DeepReinforce

An open-source family of AI models (9B, 35B MoE, and 397B MoE) built for agentic coding, reasoning, and tool use. It extends the self-scaffolding approach from Ornith 1.0 into a full self-improvement loop: the model pro…

• 💻 Coding
• 🤖 Agents
• 🔍 Advanced reasoning

DeepReinforce's open-source 397B MoE agentic coding model with FP8 quantization. Built on Qwen 3.5 and RL-trained to jointly optimize scaffolds and solutions, it achieves state-of-the-art performance on Terminal-Bench 2…

• 💻 Coding
• 🐞 Debugging
• 🤖 Agents New

A 35B Mixture-of-Experts reasoning model for agentic coding, post-trained on Qwen 3.5 using a self-improving RL framework that jointly learns solution rollouts and the task-specific scaffolds guiding them. Supports nati…

• 💻 Code generation
• 🤔 Logical reasoning
• 💻 Vibe coding
• 🤖 Ai agents

Ornith Open-source 9B-parameter language model specialized for agentic coding tasks. Post-trained on Qwen 3.5 using a self-improving RL framework that jointly learns to generate solutions and task-specific scaffolds. Ac…

• 💻 Code generation
• 📝 Text generation
• 🤖 Ai agents New

A 397B MoE open-source reasoning model for agentic coding, post-trained on Qwen 3.5 MoE via a self-improving RL framework that jointly learns task solutions and the scaffolds guiding them. Achieves 82.4 on SWE-Bench Ver…

• 🔍 Code analysis
• 🐞 Debugging
• 📚 Large Language Models
• 🤖 Agents
• 💻 Vibe coding New

An FP8-quantized 35B-parameter mixture-of-experts language model specialized for agentic coding. Built on Qwen3.5 MoE, it is trained with a self-improving RL framework that jointly learns to solve coding tasks and gener…

• 💻 Coding
• 🤖 Agents
• 🎯 Code autocompletion New