the agent visually in the OpenCharts Designer, label each step in plain English, and click Run with Theo. Theo reads the labels, infers the right skill for each step, and auto-configures the flow. You can override any step manually if you want full control, or you can ask the Theo Builder rail in natural language and watch it update the canvas.
How does Theo decide which step to pick?
When you click Set up my flow, Theo reads your node labels, the surrounding context, and the data shape of the previous step. It then picks the best capability from the canonical step library (action, theo_action, theo_autonomous, path, approval, delay, loop, call_agent). You can always override the inferred choice from the inline configuration form. Theo also surfaces its reasoning per step so you can see why a particular capability was selected.
How do human approval gates work?
Drop a Wait for Approval node anywhere in the flow. When execution reaches it, the node turns blue and you receive a Telegram notification with the data summary and Accept or Reject buttons. If you approve, the flow continues. If you reject, the run stops cleanly. Every approval is recorded in the run log along with the user who tapped Accept.
Can I run the same flow on a schedule?
Yes. Triggers include Manual (click Run), Schedule (cron-style: every Monday at 8am, every 2 hours, etc.), Webhook (an external HTTP request), Event (an in-platform signal such as a Stripe payment or a new task), and Telegram (say "Run my lead flow" to the bot). You can change a flow's trigger from the Setup panel without rebuilding the graph.
Can I share Theo Agents with my team?
Yes. Set an agent's visibility to Org from the Designer header and it appears in your team's Library. Teammates can install a private fork with one click and re-installs are idempotent (you always get back the same fork instead of duplicates). An admin can also flip the Verified badge on a shared agent, which unlocks chat-side dispatch ("@daily-standup-brief, run now") and cross-agent calls from other Theo Agents in the same org.
What is the Library and how does verification work?
The Library is the org-wide catalogue of shared and verified Theo Agents. Owners and org admins flip the Verified badge from the Designer header. Verification unlocks two things at once: org-wide Library install and cross-user chat dispatch. Until an admin verifies an agent, it can only be dispatched by its owner. Cross-org dispatch is always refused.
Are Theo Agents free?
Yes. Designing agents is free on every plan, and you get AI credits each month to run them. Heavier or higher-frequency runs use credits from your plan, and Theo Agents share the same credit balance as everything else Theo does. There is no separate agent subscription.
Can I export and re-use my Theo Agents?
Yes. Every Theo Agent can be exported as a portable JSON file containing the graph, skill bindings, trigger config, and execution metadata. The format is open, so any compatible runtime can run these files. Import them later, share them with a teammate, or version-control them in Git.
How do I see what a Theo Agent is doing?
While a flow runs, every node lights up with its current state: yellow while running, green when done, red if failed, blue if waiting for approval. The Execution Log shows a timeline of every step with duration, credits used, and Theo's reasoning. You can click any node after the run to inspect its inputs and outputs, and the Insights tab aggregates run health, average latency, and feedback across the last 100 runs.
Ready to try Theo Agents?
Free to start, no credit card needed, and your whole team can join.