Goose (Block)

https://block.github.io/goose/

Block (Square)'s open-source on-machine agent — terminal + desktop GUI. Modular: extensions for shell, computer-control, MCP servers; multi-model via LiteLLM. Released 2024; positioned as a general-purpose local agent, not coding-only. Goose Recipes provide reusable agent workflows.

At a glance

Type
OSS terminal/desktop agent (Block, Inc.)
Tier
T2
Created
2024-12
Latest release
Goose 1.x rolling
License
Apache-2.0
Pricing
Free (OSS); usage via LLM provider
Funding
Block (parent — public co, NYSE:XYZ)

Taxonomy

storage
file
retrieval
injection
persistence
cross-session
update
user-edit
unit
document
governance
inspectable
conflict
human-arbitrate

When to use

Optimised for: general-purpose local agent + Goose Recipes

Anti-fit: smaller community than Claude Code / Aider; documentation thinner

Pros & cons

Pros

Block's open-source commitment + Goose Recipes give a clean YAML-templated agent-workflow story; Rust core keeps it fast.

Cons

Younger and smaller than Aider/Claude Code; less coding-specific tuning than dedicated coding agents.

Claims & capabilities

Built by Block; ~14k★ GH; multi-model via LiteLLM; extensible via MCP and Goose Recipes.

Technical surface

API surface
CLI (Rust) + desktop GUI; MCP
Backend storage
local config + extensions
Deployment
Self-host (CLI + desktop)
Embedding model
not applicable — not a memory product
Multi-tenancy
single-user (desktop)
MCP
native — Goose is an MCP client
A2A
searched not found
OpenTelemetry
searched not found

Similar systems

Other agent ides & coding harnesses in the catalog, ranked by inbound references.

  • Bedrock AgentCore (AWS) T2

    AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).

  • Claude Code (Anthropic) T1

    Anthropic's official agentic coding CLI — runs Claude as a long-running coding agent in the developer's terminal. Memory layer = CLAUDE.md (project + user scoped), agent skills, MCP servers. Released GA October 2024; widely adopted as the reference harness for Claude-as-coder. Plan Mode and Compute Use surfaces extend it from coding to broader desktop automation.

  • GitHub Copilot (Agent Mode) T1

    The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.

  • Aider (harness) T2

    OSS terminal coding agent by Paul Gauthier — one of the original AI-pair-programmer CLIs (2023). Architect/Editor modes; repo-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited markdown. Distinct from the separate Aider memory-row in "Coding-agent memory"; this row characterises the harness itself.

  • Amazon Q Developer T1

    Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troubleshoot IAM, suggest AWS-SDK code. Companion to Kiro for spec-driven flows.

  • Anthropic Computer Use T1

    Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.

Related systems

References (2)

  • LiteLLM depends on at runtime — adjacent-infrastructure cell: LiteLLM for multi-model routing; MCP for tool integrations; Block-internal extensions (square/cash app workflows)
  • Model Context Protocol (MCP spec) depends on at runtime — adjacent-infrastructure cell: LiteLLM for multi-model routing; MCP for tool integrations; Block-internal extensions (square/cash app workflows)

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.