Sekia — Multi-agent event bus

Install

brew install sekia-ai/tap/sekia

go install github.com/sekia-ai/sekia/cmd/sekiad@latest
go install github.com/sekia-ai/sekia/cmd/sekiactl@latest
go install github.com/sekia-ai/sekia/cmd/sekia-github@latest
go install github.com/sekia-ai/sekia/cmd/sekia-slack@latest
go install github.com/sekia-ai/sekia/cmd/sekia-linear@latest
go install github.com/sekia-ai/sekia/cmd/sekia-gmail@latest
go install github.com/sekia-ai/sekia/cmd/sekia-mcp@latest

git clone https://github.com/sekia-ai/sekia.git
cd sekia
docker compose up

git clone https://github.com/sekia-ai/sekia.git
cd sekia
go build ./cmd/sekiad ./cmd/sekiactl ./cmd/sekia-github \
         ./cmd/sekia-slack ./cmd/sekia-linear ./cmd/sekia-gmail \
         ./cmd/sekia-mcp

Quick start

1 Start the daemon

sekiad

2 Write a workflow

-- ~/.config/sekia/workflows/auto-label.lua

sekia.on("sekia.events.github", function(event)
    if event.type ~= "github.issue.opened" then return end

    local title = string.lower(event.payload.title or "")

    if string.find(title, "bug") then
        sekia.command("github-agent", "add_label", {
            owner  = event.payload.owner,
            repo   = event.payload.repo,
            number = event.payload.number,
            label  = "bug",
        })
    end
end)

3 Connect an agent

export GITHUB_TOKEN=ghp_...
sekia-github

4 Check status

sekiactl status
sekiactl agents

Lua API

Function	Description
`sekia.on(pattern, fn)`	Register handler for NATS subject pattern
`sekia.publish(subj, type, data)`	Emit an event
`sekia.command(agent, cmd, data)`	Send command to an agent
`sekia.log(level, msg)`	Log a message
`sekia.ai(prompt [, opts])`	Call an LLM, returns `(result, err)`
`sekia.ai_json(prompt [, opts])`	Call an LLM, returns parsed Lua table
`sekia.name`	The workflow's name

Function

Description

sekia.on(pattern, fn)

sekia.publish(subj, type, data)

Emit an event

sekia.command(agent, cmd, data)

Send command to an agent

sekia.log(level, msg)

Log a message

sekia.ai(prompt [, opts])

Call an LLM, returns (result, err)

sekia.ai_json(prompt [, opts])

Call an LLM, returns parsed Lua table

sekia.name

The workflow's name

Agents

GitHub

Webhooks and REST API polling for issues, PRs, pushes

GITHUB_TOKEN

Slack

Socket Mode for messages, reactions, mentions

SLACK_BOT_TOKEN SLACK_APP_TOKEN

Linear

GraphQL polling for issues, comments, state changes

LINEAR_API_KEY

Gmail

IMAP polling for incoming mail, SMTP for sending

GMAIL_ADDRESS GMAIL_APP_PASSWORD

MCP Server

Expose Sekia to Claude Desktop, Claude Code, Cursor

sekia-mcp (stdio)