Ollama
PulseAugur coverage of Ollama — every cluster mentioning Ollama across labs, papers, and developer communities, ranked by signal.
- 2026-05-14 product_launch Ollama released version 0.23.4 with new features and fixes. source
- 2026-05-11 product_launch Ollama released updates including a Web Search API, improved scheduling, and a preview of cloud model integration. source
- 2026-05-11 product_launch Ollama launched a new command, 'ollama launch', simplifying the setup for using AI coding tools like Claude Code with local or cloud models. source
- 2026-05-11 research_milestone Discovery of the critical "Bleeding Llama" vulnerability in Ollama. source
8 day(s) with sentiment data
-
New RAG methods for medical QA show mixed results, with multimodal approach outperforming fine-tuning on larger scales
Researchers have developed MED-VRAG, a novel iterative multimodal retrieval-augmented generation framework that processes medical document page images, including tables and figures, rather than just text. This system ac…
-
AMD R9700 GPU runs local LLMs like Qwen3.6:35b surprisingly fast
A user shared their experience running local AI models on a new setup featuring an AMD R9700 GPU with 32 GB of VRAM. They successfully operated models such as Qwen3.6:35b using Ollama and Openwebui, noting the surprisin…
-
OpenClaw AI agent runs locally, offering privacy but demanding robust hardware
OpenClaw, an open-source AI agent framework, has gained significant traction since its launch in November 2025, quickly amassing over 100,000 GitHub stars. This proactive assistant runs entirely on local hardware, conne…
-
HATS uses debating AI agents to improve decision-making and planning
A new open-source project called HATS has been released, enabling the creation of multi-agent AI systems designed to debate and improve decision-making. Inspired by the Six Thinking Hats framework, HATS assigns distinct…
-
Google's Gemma 4 model surpasses 2 million downloads, driving on-device AI adoption
Gemma 4 has achieved over 2 million downloads in its first week, indicating significant traction for the open model. Its rapid adoption is particularly notable for local and edge deployments, with users successfully run…
-
Google's Gemma 4 26B model runs locally with LM Studio's new headless CLI
Google's Gemma 4 model family, particularly the 26B-A4B variant, is now accessible for local inference on consumer hardware like MacBooks. This mixture-of-experts model activates only a fraction of its parameters per in…
-
Google releases open-weight Gemma 4 multimodal models with long context
Google DeepMind has released Gemma 4, a new family of open-weight models licensed under Apache 2.0, marking a significant advancement in their open-source AI offerings. The models are designed for reasoning and agentic …
-
Axe CLI tool offers composable, Unix-like LLM agents
Axe is a new command-line interface tool designed to manage and execute AI agents, drawing inspiration from Unix philosophy for focused, composable functionality. It allows users to define agents with specific skills us…
-
Axe CLI tool offers composable, Unix-like LLM agent management
Axe is a new command-line tool designed to manage and run AI agents, treating them like small, composable Unix programs. It allows users to define agents with specific skills using TOML files, enabling them to be chaine…
-
AI infrastructure startups launch tools for agents, DevOps, security, and healthcare
Several startups are launching AI-powered tools aimed at improving infrastructure and developer productivity. Trigger.dev offers an open-source platform for building reliable AI agents and workflows, utilizing snapshott…
-
Show HN: OpenSwarm – Multi‑Agent Claude CLI Orchestrator for Linear/GitHub
OpenSwarm is a new command-line interface tool designed to orchestrate multiple AI agents for autonomous code-related tasks. It can integrate with various AI models, including Anthropic's Claude, OpenAI's GPT and Codex,…
-
Anthropic accuses DeepSeek, Moonshot, and MiniMax of "industrial-scale distillation attacks".
Anthropic has accused Chinese AI firms DeepSeek, Moonshot AI, and MiniMax of conducting large-scale "distillation attacks" to extract capabilities from its Claude models. The company alleges that over 24,000 fraudulent …
-
Alibaba's Qwen3.5-397B-A17B model offers multimodal capabilities and efficient inference
Alibaba has released Qwen3.5-397B-A17B, an open-weight, natively multimodal model featuring a hybrid attention mechanism and sparse Mixture-of-Experts architecture. The model boasts support for 201 languages and demonst…
-
Rowboat launches open-source AI coworker that builds knowledge graphs
Rowboat, an open-source AI coworker, has been released, allowing users to create a personal knowledge graph from their work data. This tool connects to email and meeting notes to build a persistent, local knowledge base…
-
Claude Code client offers local AI coding agents with advanced Git integration
A new open-source coding agent client, named 1code, has been released, offering support for multiple models like Claude Code and Codex. It features a Cursor-like desktop interface with integrated Git tools, diff preview…
-
BrowserOS launches as open-source, privacy-focused AI agent browser
BrowserOS has launched as an open-source Chromium fork designed to run AI agents natively within the browser. This privacy-focused alternative allows users to connect their own API keys for various AI providers or run l…
-
OpenAI launches self-serve ads for ChatGPT, targeting $2.5B revenue
OpenAI is beginning to test advertisements within its free tier of ChatGPT in the US, aiming to monetize its large user base. The company has also introduced a new $8/month 'Go' plan, which offers enhanced features and …
-
AI web service combines FastAPI, Pydantic-AI, and MCP for trend analysis
A new open-source web service project, demonstrated on GitHub, combines FastAPI, Pydantic-AI, and Model Context Protocol (MCP) servers to create a scalable AI-powered application. This service allows users to query info…
-
AI service combines FastAPI, Pydantic-AI, and MCP for trend analysis
A new open-source web service, built with FastAPI and Pydantic-AI, integrates Model Context Protocol (MCP) servers to create a scalable AI-powered application. This service allows users to query information from sources…
-
Cactus launches open-source AI engine for mobile devices
Cactus has released an open-source AI engine designed for mobile devices and wearables, prioritizing low latency and reduced RAM usage. The engine supports multimodal capabilities, including speech, vision, and language…