OpenFrame

OpenFrame v0.2.0 - Flexible LLM Model Selection

Version: 0.2.0

AIARCHITECTUREINTEGRATIONOPENFRAMEPLATFORM UPDATESUSER EXPERIENCE

MAJOR

Release Type

BETA

Release Status

November 27, 2025

Release Date

Michael Assraf

Michael Assraf

Founder and CEO

This major release introduces groundbreaking LLM model selection capabilities, allowing users to switch between AI providers based on their specific needs. The update includes significant architectural improvements with the CLI migration to a dedicated repository, enhanced chat functionality with Markdown support, and numerous stability fixes that improve the overall platform experience.

Features Added
4

  • LLM Model Selection

    Switch between different AI models (OpenAI, Anthropic, Gemini) based on task requirements, with intelligent routing, performance monitoring, and automatic fallback mechanisms

  • Onboarding Wizard

    Step-by-step guided setup for new users with progress tracking and the ability to skip or revisit onboarding steps

  • Markdown Support in Fae Chat

    Enhanced message formatting capabilities with full Markdown support in the chat interface

  • Shareable Search States

    Share specific search views with teammates via URL parameters that preserve all search criteria, time ranges, and filters

Bugs Fixed
2

  • Scripts Management Infinite Loading

    Fixed infinite scrolling state that prevented users from viewing or managing automation scripts

  • Device Status Transition Issue

    Prevented incorrect status reset from ASSIGNED to READY when management service callback is triggered

Improvements
7

  • CLI Migration to Dedicated Repository

    Separated CLI into its own repository for independent versioning, faster iteration, and streamlined distribution

  • Enhanced Agent Uninstall Process

    Complete cleanup of Windows agents including all components, services, scheduled tasks, and registry entries

  • Auto-Refresh for Device Screen

    Automatic updates at regular intervals to display current device status without manual refresh

  • Device Status Management - Archive and Delete

    Added ability to archive and delete devices from the dashboard with proper state handling

  • Soft Deletion for Installation Commands

    Remove installation files before installation command

  • Database Schema Enhancements

    Added timestamp tracking and improved status transition handling for better data integrity

  • LLM Metadata Support

    Backend and frontend implementation for tracking and displaying model information, token usage, and response metrics

Related Links

Github Release0.2.0
Michael Assraf

Michael Assraf

Founder and CEO

Hey everyone, I'm Michael - founder and CEO of Flamingo. Before this, I built Vicarius, a cybersecurity company focused on vulnerability remediation, where I raised over $60M in funding. Working closely with service providers through that journey, I saw firsthand how MSPs were losing money to vendor payouts and inefficient systems - and that's when the idea for Flamingo clicked. I set out to build an open-source platform that dramatically increases MSP margins while helping them deliver better service to their clients.

Related Content

Product Releases

Webinars

Case Studies

Blog Posts

Onboarding Guides

Frequently Asked Questions

MSP AI Agents

Yes. In production MSP shops today, 10% to 25% of tickets close before a human opens them. Thread alone has processed 173 million tickets across 750-plus MSP partners at 96% triage accuracy, handing back 490,000-plus technician hours. Agents own the low-risk, high-volume work (password resets, MFA enrollment, known installs, onboarding and offboarding) and flag anything that touches production data or needs judgment for a human to take.
On a five-person desk, reported deployments show $78,000 to $130,000 in annual direct labor savings, roughly 30% fewer escalations, and 15% to 20% better SLA compliance. Broader MSP adoption data adds ticket handling time cut by 45% and five to 12 points of margin, all from reclaimed capacity rather than headcount cuts.

AI MSP

MSPs use AI to triage and route tickets, cut alert noise, schedule patches, assist L1 security work, and draft client reports. Kaseya's 2025 benchmark found 30% already use it to eliminate tedious tasks, with ticket triage the most common starting point.
Most MSPs start with AI features inside their existing PSA, RMM, and ticketing systems rather than standalone products. Common categories include AI ticket triage, alert correlation, scripting assistants, and AI-native all-in-one platforms like OpenFrame that run intelligence across the whole stack.
Start with a readiness assessment, not a tool purchase. Confirm your ticket history is clean and your RMM, PSA, and monitoring systems connect. Then pick one high-volume, low-risk workflow, usually ticket triage, and pilot it on internal tickets before any client sees it.

AI Safety

It can be, with governance. Keep a human in the loop on high-risk actions, log every automated step for audit, and choose platforms that keep your data yours with no vendor lock-in. Pilot on internal data first so you catch issues before client systems are involved.

AI for MSPs

Set a baseline before rollout, then track tickets closed per technician, mean time to resolution, percentage of tickets resolved with no human touch, technician hours reclaimed, and cost per ticket. AI-driven automation commonly cuts operational cost per ticket by 25 to 40%.
No. AI automates routine tickets, patching, and monitoring, but trust, accountability, and complex business judgment still need people. The future of managed services moves technicians from closing tickets to advising clients, which makes the human role more valuable, not obsolete.

About OpenFrame

OpenFrame isn't built to plug into your stack. It replaces it. Instead of duct-taping a dozen tools together (RMM, MDM, SIEM, patching, remote access, each its own login and bill), we bundle it into one unified platform: RMM, MDM, monitoring, automation, remote access, patch management, security monitoring, and ticketing, plus built-in AI copilots. So "does it integrate with X?" usually means: you won't need X anymore.

AI Infrastructure

AI-powered infrastructure managed services apply machine learning to infrastructure telemetry so providers can predict failures, automatically remediate known issues, and forecast capacity needs. They replace static-threshold monitoring and manual firefighting with predictive, largely automated operations overseen by technicians.