Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding
- ID
- 2140
- Status
- summarized
- Published
- 30 Jun 2026, 12:17 AM
- Fetched
- 30 Jun 2026, 12:58 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Jun/29/ornith/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 8.0
- Created
- 30 Jun 2026, 12:58 AM
- Tags
- Audience
- developersvibe_codersai_ml_learnersai_agent_users
What happened
Ornith-1.0 is a new open-weight coding model from DeepReinforce, built on Gemma 4 and Qwen 3.5, with sizes up to 397B parameters, achieving top open-source performance on coding benchmarks. It excels at agentic coding with multiple tool calls and runs locally via LM Studio, making it accessible for offline use. Early tests show strong code search and manipulation capabilities.
Why it matters
It provides a free, open-source alternative to commercial coding agents, enabling local, privacy-respecting, and customizable coding assistance for developers and AI agent users.
Discussion angle
Test Ornith-1.0 against your own codebase tasks and compare its speed and accuracy to cloud-based agents like Copilot or Cursor.