CAIPE Features
Everything you need to run AI-powered platform engineering at enterprise scale — from multi-agent orchestration to RAG knowledge bases, skills, and production-grade deployment.
🛠️
Custom Agents
- No-code Agent Builder UI — configure identity, owner team, system prompt, model, tools, skills, subagents, middleware, approvals, and workflow access
- dynamic-agents Helm chart — deploy the agent runtime independently
- App config bootstrap: pre-wire models, MCP servers, agents, and workflows at chart install time
- Team/global ownership with RBAC-managed sharing
- MongoDB-backed persistence, Prometheus metrics, ExternalSecrets integration
🔁
Workflows
- Visual workflow builder for chaining dynamic agents into multi-step automations
- Step prompts support Jinja2 templates with previous outputs and user context
- Per-step error handling: abort, skip, or retry with configurable attempts
- MongoDB-backed workflow configs, run history, event timelines, and artifacts
- Custom agents can trigger and monitor approved workflows as built-in tools
🔌
BYO Agents & MCP Servers
- No-code Agent Builder UI — create agents without writing code
- appConfig.mcp_servers — plug in external MCP servers at chart install time
- Per-tool MCP servers for each integration
- Supported MCP transports: stdio, SSE, and Streamable HTTP
- Credential sources: secret refs, caller tokens, and provider connections
- LiteLLM proxy support — any LLM provider through a single endpoint
🔑
Credentials & Secrets
- Connected Apps — link Atlassian, GitHub, GitLab, PagerDuty, and Webex for user-scoped MCP access
- Connection health, reconnect, and permission review from one Credentials page
- Saved Secrets — store bearer tokens and other secret types without showing values again
- Rotate, share, and revoke secrets with team-scoped RBAC
- Server-side credential retrieval for agents and MCP servers — raw secrets never return to the browser
🤖
Multi-Agent Orchestration
- Multi-agent and deep agent interactions with access to multiple tools and sub-agents based on customizable system prompts
- 10+ first-party curated sub-agents and MCP servers
- Ability to create custom Agents
- Ability to customize system prompts
- [Middleware] Custom Skills Integration
🎨
Rich Web UI
- Rich/Contextual Home Page
- Rich Chat Interface with live agent/tool status via streaming
- Share chat with teams · Archive/Delete chats
- Custom Agent Builder
- Skills Gateway — AI Assist, API access, security scanner, GitHub crawling
🧠
Integrated Knowledge Bases
- Unified RAG with hybrid vector search and optional Graph RAG
- Ingestors: Web, AWS, Kubernetes, Backstage, ArgoCD, GitHub, Jira, Confluence, Slack, Webex
- MCP tools for search, fetch, datasource discovery, and graph exploration
- OAuth2/RBAC-aware ingestion and querying across data sources
💾
Agent Memory
- Chat persistence memory with multi-turn conversation
- Fact extraction across chats for a user
📡
Scheduled Runs & External Triggers
- Webhook-based agent triggers for event-driven workflows
- Scheduled/cron-based agent runs
- Integration with alerting systems (PagerDuty, VictorOps, Splunk)
- Event stream consumption — trigger agents from platform events
🔗
Agent and Tool Communications
- MCP (Model Context Protocol)
- Dynamic Agents API
- AG-UI / SSE streaming — real-time event handling across all agent types
- CLI access
🔒
Enterprise Security
- OAuth 2.0 integration with OIDC compatible IdPs
- OIDC/Okta groups base RBAC
- Team based access
- Policy based tool restrictions
🚀
Deployment
- Kubernetes based Helm charts
- Docker/Containerized Agents and MCP servers
- Docker Compose support
- Secrets management using ExternalSecrets
- LLM Tracing integration (Langfuse)
- Prometheus Metrics and Analytics
🔌
Integrations
- Web UI — rich chat interface with live agent/tool status via streaming
- Slack Bot — conversational interface for your team's existing workflow
- Webex Bot — enterprise messaging integration
- Chat CLI — invoke any agent from the terminal
Ready to get started?
Deploy CAIPE in your environment in minutes.