#hugging face
Loot, blog posts and adjacent themes connected to this topic. Follow the tag to keep it in your orbit.
More from this topic
When the community shares matching finds, they will appear here. For now, browse all loot or submit the first drop.
Related reads
Hugging Face Shows How to Benchmark Whether Tools Are Agent-Friendly
Hugging Face published an agent-evaluation harness that tests whether coding agents can use a library efficiently, not only whether they rea…
GLM-5.2 brings a 1M-token context to open coding agents
Z.ai released GLM-5.2 on Hugging Face with a claimed 1M-token context, MIT licensing, and long-horizon coding-agent benchmarks to verify bef…
Kimi K2.7 Code ships as an open coding model for long agent runs
Moonshot AI's Kimi K2.7 Code is now available as an open-weight coding model on Hugging Face, with Kimi docs, Product Hunt, and Cloudflare W…
Hugging Face Serge puts AI code review inside GitHub pull requests
Hugging Face released Serge, an open-source GitHub-native AI code reviewer that follows repository-owned review rules and works with OpenAI-…
OpenEnv gets broader open-source backing for agentic RL environments
Hugging Face says OpenEnv is moving under broader open-source coordination, positioning it as a protocol layer for agentic reinforcement lea…
Agents' Last Exam tests AI agents on real professional workflows
Agents' Last Exam is a new Berkeley-led benchmark for computer-use AI agents, with long-horizon professional tasks, verifiable outcomes, pub…
Hugging Face benchmark tests voice agents on code-switched customer speech
ServiceNow-AI published a Hugging Face benchmark and dataset for code-switched ASR, testing how voice-agent transcription handles Spanish-En…
Optimum Intel 2.0 Makes OpenVINO the Default Path for Local Open Models
Hugging Face's Optimum Intel 2.0 shifts the library to an OpenVINO-first toolkit, simplifying installs and focusing local inference, export,…
Cohere North Mini Code Gives Agent Builders a 30B Open Coding Model
Cohere released North Mini Code, a 30B-parameter sparse MoE coding model with 3B active parameters, Apache 2.0 weights, and training focused…
Hugging Face Transformers CVE-2026-4372 Turns Model Loading Into a Security Checkpoint
NVD lists CVE-2026-4372 as a critical Transformers remote code execution issue affecting versions before 5.3.0, and independent reporting sa…
Hugging Face rebuilt the hf CLI for coding agents, not just humans
Hugging Face says its hf CLI now detects coding agents, changes command output for machine parsing, and can cut token use on complex Hub wor…
Holo3.1 pushes computer-use agents toward local deployment
H Company released Holo3.1, a computer-use model family that adds mobile support, function calling, smaller model sizes, and quantized check…
JetBrains Mellum2 ships as an open MoE model for coding agents
JetBrains released Mellum2, an Apache-2.0 open-weight 12B Mixture-of-Experts model built for software engineering, routing, RAG, and low-lat…
LongTraceRL trains long-context reasoning from search-agent trajectories
LongTraceRL uses search-agent trajectories, tiered distractors, and entity-level rubric rewards to improve long-context reasoning across fiv…
Hugging Face’s AI agent glossary makes harness, scaffold, and skills easier to compare
Hugging Face’s new agent glossary turns fuzzy agent terminology into a practical checklist for choosing frameworks, skills, memory, and tool…
OpenAI Privacy Filter brings on-device PII masking to Hugging Face workflows
OpenAI Privacy Filter is a Hugging Face model card for bidirectional token classification that detects and masks PII, giving teams a local o…
NVIDIA Nemotron 3 Nano Omni targets long-context document, audio, and video agents
NVIDIA's Nemotron 3 Nano Omni release on Hugging Face points to a practical open model lane for agents that need to reason across documents,…
DeepSeek-V4 brings million-token context closer to practical agent workflows
DeepSeek-V4 combines new MoE checkpoints with 1M-token context and attention changes aimed at making long-running agent tasks less memory-he…
The Open Agent Leaderboard compares full AI agent systems, not just models
IBM Research and Hugging Face introduced the Open Agent Leaderboard, an open benchmark stack for comparing complete AI agent systems across …
Hugging Face Transformers v5.8 is a dependency upgrade worth testing, not rushing
Transformers v5.8 brings recent model-support updates, but production teams should pin, test, and verify before upgrading AI workflows.
IBM Granite Embedding Multilingual R2 lands with 32K context and a compact 97M retrieval model
IBM’s new Granite Embedding Multilingual R2 release adds two Apache 2.0 embedding models with 32,768-token context, 200-plus language covera…
DeepInfra joins Hugging Face Inference Providers and expands the practical model menu for teams that want API flexibility
Hugging Face has added DeepInfra to its Inference Providers lineup, giving developers another routed option for model access through the sam…
Granite 4.1 details how IBM trained its new open 3B, 8B, and 30B models
IBM’s Granite 4.1 release explains a five-phase 15T-token training pipeline, 512K context extension, Apache 2.0 licensing, and why its dense…
Hugging Face is turning Reachy Mini into an app-store robot platform
Hugging Face says its Reachy Mini ecosystem now includes an agentic app store for nearly 10,000 robots, with 200-plus apps and more than 150…
Cohere Transcribe lands on Hugging Face as a 2B open-source ASR release
Cohere has open-sourced a 2B speech recognition model on Hugging Face and is framing it as a production-minded ASR release with strong Engli…
huggingface_hub 1.14.0 adds Space secrets management and pushes Hub automation further into the CLI
Hugging Face’s latest huggingface_hub release matters less for a single flashy feature than for how it keeps turning the Hub CLI into a real…
Ling-2.6-1T is making a serious case for useful intelligence per token
Ling-2.6-1T is not just another open model launch. Its trillion-parameter scale, execution-first positioning, and lower-token-overhead strat…