Codename Goose: An open source local AI agent built on MCP
summary
Goose is an open‑source local AI agent that runs locally and connects to any LLM that supports tool calling, using 1,700+ MCP servers as extensions. It actually edits files, runs tests, executes shell commands, creates repos and PRs, scrapes data, and integrates with JetBrains, VS Code, Google Drive and Figma. Comes as desktop app and CLI, includes developer, memory and web‑controller MCP servers, and shows concrete demos of edits files and runs tests working end to end.
AI-written summary · about
chapters (7)
- 0:00Introduction to Goose
- 2:48How the agent works
- 3:56Tool usage and demo
- 6:34The agent ecosystem
- 8:00Extension examples
- 9:01Running Goose
- 10:40LLM support and community
related talks
24mGoose: an open source AI agent
27mThe accidental AI revolution
22mNext-Gen AI Tooling with MCP Servers in Go
36mPutting AI Agents to Work: A New Era of Open Source Connectivity with MCP
37mHow We Red-Teamed Our Own AI Agent: Lessons from... (Josiah Peedikayil, HS)
45mPowering AI Agents with Temporal and Kgoose
29mModern Day Mashups: AI Agents are Reviving the Programmable Web
45mAgents, Tools, and MCP, oh my! Next-level AI concepts for developers