Open-source, self-hostable platform for building and governing AI agents across multiple channels
Stage
Not given
Startup
Founded
Not given
2025
Based in
US
IN
Pricing model
Freemium
Open source
Pricing
Free plan with 200 credits per month for public repositories and core features; Pro plan at $16/month ($192 billed annually) with 4000 credits per month and private repository support; Enterprise plan with custom pricing and credits as needed
Free to run, fork and build on commercially under Business Source License 1.1; paid hosted plans from $0 to $79 USD
Key features
Connect agents with MCP Server for automatic documentation capture
Self-documenting pull requests
Sync existing documentation from Notion, Confluence, Coda, or repositories
Generate documentation on demand
Custom documentation templates
Shared knowledge layer for team-wide agent learning
Integration with Slack and MS Teams for context requests
Analytics dashboards and observability
Human approval workflows
Multi-channel support (WhatsApp, email, voice, web)
Retrieval and graph memory
Guardrails and governance with budgets
Browser automation
Role-based access control
OpenAPI and Swagger tool import
Agent skill learning
Sealed audit log
What makes it different
Reduces agent token consumption by 50% through shared knowledge caching
Automatically maintains up-to-date documentation as code changes
Knowledge stays in human-readable Markdown format and is portable
Improves agent consistency across runs with shared knowledge layer
SOC 2 Type II certified for enterprise security compliance
Runs on laptop, server, or Kubernetes—same images everywhere from release
Complete governance embedded in platform and SDKs with approval, budgets, audit
Open standards: MCP, A2A, AG-UI, OpenTelemetry, OIDC, OpenAPI
Business Source License allows commercial use and forking
Dosu
VegaDūta