Ornith-1.0: Open-source self-scaffolding LLM family for agentic coding, from 9B to 397B parameters
By
@ornith_
Summary
Ornith-1.0 is a new family of open-source AI models designed specifically for agentic coding tasks. Developed by a team (likely at Aloha), the models range from a compact 9B Dense variant for edge devices to a massive 397B MoE frontier-scale model for maximum performance. Built on top of pretrained Gemma 4 and Qwen 3.5, the models achieve state-of-the-art performance among open-source models of comparable size on coding benchmarks. The key innovation is a "self-scaffolding" approach that allows the models to improve their own coding capabilities through iterative refinement.
Source
Hacker NewsOrnith-1.0: Open-source self-scaffolding LLM family for agentic coding, from 9B to 397B parametersdeep-reinforce.comKey quotes
· 3 pulledToday, we are introducing Ornith-1.0, a self-improving family of open-source models specially for agentic coding tasks.
Ornith-1.0 spans the full spectrum, from compact 9B Dense models suitable for edge device deployment to 397B MoE frontier-scale models optimized for maximum performance.
Built on top of pretrained Gemma 4 and Qwen 3.5, it achieves state-of-the-art performance among open-source models of comparable size on coding benchmarks.
You might also wanna read
DeepReinforce AI Releases Ornith-1.0: Open-Source Agentic Coding Models Up to 397B Parameters
DeepReinforce AI has released Ornith-1.0, a family of open-source models for agentic coding, available in sizes from 9B to 397B parameters.
Ornith-1.0-397B
modelscope.ai·10d ago
Omnigent: An open-source meta-harness for composing and governing AI agents
Omnigent is an open-source meta-harness that provides a common layer for composing, governing, and collaborating on AI agents. It allows use
omnigent.ai·9d ago
OpenLIT: Zero-Code Observability Platform for AI Agents and LLM Applications
OpenLIT is an open-source observability platform that provides zero-code monitoring for AI agents and LLM applications. It addresses the com
Product Hunt·9mo ago
A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning
This paper presents a practical guide to AI-assisted research in mathematics and machine learning. It introduces a five-level taxonomy of AI
arxiv.org·2d ago
Orca: Open-Source Desktop App for Parallel AI Agent Development
Orca is a free, open-source desktop application that enables parallel AI agent development by combining Ghostty-style terminals, git worktre
Product Hunt·2mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.