LangChain langchain==1.3.6 — Release Notes & Engineering Impact
LangChain langchain==1.3.6. Source highlight: Changes since langchain==1.3.5
1172 tracked entries. Older history is imported progressively; see source coverage.
LangChain langchain==1.3.6. Source highlight: Changes since langchain==1.3.5
LangChain langchain==1.3.5. Source highlight: Changes since langchain==1.3.4
Ollama v0.30.7. Source highlight: Ollama Launch now supports Hermes Desktop, a native desktop interface for the Hermes agent. Run it alongside your Hermes agent to get a visual interface for managing conversations, integrations, and messaging apps.
Ollama v0.30.6. Source highlight: Gemma 4 QAT weights: the Gemma 4 family is now optimized with Quantization-Aware Training (QAT) to dramatically reduce memory requirements and maximize on-device performance. Look for the tags ending in `-qat`:
vLLM v0.22.1. Source highlight: This release features 8 commits from 6 contributors (1 new)!
Hugging Face Transformers v5.10.2. Source highlight: Patch release v5.10.2
Ollama v0.30.5. Source highlight: Fixed the `gemma4:12b` floating point exception crash on x86, CUDA, Linux, and Windows systems.
Ollama v0.30.4. Source highlight: Nemotron-3-Ultra: NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
Ollama v0.30.3. Source highlight: Gemma 4 12B: high-performance multimodal intelligence that runs directly on laptops, combining efficiency with advanced reasoning.
Hugging Face Transformers v5.10.1. Source highlight: v5.10.0 was yanked as we publish on a corrupted branch. Sorry everyone, this happens when we rush a release!!!
Ollama v0.30.2. Source highlight: `ollama launch` now supports Qwen Code and can guide users through installing the Cline CLI when it is missing.
LangChain langchain==1.3.4. Source highlight: Changes since langchain==1.3.3
LangChain langchain==1.3.3. Source highlight: Changes since langchain==1.3.2
Open WebUI v0.9.6. Source highlight: 📦 **Official knowledge base sync tool.** A new companion tool from Open WebUI, oikb, keeps a knowledge base in sync with a local directory, GitHub repo, S3 bucket, Confluence space, or any of more than 40 other sources, uploading only new and changed files using the incremental sync support added in
LocalAI v4.3.6. Source highlight: chore: :arrow_up: Update ggml-org/llama.cpp to `22d66b567eef11cf2e9832f04db64ee0323a0fd0`
LocalAI v4.3.5. Source highlight: fix: tool-call JSON leaks into content with stream+tools on tokenizer-template models (#10052)
vLLM v0.22.0. Source highlight: This release features 459 commits from 230 contributors (63 new)!
LocalAI v4.3.4. Source highlight: fix(turboquant): guard upstream-only grpc-server fields for fork
LocalAI v4.3.3. Source highlight: chore: :arrow_up: Update ikawrakow/ik_llama.cpp to `3bf7e836c2c5a895e8d12d3eb7e398ae7ab2f9ce`
LocalAI v4.3.2. Source highlight: chore(deps): bump github.com/nats-io/nats.go from 1.50.0 to 1.52.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/10003
LangChain langchain==1.3.2. Source highlight: Changes since langchain==1.3.1
LocalAI v4.3.1. Source highlight: Fix kokoros backend build break from Backend trait drift
LocalAI v4.3.0. Source highlight: 🎉 LocalAI 4.3.0 Release! 🚀
Hugging Face Transformers v5.9.0. Source highlight: Command A+ is a Mixture-of-Experts (MoE) language model from Cohere that features a hybrid attention pattern combining sliding window and full attention layers. The model incorporates both shared and routed experts and supports a very large context window for processing extensive text sequences.
Dify 1.14.2. Source highlight: 🚀 What's New in v1.14.2?
LocalAI v4.2.6. Source highlight: feat(llama-cpp): bump to MTP-merge SHA and automatically set MTP defaults
LocalAI v4.2.5. Source highlight: fix(ollama): guard nil filter in galleryop.ListModels (#9817)
LangChain langchain==1.3.1. Source highlight: Changes since langchain==1.3.0
vLLM v0.21.0. Source highlight: This release features 367 commits from 202 contributors (49 new)!
Ollama v0.24.0. Source highlight: Ollama 0.24 includes support for the Codex App, OpenAI's desktop experience for working on Codex threads in parallel with built-in worktree support and git functionality.
LocalAI v4.2.4. Source highlight: fix(distributed): cascade-clean stale node_models rows + filter routing by healthy status
Ollama v0.23.4. Source highlight: `ollama launch opencode` now supports vision models with image inputs
Ollama v0.30.0. Source highlight: Ollama 0.30 is now available, with improved compatibility and performance using llama.cpp. This augments the MLX engine on Apple Silicon, bringing support to a wider range of hardware.
Hugging Face Transformers v5.8.1. Source highlight: Patch release v5.8.1
LocalAI v4.2.3. Source highlight: chore: :arrow_up: Update ggml-org/whisper.cpp to `338cce1e58133261753243802a0e7a430118866d`
LocalAI v4.2.2. Source highlight: fix: parse vulkan VRAM from text
LangChain langchain==1.3.0. Source highlight: This release adds support for `version="v3"` in `stream_events` / `astream_events` for `langchain` agents. Refer to the event streaming guide for details.
Dify 1.14.1. Source highlight: 🚀 What's New in v1.14.1?
Ollama v0.23.3. Source highlight: mlx: refined model push behavior
LocalAI v4.2.1. Source highlight: Exciting New Features 🎉
LocalAI v4.2.0. Source highlight: 🎉 LocalAI 4.2.0 Release! 🚀
Open WebUI v0.9.5. Source highlight: 🛡️ **Redirect-based SSRF protection.** All outbound HTTP requests now block 3xx redirects by default via a new `AIOHTTP_CLIENT_ALLOW_REDIRECTS` environment variable, preventing redirect-based SSRF where a public URL silently redirects to internal addresses (RFC 1918, loopback, cloud-metadata endpoin
vLLM v0.20.2. Source highlight: This release features 6 commits from 6 contributors (0 new)!
Open WebUI v0.9.4. Source highlight: 📜 **Chat scroll position on load.** Opening a chat conversation now reliably scrolls to the bottom of the message history, fixing a regression caused by `content-visibility: auto` where estimated element sizes prevented the initial scroll from reaching the true bottom.
Open WebUI v0.9.3. Source highlight: 🔇 **Voice Mode mute control.** Voice Mode now includes a dedicated mute toggle with an "M" shortcut and auto-unmute after assistant playback, so you can prevent accidental interruptions from background noise without leaving the call overlay. Commit, #23832
LangChain langchain==1.2.18. Source highlight: Changes since langchain==1.2.17
Ollama v0.23.2. Source highlight: `ollama launch` no longer includes Claude Desktop due to the third-party integration being limited to Anthropic models.
LangChain langchain==0.3.30. Source highlight: Changes since langchain==0.3.29
LangChain langchain==1.3.0a2. Source highlight: release(langchain): 1.3.0a2 (#37225)
LangChain langchain==0.3.29. Source highlight: Changes since langchain==0.3.28