Update README.md

README.md

@@ -1,10 +1,78 @@
 ---
 title: README
-emoji: 🏢
+emoji: 🧠
 colorFrom: red
 colorTo: blue
 sdk: static
 pinned: false
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+<div align="center">
+
+# GestaltLabs
+
+**Open model research for reasoning, agents, and local-first multimodal AI.**
+
+GestaltLabs is the research home for the Ornstein, Harmonic, Acta, Talos, and related releases by [DJLougen](https://huggingface.co/DJLougen). We build, curate, and publish models and datasets for practical reasoning systems: multimodal assistants, tool-using agents, local GGUF deployments, and post-training experiments around capability preservation, refusal ablation, and high-signal synthetic data.
+
+[Models](https://huggingface.co/GestaltLabs?sort_models=lastModified) · [Datasets](https://huggingface.co/datasets?author=DJLougen) · [DJLougen](https://huggingface.co/DJLougen)
+
+</div>
+
+---
+
+## Current Focus
+
+- **Ornstein** - multimodal and MoE model releases for reasoning, conversation, and image-text workflows
+- **Harmonic** - reasoning-oriented models and datasets for self-correction, chain-of-thought style supervision, and agent traces
+- **SABER / RYS** - post-training experiments around refusal ablation, capability preservation, layer surgery, and model behavior editing
+- **Acta / Talos** - curated agentic tool-use and coding-assistant traces for SFT and evaluation
+- **Local inference** - GGUF, quantized, and deployment-friendly builds for llama.cpp-compatible workflows
+
+## Featured Model Lines
+
+### Ornstein
+
+The Ornstein line explores multimodal reasoning and local deployment across Qwen and Gemma-derived models, including 27B, 31B, and 35B-A3B variants.
+
+- [GestaltLabs/Ornstein-3.6-27B](https://huggingface.co/GestaltLabs/Ornstein-3.6-27B)
+- [GestaltLabs/Ornstein-3.6-27B-GGUF](https://huggingface.co/GestaltLabs/Ornstein-3.6-27B-GGUF)
+- [DJLougen/Ornstein3.6-35B-A3B-GGUF](https://huggingface.co/DJLougen/Ornstein3.6-35B-A3B-GGUF)
+- [DJLougen/Ornstein-27B-v2-GGUF](https://huggingface.co/DJLougen/Ornstein-27B-v2-GGUF)
+
+### Harmonic
+
+Harmonic releases focus on reasoning, tool use, self-correction, and lightweight local experimentation.
+
+- [DJLougen/Harmonic-Hermes-9B-GGUF](https://huggingface.co/DJLougen/Harmonic-Hermes-9B-GGUF)
+- [DJLougen/Harmonic-27B-GGUF](https://huggingface.co/DJLougen/Harmonic-27B-GGUF)
+- [DJLougen/Qwen3.5-9B-Harmonic-GGUF](https://huggingface.co/DJLougen/Qwen3.5-9B-Harmonic-GGUF)
+
+### SABER / RYS
+
+SABER and RYS are experimental post-training branches for studying model behavior, refusal boundaries, and capability-preserving edits.
+
+- [DJLougen/Ornstein3.6-35B-A3B-RYS-SABER](https://huggingface.co/DJLougen/Ornstein3.6-35B-A3B-RYS-SABER)
+- [DJLougen/Ornstein3.6-35B-A3B-RYS-SABER-GGUF](https://huggingface.co/DJLougen/Ornstein3.6-35B-A3B-RYS-SABER-GGUF)
+- [DJLougen/gemma-4-E2B-it-saber](https://huggingface.co/DJLougen/gemma-4-E2B-it-saber)
+
+## Featured Datasets
+
+- [Ornstein Curated 100K](https://huggingface.co/datasets/DJLougen/ornstein-curated-100k) - curriculum-sorted multi-domain reasoning data
+- [Hermes Agent Traces Filtered](https://huggingface.co/datasets/DJLougen/hermes-agent-traces-filtered) - quality-filtered agent reasoning traces
+- [Harmonic Reasoning v1](https://huggingface.co/datasets/DJLougen/harmonic-reasoning-v1) - compact synthetic reasoning data for math, code, and self-correction
+- [WittgenSite](https://huggingface.co/datasets/DJLougen/wittgensite) - prompt consistency benchmark for AI coding agents
+- [Acta](https://huggingface.co/datasets/DJLougen/Acta) - curated agentic tool-use conversations
+- [Talos Scenarios](https://huggingface.co/datasets/DJLougen/Talos-Scenarios) - agentic task scenarios for synthetic trace generation
+
+## Principles
+
+- Ship open artifacts that people can inspect, run, and adapt
+- Pair model releases with practical local inference formats
+- Treat datasets as research objects, not just training fuel
+- Explore behavior editing while preserving useful capabilities
+- Build for researchers, tinkerers, and builders who want systems they can actually run
+
+## Contact
+
+For questions, collaboration, eval results, or licensing discussions, open a discussion on the relevant repository or reach out through [DJLougen](https://huggingface.co/DJLougen).