Open source
Libraries, tools and repos: releases you depend on and projects gaining stars.
llm-openai-decisions 0.1a0
OpenAI released their new Jev-style Decisions API, as previously announced at last week's DevDay.
VideoParameter Golf with AutoResearch — Vayum Arora, Zhengyao Jiang, Dixing Xu & Dhruv Srikanth, Weco AI
Zhengyao Jiang introduces autoresearch as repeated proposals and evaluations, and Dixing Xu explains the team's Aiden system and its contributions to OpenAI's Parameter Golf challenge.
Converting dense models into Mixture-of-Experts
For the past few weeks I've been trying out converting existing dense models to sparse Mixture-of-Experts models, with no pretraining from scratch.
Asana cuts model costs 76x in browser tests with GPT-6.1 Sol
Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.
langchain-ai/langchain langchain-openai==1.7.0
chore(deps): bump langgraph-sdk from 0.4.4 to 0.4.6 in /libs/partners/openai (#41096)
unslothai/unsloth v0.1.905-beta: Sandboxing is here!
We're introducing Windows, Mac and Linux sandboxing in Unsloth!
huggingface/transformers v5.19.0: Release v5.19.0
EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture.
langchain-ai/langgraph cli==0.4.33: langgraph-cli==0.4.33
feat(cli): add 'langgraph deploy listeners list' (#9221)
huggingface/trl v1.14.2
Patch release fixing two cases of silently wrong training and three crashes.
Mia-AiLab/GLM-5.3-Flash-EXL3-4bpw-TensorFold-Ablit
Mia-AiLab published the model GLM-5.3-Flash-EXL3-4bpw-TensorFold-Ablit on Hugging Face.
langchain-ai/langchain langchain==1.4.4
chore(deps): bump langgraph-sdk from 0.4.2 to 0.4.4 in /libs/langchainv1 (#41074)
langchain-ai/langchain langchain-core==1.6.9
feat(core): accept a callable in withretry (#41158)
ttok 0.4
ttok is my CLI tool for counting tokens, using OpenAI's open source tiktoken library.
langchain-ai/langchain langchain-huggingface==1.2.3
chore(deps): bump langgraph-sdk from 0.4.4 to 0.4.6 in /libs/partners/huggingface (#41098)
unslothai/unsloth v0.1.904-beta: Train your own Decision model
Turn any text or vision LLM into a Jev-style decision model in Unsloth, with decision accuracy going from 30% to 80%.
langchain-ai/langchain langchain-fireworks==1.7.1
chore(deps): bump langgraph-sdk from 0.4.4 to 0.4.6 in /libs/partners/fireworks (#41100)
langchain-ai/langgraph sdk==0.4.6: langgraph-sdk==0.4.6
fix(sdk-py): percent-encode threadid and assistantid in thread stream requests (#9213)
unslothai/unsloth v0.1.903-beta: New Browser + Voice Cloning
This release adds a browser inside Unsloth (browser use coming very soon), so files, web pages and pages the model writes open right beside your chat.
langchain-ai/langgraph 1.2.13: langgraph==1.2.13
fix(langgraph): fork before replaying an update checkpoint the thread moved past (#9170)