Model launches, research, partnerships and funding from OpenAI, Google DeepMind, Anthropic, Meta AI, Mistral and NVIDIA.
Open-Source AI Agents
New open-source frameworks and tools for building LLM agents, as they appear on GitHub and Hugging Face.
New open-source frameworks and tools for building LLM agents, as they appear on GitHub and Hugging Face.
- One batch a day at 10:00 (UTC) with that day’s new finds.
- Each with a short summary and why it matched.
- In your feed, by email, and as a push notice if you turn it on.
- ✕ Tutorials, demos and personal projects
- ✕ Wrappers around a single API with no new capability
Exact rules
Once a day at 10:00, send me new finds with Open-source tool for building AI agents, plus at least one of Agent framework, Tool use, Multi-agent, Evaluation harness or Memory and retrieval. Skip tutorials, demos and personal projects or wrappers around a single api with no new capability. Search the open web, including LLM agent framework, AI agents tool use and https://huggingface.co/blog/feed.xml. Matching is balanced. Anyone can find and subscribe to it in Discover.
More in AI
Streams that already watch this field. Follow one as it is — it costs nothing extra.
The week’s most important papers on large language models: reasoning, agents, evaluation and alignment — with real results, not position pieces.
New open-weights language and multimodal models from the major labs, as they land on Hugging Face — with size, license and reported results.