Blog

Engineering insights, tutorials, and deep-dives into multi-channel conversation systems.

Introducing roomkit-sandbox: Secure Sandboxed Execution for AI Agents

April 2, 2026 · 6 min read

Give AI agents secure, container-based command execution with 10 built-in tools, three isolation backends (Docker, Kubernetes, SmolBSD), and token-optimized output via RTK. Now on PyPI.

Read more

Introducing roomkit-graph: Workflow Graphs for RoomKit

April 1, 2026 · 5 min read

Define multi-step AI workflows as serializable directed graphs — with agents, human approvals, parallel execution, and conditional branching — and run them inside RoomKit rooms. Now on PyPI.

Read more

Guardrails in RoomKit: Composable Safety for Multi-Channel AI

March 26, 2026 · 18 min read

How RoomKit turns AI safety from a monolithic afterthought into layered, composable primitives (hooks, policies, rate limits, circuit breakers) that you wire together like middleware at every stage of the message lifecycle.

Read more

Where RoomKit Fits in the Voice AI Production Framework Landscape

March 24, 2026 · 12 min read

WebRTC.ventures compared Bedrock, Vertex, LiveKit, and Pipecat for production voice AI. Here's the missing fifth architecture: multi-channel conversation rooms where voice coexists with SMS, Email, and WhatsApp in the same room.

Read more

The 9 Pillars of Production-Ready Multi-Agent Systems

March 21, 2026 · 6 min read

Not just multiple LLM calls. A real multi-agent system requires orchestration, memory, tools, and evaluation. This series breaks down the 9 pillars of production-ready multi-agent architecture and shows how RoomKit addresses each one.

Read more

Multi-Agent Architecture, Part 1: User Interaction — Every Channel Is an Entry Point

March 21, 2026 · 8 min read

How RoomKit handles user interaction across chat, voice, SMS, email, and WebSocket — normalizing every entry point into a unified conversation model with identity resolution and request validation.

Read more

Multi-Agent Architecture, Part 2: Orchestration — Routing Conversations to the Right Agent

March 21, 2026 · 10 min read

How RoomKit orchestrates multi-agent conversations with ConversationRouter, phase-based routing, intent classification, and automatic agent handoffs.

Read more

Multi-Agent Architecture, Part 3: Knowledge — Giving Agents the Context They Need

March 21, 2026 · 8 min read

How RoomKit manages the intelligence backbone of multi-agent systems — memory providers, context retrieval, skill registries, and cross-agent knowledge sharing.

Read more

Multi-Agent Architecture, Part 4: Storage — Persistent Memory for Multi-Agent Conversations

March 21, 2026 · 8 min read

How RoomKit persists conversation history, agent state, and identity across sessions with ConversationStore, PostgresStore, and JSONB event storage.

Read more

Multi-Agent Architecture, Part 5: Agents — Supervisors, Specialists, and Delegation

March 21, 2026 · 10 min read

How RoomKit models agents as execution units — supervisor oversight, specialized AI channels, background delegation, and multi-provider support across Anthropic, OpenAI, Gemini, and Mistral.

Read more

Multi-Agent Architecture, Part 6: Integration — Secure Tool Access with MCP and Policies

March 21, 2026 · 8 min read

How RoomKit controls tool access in multi-agent systems — MCP integration, policy-based allow/deny, role overrides, and secure credential handling.

Read more

Multi-Agent Architecture, Part 7: External Tools — Connecting Agents to the Real World

March 21, 2026 · 8 min read

How RoomKit connects multi-agent systems to external services — SMS providers, voice APIs, email, CRM integrations, and custom tool handlers for any business system.

Read more

Multi-Agent Architecture, Part 8: Observability — Seeing Inside Your Multi-Agent System

March 21, 2026 · 8 min read

How RoomKit provides full observability into multi-agent systems — OpenTelemetry integration, span hierarchies, token tracking, latency metrics, and agent traceability.

Read more

Multi-Agent Architecture, Part 9: Evaluation — Scoring and Improving Agent Conversations

March 21, 2026 · 8 min read

How RoomKit evaluates and improves multi-agent conversations — observations, task tracking, phase audit trails, and feedback loops for continuous quality improvement.

Read more

I Built a Desktop Voice Assistant in Python. Here’s What I Learned

February 10, 2026 · 8 min read

I built RoomKit UI, a desktop voice assistant for macOS, Linux, and Windows. It supports Google Gemini and OpenAI Realtime, connects to external tools via MCP, includes system-wide dictation, and ships as a standalone app — all built on top of RoomKit.

Read more

RoomKit Speaks SIP: Bridge Any PBX to Conversational AI

February 10, 2026 · 12 min read

RoomKit now supports SIP natively. Incoming calls from any PBX are answered and bridged to conversational AI in real time — no WebRTC, no browser, just a phone call in under 50 lines of Python.

Read more

Gradium + RoomKit: Building Voice AI Agents with Ultra-Low Latency STT/TTS

February 9, 2026 · 15 min read

How I integrated Gradium's audio language models into RoomKit for multi-channel voice AI — with semantic VAD for natural turn-taking, streaming STT/TTS via WebSocket, and sub-300ms time-to-first-token.

Read more

RoomKit, Pipecat, TEN Framework, LiveKit Agents: Choosing the Right Conversational AI Framework

February 9, 2026 · 18 min read

A fair comparison of four open-source conversational AI frameworks — their philosophies, code examples, strengths, and ideal use cases. Pipelines vs. graphs vs. rooms vs. sessions: choose the abstraction that matches your problem.

Read more

Your Voice Assistant Doesn't Need the Cloud

February 7, 2026 · 14 min read

Build a fully local, open-source voice assistant in Python — no API keys, no subscriptions, no data leaving your machine. A fully local voice pipeline running on a single NVIDIA 4070, responding in under 300ms.

Read more

I Built a Multi-Channel Conversation Framework in Python. Here's Why.

February 7, 2026 · 12 min read

If you've ever integrated SMS, email, voice, and chat into the same app, you know the pain. Each channel has its own SDK, its own webhooks, its own quirks. After the third time rebuilding the same plumbing, I extracted the pattern into a library.

Read more