OPEN SOURCE

→ View original post on X — @abacusai

Open Source LLMs Excelling with ChatLLM Auto-Selection Feature

By

@abacusai

–

15 February 2026 19h05

Open source LLMs are CRUSHING it right now! Kimi K2, GLM-5 leading the pack Why choose one when you can have the best of both worlds? ChatLLM auto-selects the perfect model for your task—open OR closed source Maximum efficiency, zero hassle

→ View original post on X — @jeremyphoward

Impressive coding results in AI development

By

@jeremyphoward

–

15 February 2026 6h28

Coding results look impressive too. Anyone tried this yet?

→ View original post on X — @elliotchen100

Aliyun Tongyi Launches CoPaw Open-Source Personal AI Assistant

By

@elliotchen100

–

15 February 2026 5h40

Check this out, the full-scenario personal assistant CoPaw under Aliyun's Tongyi Yep, it's exactly because we saw the hype around @openclaw that we came up with this. In theory, it's more friendly to domestic IMs, supports Skills, self-hosting, and is open-source friendly

→ View original post on X — @elliotchen100

Firecrawl: Open-Source Web Data API for AI

By

@elliotchen100

–

15 February 2026 2h01

Sharing a library from the Firecrawl family: "crawler + rendering + parsing + extraction" — the entire chain packaged into a Web Data API for AI use. Open-source, self-deployable, with 82K stars on GitHub. This library mainly converts entire websites into LLM-ready markdown or

LTX-2: Open-Source Model with 3.3M Downloads in One Month

By

–

14 February 2026 20h39

https://t.co/BbJXl2NWd7
— Linus ✦ Ekenstam (@LinusEkenstam) 14 février 2026

+3.3 Million downloads in 1 Month Yet most people are sleeping on LTX-2 plus the fact that its Open-Source
That's right, you can even run it at home, at the cost of electricity. Let's dig into why I think you should spend some time with this model. A thread

→ View original post on X — @julien_c

LanceDB and Hugging Face Partner for Vector Storage

By

@julien_c

–

14 February 2026 12h24

in case you missed it @lancedb and HF are partnering up to unlock the next generation of large dataset storage on the Hub And it's fire! – Supports storing embeddings (and their indexes) directly alongside the data
– Vector search / similarity search is built-in
– Large

Local models closing fast on Seedance 2.0 quality

By

–

14 February 2026 10h17

Yes, even with seedance 2.0 running ahead, the fact that we have these models locally at this quality right now shows the gap is indeed closing fast. I see some incredible stuff around the internet

Download or clone repo for open source video and audio model

By

–

14 February 2026 9h26

You can download now, or clone the repo, explore the bleeding edge of Open Source and Audio model from @ltx_model

Workflow: one photo to multiple angles cinematic video

By

–

14 February 2026 9h25

Workflows that you might be used to with closed source models, like nanobanana pro etc can now be achieved through mixing different providers.

Here us an example of:

One photo → multiple camera angles → cinematic video

video from: @FloyoAI pic.twitter.com/0pbcZIyDP4
— Linus ✦ Ekenstam (@LinusEkenstam) 14 février 2026

Workflows that you might be used to with closed source models, like nanobanana pro etc can now be achieved through mixing different providers. Here us an example of: One photo → multiple camera angles → cinematic video video from: @FloyoAI