Quick Start
Get up and running in under 2 minutes — from the web or the terminal.
Option A: Web App
- Sign up at /portal
- Create a project in the OS shell (New Project app)
- Chat with your agents from the Agent Chat app
Option B: CLI
# Install bun add -g pantheon-cli # Create account (or login if you have one) pantheon signup # Initialize your project cd your-project pantheon init # Start chatting pantheon chat arjun
Option C: Web + CLI Together
Use the web for visual management and the CLI for terminal workflows. Both share the same backend.
- Sign up on the web at /portal
- Go to Settings > API Keys and generate a key
- In your terminal:
pantheon login --api-key # Paste your bos_live_... key
API Keys
API keys let you authenticate without email/password. Use them for the CLI, CI pipelines, and programmatic access.
Generate from the Web
- Open the OS shell and launch Settings
- Go to API Keys in the sidebar
- Click "+ Create API Key", name it, and copy the key
- Keys start with
bos_live_and are shown only once
Generate from the CLI
# Must be logged in first (email/password or existing key) pantheon api-keys --create # List your keys pantheon api-keys # Revoke a key pantheon api-keys --revoke <key-id>
Use an API Key
# CLI login with API key pantheon login --api-key # Direct API usage (any HTTP client) curl -H "Authorization: Bearer bos_live_your_key_here" \ https://api.pantheonos.dev/api/v1/me
API keys have the same permissions as your account. Treat them like passwords — never commit them to git.
CLI Reference
The Pantheon CLI gives you full access to your AI team from the terminal.
bun add -g pantheon-cli
Authentication
pantheon signupCreate a new accountpantheon loginAuthenticate (email/password or API key)pantheon whoamiShow your profile, plan, providerProject Setup
pantheon initInitialize project — auto-detects stack, repo, scaffolds .pantheon/pantheon doctorCheck all systems — local config, server, connectorsAgent Interaction
pantheon chat [agent]Interactive chat (default: Krishna)pantheon ask <question>Quick one-shot questionpantheon briefMorning briefing from Yudhishthirpantheon oracleOracle Report from Sahadevpantheon review [file]Code review from ArjunMonitoring
pantheon statusSystem health, agent routing, approvalspantheon approvalsList and approve/reject pending actionspantheon auditRecent audit log entriespantheon violationsVishvarupa threshold violationspantheon memory [agent]View agent conversation historySettings
pantheon api-keysList, create, or revoke API keysSee the interactive CLI playground for demos of each command.
Agents
Every project gets 6 specialized AI agents, each mapped to a Pandava from the Mahabharata.
High-level strategy, decision-making, cross-agent coordination.
Operations, daily briefings, Gmail/Calendar (when connected).
CI/CD, deployments, GitHub PRs, infrastructure.
Code review, architecture, technical decisions.
Content, marketing strategy, campaigns.
Financials, metrics, Oracle Report, anomaly detection.
Plus Vishvarupa — the cosmic observer that monitors thresholds across all projects and speaks when the universe demands it.
Agents are fully sandboxed per project. Your agents in Project A have no access to Project B's data, memory, or tools.
Connectors
Pantheon connects to the tools your team already uses. Each connector provides read, write, and watch capabilities with governance baked in.
Available Connectors
| Service | Capabilities | Status |
|---|---|---|
| GitHub | Read files/PRs, create PRs, push code, CI status | Live |
| Google Workspace | Gmail read/send, Calendar read/create | Live |
| Slack | Post messages, read history, list channels | Live |
| Linear | List/create/update issues | Live |
| Stripe | MRR, revenue, churn, customer data | Live |
| Notion | Search, read pages, query databases, create pages | Live |
| Tavily | Web research with citations | Live |
Connecting a Service
- Go to Settings → Connectors in the OS shell
- Click Authorize on the service you want
- Complete the OAuth flow in the popup
- The connector is now active for your project
Write operations (sending emails, creating PRs, posting to Slack) always require approval through the governance gate.
Policies
Policies define what agents can and cannot do. They control which tools require approval and who can approve them.
Default Policy
By default, all read-only tools are auto-allowed and all write tools require human approval. This is the safest starting point.
Custom Policies (Team Plan)
On the Team plan, you can define role-based approval rules:
# policies.yaml
approval_rules:
# Production deploys need admin/owner approval
- tool: github_push_file
target: main
requires_role: [admin, owner]
# Staging deploys auto-approved for members
- tool: github_push_file
target: staging
requires_role: [member, admin, owner]
auto_approve: true
# High-value Stripe actions need owner only
- tool: stripe_*
amount_above: 1000
requires_role: [owner]How Policies Are Evaluated
- Agent requests a tool action
- Policy engine checks the tool against all rules
- If a rule matches: action is allowed, queued for approval, or denied based on the user's role
- If no rule matches: default policy applies (write tools → approval required)
Policies are version-controlled. Store them in your repo and deploy with your code — your security team will recognize the pattern.
Telegram
Connect a Telegram group to your project so agents can post updates, briefings, and alerts directly to your team.
Setup
- Create a Telegram group (or use an existing one)
- Add
@PantheonOSBotto the group - Type
/connect your-project-idin the group - The bot will confirm and your agents are now active
Bot Commands
/connect <project-id>Link this group to a project/disconnectUnlink the current project/statusShow system status and uptime/pingCheck if the bot is aliveTalking to Agents
Once connected, message any agent by name:
krishna what should we focus on this week? arjun review the auth module sahadev what's our runway?
What Agents Post
Morning briefingYudhishthir posts daily at 8 AMMetric snapshotSahadev posts every 6 hoursOracle ReportSahadev posts Friday at 9 AMApproval requestsAny agent needing approval notifies hereVishvarupa alertsThreshold violations posted to all groupsEach Telegram group links to ONE project. If you have multiple projects, create separate groups for each.
Webhooks
Receive real-time events when things happen in your projects. All payloads are signed with HMAC-SHA256.
Events
agent.responseAgent produced a responseapproval.pendingAn action needs your approvalapproval.resolvedYou approved or rejected an actionvishvarupa.invokedVishvarupa threshold triggeredscheduled.completedA scheduled task completedPayload Format
{
"event": "approval.pending",
"timestamp": "2026-04-08T09:14:32Z",
"data": {
"approvalId": "abc-123",
"projectId": "my-saas",
"agent": "bheem",
"actionType": "deploy",
"summary": "Deploy v2.1.0 to production"
}
}Verify the signature using the X-Pantheon-Signature header with your webhook secret.
Workspace Config
Customize agent behavior per project using workspace config files or the web onboarding.
CLI: .pantheon/ Files
When you run pantheon init, a .pantheon/ directory is created with:
PRIORITIES.mdYour project priorities — agents reference these on every messageSTACK.mdTech stack, architecture notes, conventionsAGENTS.mdCustom instructions for specific agentsEdit these files anytime — agents read them on every message.
Web: Workspace Notes
When creating a project through the web onboarding, you can add "Notes for your agents" in the Priorities step. These are stored in the database and serve the same purpose as .pantheon/ files.
Both sources work simultaneously. If you use both CLI and web, agents get context from .pantheon/ files AND database workspace notes.