AI Briefing#ollama
The latest AI and developer news about #ollama, with the original source and a short summary.
The latest AI and developer news about #ollama, with the original source and a short summary.
It's a caching proxy tool that saves GPU resources by preventing redundant computation for embedding models like Ollama.
Ollama has raised $65 million in a Series B round, accelerating its push into the enterprise AI agent market.
A CLI tool has been released that saves responses from local Ollama models and makes it easy to compare performance across models.
A menu bar app has been released that lets you explore Hugging Face models on Mac and manage them with Ollama, MLX, and more.
An open-source tool called swm has been released that automatically installs AI frameworks on cloud GPUs and syncs work environments to S3.
Skales, a local AI agent connecting directly to Ollama and optimized for privacy protection and low-spec environments, has been released.
It's an MCP-based plugin that delegates heavy code generation tasks to a local LLM to reduce token consumption in Claude Code and Codex CLI.
Ollama has switched from a GGML-based build to direct llama.cpp support.
Hugging Face has released ml-intern, a tool for agents that controls ML libraries using local models.
You can integrate Claude Code with Ollama models via the open-source LLM router Manifest to reduce costs.
Hermes Agent was introduced as a self-improving local AI agent for NVIDIA RTX PCs and DGX Spark.
Ollama has added context length, parameter count, and quota usage information to model cards.
Visual Studio Insiders has updated its AI coding support feature to work with custom models such as Ollama.
MiniCPM has released MiniCPM-V 4.6, unveiling a 1.3B vision-language model for mobile use.
A memory leak causing data exposure and a remote code execution (RCE) risk via Windows Update have been discovered in Ollama.
Ollama vulnerabilities reveal prompt/API key leakage and potential Windows RCE.
Ollama has acknowledged a usage limit overage issue caused by a model hosting caching error and is issuing refunds.
cdo, an open-source tool that lets you use local Ollama models while keeping the Claude Desktop UX, has been released.
A vulnerability in Ollama's GGUF processing allowed process memory, prompts, and environment variables to be leaked without authentication.
Thoth, a local-first AI assistant, has announced the v3.20.0 update, which includes Linux support and MiniMax integration.
claudely, an open-source tool that lets you connect local LLMs while keeping Claude Code's ecosystem, has been released.
On a Mac Mini M4 Pro 64GB, the 14B dense model hit 16.2 t/s, while Qwen3.6 35B NVFP4 reached 69.8 t/s.
On MBP M3 Max benchmarks, the gap between three Qwen3.6 variants and gpt-oss:120b was revealed.
Plano 0.4.22 adds a local TUI for checking cost and request counts, plus Ollama support.