Coding Tools
OpenAI Codex Integrates with Ollama Models
Ollama Blogmedium confidence
Why it matters
- →This development enhances the capabilities of Codex by allowing users to leverage open-weight models for coding tasks.
Ollama has announced that OpenAI's Codex CLI can now utilize open models, allowing it to read, modify, and execute code in users' working directories. This integration supports models like gpt-oss:20b and gpt-oss:120b.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1New coding models & integrations released
Ollama Blog · October 16, 2025 · Background
- 2OpenAI Launches gpt-oss-safeguard Models
Ollama Blog · October 29, 2025 · Related
- 3OpenAI Releases GPT-5.2 Model
AI Explained · December 12, 2025 · Background
- 4OpenAI Plans New Model Release in 2024
AI Explained · December 12, 2025 · Background
What happened next
- 5OpenAI Updates Codex with Superapp Features
The Rundown AI · April 17, 2026 · Related
- 6OpenAI Codex Update Enhances Functionality
The AI Advantage · May 1, 2026 · Related
- 7OpenAI Develops Secure Sandbox for Codex on Windows
OpenAI · May 13, 2026 · Related
- 8Codex Now Accessible via ChatGPT Mobile App
OpenAI · May 14, 2026 · Related
- 9OpenAI's Codex Now Available on Mobile
TechCrunch AI · May 14, 2026 · Related
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
llama.cpp Releases