LeemerChat · Editorial

The Journal

FeaturedMay 9, 2026GA1 launch

LeemerChat GA1: General Availability After Years of Iteration

LeemerChat GA1 is now generally available, shaped by years of development and billions of tokens across chat, research, podcast, Analyst, LeemerStudio, and new model lanes.

Read the storyLeemerChat Team9 min read

About the journal

LeemerChat is Ireland's leading AI chat platform, bringing together the world's most powerful language models in a single, unified workspace. Our editorial covers frontier model launches, multi-model architecture write-ups, research tooling, and the day-to-day work of shipping AI products from Dublin. You'll find launch notes for GPT-5, Claude 4.6, Gemini 3, Kimi K2.5, GLM-5 and LeemerChat's own internal stack, as well as essays on engineering practice, AI safety, and the economics of inference. Whether you're a developer integrating AI coding agents, a researcher exploring multi-model synthesis, or simply tracking the state of the field, the archive below is organised by releases, models, benchmarks, engineering, and broader insights.

Archive

All posts

36 stories, newest first.

01May 9, 2026

LeemerChat GA1: General Availability After Years of Iteration

LeemerChat GA1 is now generally available, shaped by years of development and billions of tokens across chat, research, podcast, Analyst, LeemerStudio, and new model lanes.

LeemerChat Team9 min readGA1General AvailabilityLeemerChat
02May 7, 2026

Introducing LeemerH2: The Model Council

LeemerH2 is the successor to Leemer Heavy, built as a council of models for stronger software engineering, research, verification, and 128K-token synthesis.

Repath 'Ray' Khan, Founder of LeemerChat10 min readLeemerH2Leemer HeavyMulti-Model AI
03May 7, 2026

Introducing Leemer Analyst: Living Research Agents

Leemer Analyst is a persistent research agent inside its own E2B VM, built for long-running analysis, memory, connectors, verification, and private artifact deployment.

Repath 'Ray' Khan, Founder of LeemerChat12 min readLeemer AnalystAI Research AgentE2B
04May 6, 2026

Introducing LeemerStudio: Image and Video Generation Built Into LeemerChat

LeemerStudio is a new creative workspace inside LeemerChat for generating images, animating references, rendering video, tracking live status, and keeping every output in private history.

LeemerChat Team11 min readLeemerStudioAI Image GenerationAI Video Generation
05May 6, 2026

Grok 4.3, Qwen 3.6, and a Cleaner Frontier Lineup for LeemerChat

We replaced every active Grok route with Grok 4.3, promoted Qwen3.6 Max Preview into the premium slot, added Qwen3.6 35B A3B, and cleaned out older Qwen/Grok baggage. Here's why.

LeemerChat Team7 min readGrok 4.3Qwen 3.6Kimi K2.6
06April 26, 2026

LeemerChat v8 Spring Update: DeepSeek V4, MiMo 2.5, Firecrawl Search, and the Move to Critique

A detailed product update after eight recent PRs: why PowerCode now lives on as Critique.sh, what changed across the app shell and settings UX, how DeepSeek V4 Flash and Pro plus Xiaomi MiMo V2.5 and V2.5 Pro landed in the lineup, and why Firecrawl now sits under the live search stack for both free and pro flows.

LeemerChat Team13 min readv8.0.0DeepSeek V4MiMo V2.5
07April 26, 2026

From PowerCode to Critique: The Full Story Behind LeemerChat v8.0.0 and What Happens Next

LeemerChat v8.0.0 retires the in-app PowerCode agent (4.9+). What it was, why Critique.sh fits review and ship work better, and what stays in main chat. Partner terms on /tips.

LeemerChat Team16 min readPowerCodeCritiquev8.0.0
08April 24, 2026

The Trillion-Parameter Open-Weight Wave Hits LeemerChat: DeepSeek V4, MiMo 2.5, Kimi K2.6, and a Limited Ling Promo

We refreshed our partner lineup around Chinese-led trillion-scale open models—DeepSeek V4 Pro and Flash, Xiaomi MiMo 2.5 Pro and 2.5, Moonshot Kimi K2.6, plus a time-bound free route for InclusionAI Ling 2.6 1T. Here is why we bundled them, how they differ, and how to benchmark them on real work instead of leaderboard screenshots alone.

LeemerChat Team9 min readDeepSeekXiaomiMoonshot
09April 17, 2026

Introducing LeemerLabs

LeemerLabs is the infrastructure arm of the Leemer Group: Ireland-hosted inference, custom model creation through LeemerFoundry, and the systems powering products like LeemerChat.

Repath 'Ray' Khan, Founder of LeemerLabs6 min readLeemerLabsInferenceEuropean AI
10April 9, 2026

GLM-5.1 Is Now Free on LeemerChat — The Model That Works for 8+ Hours Without Stopping

Z.AI's GLM-5.1 is the first model built for long-horizon autonomous coding — running independently for 8+ hours, planning, executing, and self-improving without human input. It beats or matches GPT-5.4 and Claude Opus 4.6 on several benchmarks. Here's why we made it free, how it compares, and why Pro still matters.

LeemerChat Team8 min readModel LaunchGLM-5.1Z.AI
11April 4, 2026

We Just Moved a Chunk of the Frontier Into the Free Tier

Three frontier-grade models go free — Xiaomi MiMo-V2-Pro (1M context), Z.AI GLM-5V-Turbo (native multimodal agent), and Google Gemma 4 31B IT (89.2% AIME 2026). Premium gets sharper with GPT-5.4, GLM-5, and MiniMax M2.7. Plus: why we cleaned up the lineup and what frontier actually means now.

LeemerChat Team9 min readModel LaunchFrontier ModelsGPT-5.4
12March 2, 2026

Get Ready for Mission Control: The Next Evolution of Agentic Execution

Mission Control is our next-generation agentic research and execution platform. It represents a fundamental shift in how we interact with AI—moving away from rigid pipelines and chat interfaces, and stepping into the era of autonomous, goal-oriented swarms.

Repath 'Ray' Khan, Founder of LeemerChat10 min readMission ControlAgentic AIMulti-Agent
13February 22, 2026

The Foundry Report: Why Fine-Tuned Models Are Still the Sharpest Weapon in Enterprise AI

Tinker is now generally available. Vision input, Kimi K2 Thinking, and LoRA Without Regret are reshaping what custom model training looks like in 2026. Here's why fine-tuning is more strategically important than ever — and how LeemerLabs Model Foundry is building the infrastructure to prove it.

Repath 'Ray' Khan, Founder of LeemerLabs14 min readModel FoundryFine-TuningAgentic AI
14February 12, 2026

MiniMax M2.5 Is Live: SOTA Productivity Model for Real-World Office Work

MiniMax M2.5 launches on LeemerChat with breakthrough performance in Word, Excel, and PowerPoint generation. Scoring 80.2% on SWE-Bench Verified and 76.3% on BrowseComp, M2.5 extends M2.1's coding expertise into general office productivity.

LeemerChat Team6 min readMiniMaxM2.5Model Launch
15February 11, 2026

GLM-5 Is Live: Frontier Open-Source Scale for Complex Engineering and Agentic Work

GLM-5 launches on LeemerChat with major upgrades in scale, training data, and RL infrastructure. Built for long-horizon agentic systems, coding reliability, and complex reasoning under production constraints.

LeemerChat Team7 min readGLM-5Z.AIModel Launch
16February 7, 2026

Cursor Cloud Agents Meet LeemerChat: Launch, Monitor & Refine AI Agents from Chat

We've integrated Cursor's Cloud Agents API into LeemerChat so you can launch, monitor, stop, and follow-up with autonomous coding agents on your GitHub repos — all from the chat. Just enter your API key in settings and start dispatching agents with natural language.

LeemerChat Team8 min readCursorCloud AgentsAI Agents
17February 7, 2026

Blackbox Cloud Meets LeemerChat: Dispatch AI Coding Agents from Chat

We've integrated Blackbox Cloud into LeemerChat so you can dispatch autonomous coding agents to your GitHub repos — single-agent or multi-launch — without leaving the conversation. Create, monitor, and cancel tasks with natural language.

LeemerChat Team7 min readBlackbox CloudAI AgentsIntegration
18February 2, 2026

Introducing KingLeemer: Multiple Brains Behind Every Answer

What if AI answers came from a council of experts instead of a single voice? KingLeemer orchestrates multiple frontier models to think together, disagree, debate, and converge on answers more reliable than any single model could produce alone.

Repath Khan, Founder of LeemerChat18 min readKingLeemerMulti-AgentArchitecture
19January 30, 2026

Kimi K2.5: Moonshot AI’s Frontier Multimodal Model, Now Live on LeemerChat

Kimi K2.5 brings state-of-the-art visual coding, 262K context, and self-directed agent swarms. We’re Ireland’s first AI platform to launch it — and it’s live free on LeemerChat.

LeemerChat Team8 min readKimi K2.5Moonshot AIModel Launch
20January 25, 2026

PDF AI Processing: From Static Documents to Solved Answers

Upload a PDF, get it back solved. No prompts required. Introducing our standalone PDF processing workflow with Mistral OCR, Multi-Agent Consensus, and Visual Overlay.

Repath Khan, Founder of LeemerChat6 min readNew FeaturePDF ProcessingMistral OCR
21January 11, 2026

LeemerChat v5.1: Talk to Your Codebase, AI Memory, and Expert Consultations

Introducing Codebase Chat with GitHub integration, natural AI Memory for preferences, Second Thought expert consultations, and concurrent generation. The biggest evolution of LeemerChat yet.

Repath Khan, Founder of LeemerChat15 min readv5.1Codebase ChatGitHub
22December 19, 2025

Gemini 3 Flash Explained: Google's Fastest Frontier-Grade AI for Real-World Scale

Google's Gemini 3 Flash represents a clear shift in how frontier-level AI is delivered in production. Near-Pro-level reasoning and multimodal understanding while remaining fast, responsive, and economical enough for large-scale deployment.

LeemerChat Team10 min readGemini 3GoogleFlash
23December 15, 2025

RIN: Sharp. Fast. Precise. Our Free Unlimited Reasoning Model

Meet RIN (凛) — a 26B-A3B MoE model running at 450 tokens/second, completely free and unlimited. The precision instrument for builders who value speed over hand-holding. Semi-successor to LeemerGLM.

Repath Khan, Founder of LeemerChat8 min readRINModel LaunchFree
24December 14, 2025

Happy Holidays from LeemerChat: Year in Review 🎄

This holiday season, we're reflecting on an incredible year together. From V3 to V4.9, over 1.5B+ tokens processed, LeemerLite at 1,750 T/s, PowerCode, and welcoming GPT-5.1, Claude 4.5 Sonnet, Gemini 3, and Qwen — here's to building the future together.

Repath 'Ray' Khan, Founder of LeemerChat7 min readHolidayThank YouCommunity
25December 10, 2025

LeemerChat v4.8: The Smoother AI Experience You've Been Waiting For

Discover how IKEA-inspired design, frosted glass interfaces, and revolutionary durable generation create an AI workspace that feels effortless yet powerful. This is what happens when design meets reliability.

Repath Khan, Founder of LeemerChat12 min readv4.8UI DesignProduct Launch
26December 7, 2025

LeemerLite Drop: The 1,750 T/s Sandbox Powered by Groq

We just dropped LeemerLite: a super-simplified, no-signup chat running gpt-oss-safeguard-20b at world-class speeds. See how it stacks up against GPT-5 Nano, Llama 4 Scout, and Mistral.

Repath Khan, Founder of LeemerChat4 min readProduct DropGroqPerformance
27November 2025

LeemerChat v4.5: Research, Email, and Automation

Detailed drop of research, email, and automation updates with new model lineup.

Repath Khan, Founder of LeemerChat10 min readreleaseresearchemail
28December 7, 2025

Meet LeemerGLM: our Gemma 3-powered multimodal expert

A behind-the-scenes look at how we built LeemerGLM on top of Gemma 3 4B, why we paired it with a multimodal specialist, and how it slots into our expert panel.

LeemerLabs Team11 min readLeemerGLMGemma 3Multimodal
29December 3, 2025

The $50B Vibe Coding Time Bomb: Why 80% of Startups Die from Shitty Code

Vibe coding feels fast, but it hides a $50B cleanup bill. This editorial exposes why 80% of startups crash because of sloppy code and how frontier AI turns vibes into infrastructure.

Repath Khan, Founder of LeemerLabs16 min readVibe CodingEngineering DisciplineFrontier AI
30December 1, 2025

The $100B AI Bubble: Why 90% of AI Companies Will Be Worthless by 2027

The AI boom is the biggest technological surge since the internet — and it is dangerously overheated. Based on historical venture cycles, market concentration, and structural economics, 90% of today's AI companies will likely be worth close to zero by 2027. This is not pessimism. It is pattern recognition.

Repath Khan, Founder of LeemerLabs18 min readAI BubbleVenture CapitalMarket Analysis
31December 1, 2025

Why Sovereign AI Models Matter: The Case for Owning Your Intelligence

In a world where AI is becoming critical infrastructure, relying on third-party APIs is like renting your brain. We explore why self-hosted, sovereign AI models are the future—and why the smartest companies are already making the switch.

Repath Khan, Founder of LeemerLabs14 min readSovereign AISelf-HostingAI Independence
32November 22, 2025

Introducing LeemerLabs Model Foundry: Your Data. Your Model. Our GPUs.

We're launching Ireland's first custom LLM creation studio. Fine-tune frontier models up to 235B parameters using Tinker distributed training, powered by Thinking Machines Lab. Build domain-specific intelligence layers that you own and deploy anywhere.

Repath Khan, Founder of LeemerLabs12 min readLeemerLabsModel FoundryTinker
33November 21, 2025

We Let GPT-5, Claude 4.5, Grok-4.1, and Gemini Fight. Here's Who Won (And Why It Doesn't Matter)

We tested GPT-5.1, Claude Sonnet 4.5, Grok-4.1-Fast, and Gemini 2.5 Pro across coding, reasoning, writing, vision, research, and speed. The results reveal why using multiple models in one chat is the future of AI.

Repath Khan, Founder of LeemerChat8 min readAI ModelsBenchmarksGPT-5
34November 2025

How we protected Gemini 3 Pro access from synthetic abuse

How LeemerChat used BotID Deep Analysis to shut down coordinated synthetic agents without slowing down real users.

Repath Khan, Founder of LeemerChat6 min readSafetyGemini 3 ProBotID
35November 2025

Behind the scenes: How Leemer Heavy and Heavy (Fast) work

A deep dive into the union model architecture powering Leemer Heavy's iterative research orchestration and Heavy (Fast)'s rapid debate synthesis system.

Repath Khan, Founder of LeemerChat12 min readArchitectureAI ModelsUnion Models
36November 2025

Welcome Deep Research: The World's Best Multi-Model Research System

How we built Deep Research by orchestrating three world-class AI models together, powered by K2-Thinking—the world's strongest reasoning open-source model. Plus a preview of Ultra version running autonomously for 3-4 hours.

Repath Khan, Founder of LeemerChat10 min readDeep ResearchMulti-ModelK2-Thinking