Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.oktolabs.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Install

Pulse runs as a single Python process on your machine. No cloud account. No data leaves your system. Two commands and you have a board.

​
Prerequisites

  • Python 3.11 or higher
  • pip
python --version
If you are on macOS with Homebrew: brew install python@3.12

​
Install Pulse

​
Initialize

Run this in the directory where your agent will work. Pulse creates your board and writes the MCP configuration file your agent will use to connect. 
okto-pulse init --agents
What it does:
  • Creates ~/.okto-pulse/ with your database and board data
  • Writes .mcp.json in the current directory with a scoped API key
.mcp.json contains an agent API key. Do not commit it to a public repository. Add it to .gitignore.

​
Start

okto-pulse serve --accept-terms
Pulse starts two listeners on a single process:
EndpointDefault URL
Web board and APIhttp://localhost:8100
MCP server (agent access)http://localhost:8101/mcp
Open http://localhost:8100. Your board is ready. First run note: If you installed via pip, Pulse downloads the semantic search model (all-MiniLM-L6-v2, ~90 MB) on first start. This takes 30–60 seconds depending on your connection. The model is cached; subsequent starts are fast.

​
Verify

okto-pulse status
Both ports should report as live. If you used custom ports: 
okto-pulse serve --api-port 9000 --mcp-port 9001 --accept-terms
okto-pulse status --api-port 9000 --mcp-port 9001
If MCP port changes after initialization, regenerate .mcp.json: 
okto-pulse init --agents

​
Where your data lives

All Pulse data is stored locally at ~/.okto-pulse/: 
~/.okto-pulse/
  data/pulse.db            SQLite database (boards, specs, cards, decisions)
  boards/{id}/graph.lbug   per-board knowledge graph
  uploads/{id}/            file attachments
  global/discovery.lbug    cross-board discovery index
Nothing is sent to a remote server.

​
Next steps

Connect your agent

Wire up Claude Code, Cursor, Cline, or any MCP-compatible agent.

First workflow

Idea → spec → cards in your first session.
Last modified on May 7, 2026