Multi-agent orchestration platform for AI coding agents
Structured AI decisions via API and playground
Stage
Not given
Not given
Founded
Not given
Not given
Based in
DE
Not given
Pricing model
Free
Not given
Pricing
Open-source MCP server is free. SideButton Portal offers a free trial with paid tiers for Business and Enterprise plans (pricing details to be announced).
Free: 5 successful runs per UTC day after email verification. Starter: $9.90/month for 30M tokens/month. Builder: $19.90/month for 80M tokens/month. Pro: $39.90/month for 200M tokens/month. Scale: $79.90/month for 500M tokens/month. Tokens refresh monthly and do not roll over. One-time token packs a
Key features
Model Context Protocol (MCP) Server with 40+ Tools
Native Claude Code Integration
Role-based agent assignment (PM, QA, SD, SE)
Playbooks for workflow orchestration
Real-time fleet monitoring and cost tracking
Jira and GitHub integration
Browser automation capabilities
Installable knowledge packs
Self-hosted deployment option
Choice decision type: select from supplied options
Score decision type: assign level on defined scale
Noul decision type: yes/no judgment against criterion
Decision flows: chain questions on canvas with branching
Batch processing for CSV, TXT, JSONL files up to 1,000 rows
Shared account balance across console, batch and API
Export results as CSV or JSONL
Failed requests are refunded
Probabilities included with all answers
What makes it different
Role-based agents that specialize by layer (QA, frontend, backend, senior review) rather than generalist agents
Runs on your own infrastructure with full integration into existing tools (Jira, GitHub, your cloud)
Open-source MCP server that can be self-hosted independently
Proven production results with 95% quality acceptance rate
Achieves 50 tickets shipped per day with just 5 agents running 24/7
One API and console for playground, flows, batch and API access
Only questions on the executed path in flows are billed
Built on TypeSafe AI's Jev structured decision model
Test and measure decisions on your own data before production
Custom decision criteria defined by your own labels and rules