v0.7.0
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cpp11 min read
goose Blog
Stay updated with the latest developments in Artificial Intelligence
Agents on live hardware: reason where you must, engineer everywhere else
CoreWeave Blog10 min read
b11669
llama.cpp1 min read
Agentic State Machines
goose is replacing its classic agent loop with a re-entrant state machine where the conversation is the state and each behavior is an Operation.
goose Blog5 min readMoving to issues as the new PRs
We’re changing how people contribute to goose by moving design and discussion into issues before agents turn ready issues into code.
goose Blog3 min readSelf-Improving Agents Still Need Humans
Benchmarks are most useful when they become bug reports. Here's how the goose team uses Terminal-bench failures, Harbor, and human judgment to improve real agent behavior.
goose Blog4 min readHooks: run your own scripts on every goose event
goose now supports lifecycle hooks via the Open Plugins spec. Wire shell scripts into PreToolUse, PostToolUse, UserPromptSubmit, SessionStart, and more.
goose Blog5 min readOrchestrate complex workflows across multiple agents with goose
Use goose to coordinate multi-agent workflows — decompose complex tasks, delegate to specialized agents in parallel, and synthesize the results.
goose Blog4 min readApproaching frontier performance for 1/30th the cost
Using goose with MiniMax M2.5 on the Databricks OfficeQA benchmark
goose Blog1 min readBeyond the Terminal: goose Controls Your Desktop with Peekaboo
The Computer Controller extension was rebuilt with Peekaboo, giving goose the ability to see, click, type, and interact with any application on your Mac.
goose Blog4 min readPrivate by Default: Built-in Local Inference Models with goose
goose now ships with built-in local inference powered by llama.cpp — no server, no API key, no cost. Here's how it works and what to expect.
goose Blog3 min readMesh LLM in goose: routing across models
Quick note: Mesh LLM is now in goose as an option for accessing and sharing (open) LLMs with friends and family.
goose Blog1 min readHow to Break Up with Your Agent
ACP lets you keep your favorite editor but swap the AI agent, or keep your agent but use it from any editor. Here's what actually works today in Goose.
goose Blog4 min readgoose 2.0 beta - new architecture and clients
We're shipping a new TUI, rewriting the desktop app in Tauri, and unifying everything under ACP.
goose Blog3 min readgoose has a new home - the Agentic AI Foundation (AAIF)
goose has moved to the Agentic AI Foundation (aaif) at the Linux Foundation
goose Blog1 min readAdversary Agent: using a hidden agent to keep the main agent safe
Introducing adversary mode — an independent agent reviewer that silently watches the main agent to keep it away from danger.
goose Blog3 min readUse Goose with Your AI Subscription
A quick update on using subscriptions for claude, gemini and codex
goose Blog3 min readWebMCP for Beginners
WebMCP lets websites expose structured actions that AI agents can call directly. This guide explains how it works, how it differs from MCP and browser automation, and how to build your own WebMCP-enabled site.
goose Blog7 min readOrder Lunch Without Leaving Your AI Agent
Use the Neighborhood extension in goose to discover nearby restaurants, browse interactive menus, and place a takeout order, all from a simple chat prompt.
goose Blog6 min readGrant Winner: Goose In A Pond
Introducing a privacy-first, local AI home assistant powered by Goose on edge hardware.
goose Blog5 min readgoose v1.25.0: Sandboxed, Streamlined, and More Secure
goose v1.25.0 brings macOS sandboxing, a unified summon extension, rich MCP app UIs, agentic CLI upgrades, and SLSA build provenance.
goose Blog5 min read
Showing 18 of 21 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from goose Blog
Join 15,000+ AI enthusiasts