Ollama v0.15.4 — Release Notes & Engineering Impact
Ollama v0.15.4. Source highlight: `ollama launch openclaw` will now enter the standard OpenClaw onboarding flow if this has not yet been completed.
1172 tracked entries. Older history is imported progressively; see source coverage.
Ollama v0.15.4. Source highlight: `ollama launch openclaw` will now enter the standard OpenClaw onboarding flow if this has not yet been completed.
Ollama v0.15.3. Source highlight: Renamed `ollama launch clawdbot` to `ollama launch openclaw` to reflect the project's new name
vLLM v0.15.0. Source highlight: This release features 335 commits from 158 contributors (39 new)!
Ollama v0.15.2. Source highlight: New `ollama launch clawdbot` command for launching Clawdbot using Ollama models
Hugging Face Transformers v5.0.0. Source highlight: Transformers v5 release notes
Ollama v0.15.1. Source highlight: GLM-4.7-Flash performance and correctness improvements, fixing repetitive answers and tool calling quality
vLLM v0.14.1 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
LangChain langchain==1.2.7. Source highlight: Changes since langchain==1.2.6
LocalAI v3.10.1. Source highlight: This is a small patch release intended to provide bugfixes and minor polishment, along, we also added support to Qwen-TTS that was just released yesterday.
Ollama v0.15.0. Source highlight: A new `ollama launch` command to use Ollama's models with Claude Code, Codex, OpenCode, and Droid without separate configuration.
vLLM v0.14.0. Source highlight: **Breaking Changes:**
LocalAI v3.10.0. Source highlight: 🎉 LocalAI 3.10.0 Release! 🚀
Ollama v0.14.3. Source highlight: Z-Image Turbo: 6 billion parameter text-to-image model from Alibaba’s Tongyi Lab. It generates high-quality photorealistic images.
LangChain langchain==1.2.6. Source highlight: Changes since langchain==1.2.5
LangChain langchain==1.2.5. Source highlight: Changes since langchain==1.2.4
Hugging Face Transformers v4.57.6. Source highlight: Another fix for qwen vl models that prevented correctly loading the associated model type - this works together with https://github.com/huggingface/transformers/pull/41808 of the previous patch release.
Ollama v0.14.2. Source highlight: TranslateGemma: A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.
Dify 1.11.4. Source highlight: Dify now requires Node.js 24.13.0 to pick up the upstream fix for the AsyncLocalStorage/async_hooks DoS CVE that can crash apps with deeply nested input. **All self-hosted deployments should upgrade Node.js**. Thanks to @hyoban in #30945.
LangChain langchain==1.2.4. Source highlight: Changes since langchain==1.2.3
Ollama v0.14.1. Source highlight: Image generation models (experimental)
Hugging Face Transformers v4.57.5. Source highlight: Should not have said last patch :wink: These should be the last remaining fixes that got lost in between patches and the transition to v5.
Hugging Face Transformers v4.57.4. Source highlight: Last patch release for v4: We have a few small fixes for remote generation methods (e.g. group beam search), vLLM, and an offline tokenizer fix (if it's already been cached).
Dify 1.11.3. Source highlight: 🚀 What's New in v1.11.3?
Open WebUI v0.7.2. Source highlight: [0.7.2] - 2026-01-10
Ollama v0.14.0. Source highlight: `ollama run --experimental` CLI will now open a new Ollama CLI that includes an agent loop and the `bash` tool
Open WebUI v0.7.1. Source highlight: [0.7.1] - 2026-01-09
Open WebUI v0.7.0. Source highlight: [0.7.0] - 2026-01-09
LangChain langchain==1.2.3. Source highlight: Changes since langchain==1.2.2
LangChain langchain==1.2.2. Source highlight: Changes since langchain==1.2.1
LangChain langchain==1.2.1. Source highlight: Changes since langchain==1.2.0
Dify 1.11.2. Source highlight: 🌟 What’s New in v1.11.2 🌟
LocalAI v3.9.0. Source highlight: Xmas-release :santa: **LocalAI 3.9.0**! 🚀
Open WebUI v0.6.43. Source highlight: [0.6.43] - 2025-12-22
Open WebUI v0.6.42. Source highlight: [0.6.42] - 2025-12-21
vLLM v0.13.0. Source highlight: vLLM v0.13.0 Release Notes Highlights
Ollama v0.13.5. Source highlight: Google's FunctionGemma a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
LangChain langchain==1.2.0. Source highlight: Changes since langchain==1.1.3
Ollama v0.13.4. Source highlight: Nemotron 3 Nano: A new Standard for Efficient, Open, and Intelligent Agentic Models
Dify 1.11.1. Source highlight: This version contains **very important security updates**, and we recommend that all users upgrade to this version as soon as possible.
Dify 1.11.0. Source highlight: 🧠 Multimodal Knowledge Base
Ollama v0.13.3. Source highlight: Devstral-Small-2: 24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
LangChain langchain==1.1.3. Source highlight: Changes since langchain==1.1.2
Dify 1.10.1-fix.1. Source highlight: For users who upgraded to version 1.10.1-fix.1 before 2025-12-09 03:00:00 UTC, please verify your docker compose configuration to ensure the web service is using the correct image version langgenius/dify-web:1.10.1-fix.1. This verification is critical to address the https://github.com/advisories/GHS
LangChain langchain==1.1.2. Source highlight: Changes since langchain==1.1.1
LangChain langchain==1.1.1. Source highlight: Changes since langchain==1.1.0
Ollama v0.13.2. Source highlight: Qwen3-Next: The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
vLLM v0.12.0. Source highlight: vLLM v0.12.0 Release Notes Highlights
Open WebUI v0.6.41. Source highlight: [0.6.41] - 2025-12-02
Ollama v0.13.1. Source highlight: Ministral-3: The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
LocalAI v3.8.0. Source highlight: Welcome to **LocalAI 3.8.0** !