IBM’s AISteer360 Empowers Safe and Customizable LLM Outputs As large language models (LLMs) become increasingly sophisticated, so does the challenge of ensuring their outputs remain safe, relevant, and trustworthy especially in high-stakes enterprise environme... AI safety AISteer360 AI steering enterprise AI generative AI large language models model alignment open source
Sentence Transformers Joins Hugging Face: What This Means for NLP Innovation The Sentence Transformers library, a staple in natural language processing, is officially joining the Hugging Face ecosystem. This move marks a significant leap for both the tool and the community, as... community embeddings Hugging Face machine learning NLP open source semantic search Sentence Transformers
Toucan Dataset: Transforming AI Agents Into Digital Doers Toucan, a groundbreaking open-source dataset from IBM and the University of Washington is crafted to propel tool-calling capabilities in large language models (LLMs) to new heights. For AI to move bey... AI agents API integration benchmarking large language models machine learning open source tool-calling Toucan dataset
LangChain and LangGraph 1.0: Powering the Next Generation of AI Agents AI agent development just got a major upgrade. With the release of LangChain and LangGraph 1.0, developers now have access to more stable, flexible, and high-performance frameworks. These releases are... agent frameworks AI agents LangChain LangGraph LLM integration middleware open source
IBM's Lightweight AI Models Are Transforming Earth Observation from Satellites to Smartphones Thanks to IBM Research, NASA, and ESA, who have released compact, open-source versions of their Prithvi and TerraMind AI models researchers can access powerful Earth observation AI. These streamlined ... AI models disaster response Earth observation edge computing environmental monitoring geospatial AI open source satellite technology
vLLM TPU’s Unified Backend is Revolutionizing LLM Inference The latest vLLM TPU release is enabling developers to run open-source LLMs on TPUs with unmatched performance and flexibility. Powered by the tpu-inference backend, this innovation ensures a smooth, h... attention kernels JAX LLM inference open source PyTorch TPU tpu-inference vLLM
ROMA: A Recursive Roadmap for Multi‑Agent Systems ROMA (Recursive Open Meta-Agents) is an open-source framework from Sentient that turns complex goals into structured, parallelizable work. It does this by recursively decomposing tasks and orchestrati... agents Agno E2B fastapi goofys LiteLLM LLM multi-agent open source python research
ROMA: The Backbone for Open-Source Meta-Agents ROMA, short for Recursive Open Meta-Agents , is an open-source meta-agent framework from Sentient that turns long, messy goals into clear, solvable task trees. It gives developers a repeatable way to ... AI agents E2B Firecrawl GRID Kimi Researcher meta-agent open source recursive planning Sentient SimpleQA
AGENTS.md: OpenAI's Tiny File Trying To Standardize Agentic Coding Every now and then, a small convention quietly moves an ecosystem forward. AGENTS.md, a single markdown file placed in a repo, aims to give coding agents consistent, project-specific guidance without ... agentic coding Android Studio Copilot GitHub Next.js open source Semgrep standardization Warp
IBM's Granite Docling: A Compact VLM for End-to-End Document Conversion Background: Docling's Journey Docling addresses a persistent bottleneck in AI workflows: converting messy, unstructured PDFs and scans into clean, structured, model-ready data. In its first year, the ... data extraction docling document ai granite docling ocr open source rag vision-language
GitHub Copilot CLI: AI-Powered Coding Now in Your Terminal Yet another Ai CLI tool? Ye it is! The new GitHub Copilot CLI developer tool imagines AI as collaborator that truly understands your code and your GitHub workflow, working right alongside you in your ... AI development automation CLI developer tools GitHub Copilot open source productivity terminal
Paper2Agent: Transforming Research Papers into Interactive AI Agents Research papers are traditionally require readers and reviewers to interpret code, methods, and results independently. Paper2Agent aims to transform published research into interactive AI agents allow... AgentScope AI agents AutoGen Azure AI Agents Claude Code Code2MCP computational biology LangGraph MCP NotebookLM OpenAI Assistants OpenDevin open source reproducibility Stanford tutorial extraction