AI visibility report
AI visibility report for Block (Goose) in Autonomous Coding Agents.
Outside the top three on 13 of the 25 prompts buyers actually ask.
Augment Code is cited on 6 of those losses.
Free trial. Setup comes pre-filled for Block (Goose).
Track Block (Goose) across these prompts daily.
Start free trialStill absent from 96.8% of tracked prompt responses
Top-3 citations across 125 prompt × platform pairs
Peer Ranking
Key Metrics
Platform Breakdown
Gemini Search
ChatGPT
Bing Copilot
Perplexity
Google AI ModeHow to read this. Block (Goose) appears in 3.2% of tracked prompt responses. Presence is absolute coverage; share of voice is relative citation share; sentiment measures tone only when the brand appears.
Where Block (Goose) is losing
Prompts where competitors are visible and Block (Goose) is not.
These prompt-level losses are the first prompts to track and repair.
Where Block (Goose) is winning2
What autonomous coding tools have the best ecosystem of community plugins for extending agent capabilities with custom tools and workflows?
Avg # 1.0 · 1 platform
I'm looking for an agentic CLI that supports tool use like web search and shell execution during a coding task — what are my options?
Avg # 6.5 · 2 platforms
Where Block (Goose) is losing5
Which AI coding agents handle context window limitations most gracefully when working across dozens of files in an enterprise codebase?
Competitors on 3 platforms
Track this promptWhat AI coding agents support bring-your-own LLM provider so a platform team can route through an existing enterprise model contract?
Competitors on 3 platforms
Track this promptWhat agentic coding tools handle long-running tasks reliably — resuming after an interruption rather than starting over from scratch?
Competitors on 2 platforms
Track this promptWhich cloud coding agents integrate with CI pipelines to automatically attempt fixes when a build or test suite fails?
Competitors on 1 platform
Track this promptWhat autonomous coding agents run tasks inside a secure sandbox so a compromised prompt can't affect the host filesystem?
Competitors on 1 platform
Track this prompt
Track Block (Goose) daily before the next report refresh.
Track these gapsResearch dossierCapabilities, use cases, sources, reviews, pricing, and FAQ
Overview
Goose is an open-source, local-first AI agent originally built at Block, Inc. (NYSE: XYZ) and publicly released in January 2025 under the Apache 2.0 license. In April 2026 it was donated to the Agentic AI Foundation (AAIF) at the Linux Foundation alongside Anthropic's Model Context Protocol (MCP) and OpenAI's AGENTS.md. Unlike code-completion tools, Goose autonomously executes entire engineering workflows: writing and running code, editing files, installing dependencies, calling external APIs, and iterating — all on the user's machine. It is model-agnostic, supporting 15+ LLM providers, and extensible through 70+ documented MCP extensions plus 3,000+ community integrations. Goose ships as a native desktop app, CLI, and embeddable API, all built in Rust. It is free under Apache 2.0; users pay only for their chosen LLM API. The project has 45,000+ GitHub stars and 500+ contributors.
Goose is a free, open-source, local-first autonomous AI agent built in Rust, originally developed by Block (NYSE: XYZ) and now stewarded by the Linux Foundation's Agentic AI Foundation. It goes beyond code suggestions to autonomously install, execute, edit, test, and deploy across the full development loop. Key product pillars are: model-agnosticism (15+ LLM providers, including local models via Ollama), deep MCP extensibility (70+ extensions, 3,000+ community servers), YAML-based Recipes for reproducible agentic workflows, parallel subagents, and a security layer with prompt injection detection and an adversary reviewer. It ships as a desktop app (macOS, Linux, Windows), CLI, and embeddable API.
Key Facts
- Founded
- 2009
- HQ
- Oakland, California, USA
- Founders
- Jack Dorsey
- Employees
- 5000-6000
- Status
- Public (NYSE: XYZ)
Target users
Key Capabilities10
- Autonomous multi-step task execution: writes and runs code, edits files, installs dependencies, runs tests, and iterates — end to end
- Model-agnostic provider support: 15+ LLM providers including Anthropic, OpenAI, Google, Ollama (local), OpenRouter, Azure, and Bedrock
- MCP-native extensibility with 70+ documented extensions and 3,000+ community MCP servers
- YAML-based Recipes system for repeatable, shareable, parameterised agentic workflows and CI integration
- Parallel subagent orchestration for concurrent code review, research, and file-processing tasks
- Native desktop app (macOS, Linux, Windows), full CLI, and embeddable API — all built in Rust
- Security layer: prompt injection detection, tool permission controls, sandbox mode, and adversary reviewer agent
- ACP (Agent Client Protocol) server: connects from Zed, JetBrains, or VS Code; uses Claude Code or Codex as sub-providers
- Local-first execution with optional local LLM support via Ollama — code never leaves the machine unless a cloud API is chosen
- MCP Apps: extensions render interactive UIs (buttons, forms, visualisations) directly inside Goose Desktop
Key Use Cases8
- Autonomous software engineering: scaffolding projects, fixing bugs, running test suites, and iterating without manual steps
- Large-scale code migrations (e.g., Ember to React, Ruby to Kotlin, class components to hooks)
- CI/CD pipeline automation via CLI and Recipes running in headless mode
- Automated code review: fetching PRs via GitHub MCP, analysing diffs, and posting review comments
- Incident response: parallel log analysis across services to accelerate time-to-recovery
- Cross-functional workflow automation: data analysis, research, content generation, and meeting prep via MCP integrations
- Privacy-sensitive development using fully local LLMs (Ollama) in air-gapped or regulated environments
- Developer productivity tooling: nightly test suites, vulnerability ticket handling, and security detection engineering
Block (Goose) customer outcomes
60% of Block workforce uses Goose weekly; 75% of Block engineers report saving 8–10+ hours per week
Block deployed Goose internally across engineering and non-engineering roles. The company reports broad adoption and significant weekly time savings per user.
100% task delivery rate (vs. 56% without Code Mode); ~2× cost reduction per run ($0.20 vs $0.41); ~3× fewer input tokens
Port of Context used Goose with Code Mode to build a GTM intelligence agent that searched GitHub and Hacker News in real time and delivered digests to Slack. Code Mode eliminated all rate-limit failures and cut per-run cost and token usage.
Recent Trend
How AI describes Block (Goose)
No concise AI response excerpt is available for this brand yet.
Most cited sources1
Alternatives in Autonomous Coding Agents6
Goose occupies the free, open-source, local-first lane of the autonomous coding agent market.
- Its primary differentiators are: (1) zero subscription cost with a bring-your-own-key (BYOK) model supporting 15+ LLM providers, preventing vendor lock-in; (2) local-first architecture keeping code on-device unless a cloud API is explicitly used, appealing to privacy-sensitive teams; (3) MCP-native extensibility reaching 70+ documented and 3,000+ community extensions, giving it the broadest tool surface area of any agent in the category; (4) governance under the Linux Foundation's Agentic AI Foundation (AAIF) alongside Anthropic's MCP and OpenAI's AGENTS.md, signaling infrastructure-grade neutrality.
- Goose does not compete on IDE-native autocomplete or curated SaaS polish; it competes on autonomy, model-agnosticism, and extensibility depth.
- Reviewed sources consistently frame it as the strongest free alternative to Claude Code and Cursor for developers who prioritise control over convenience.
- AAugment Code#19
- AAnthropic (Claude Code)#23
- OpenAI (Codex CLI / Codex)#43
- CCursor (Anysphere)#62
- Factory (Droid)#52
- WWarp#72
Reviews
Praised
- Zero subscription cost with BYOK model
- Model-agnostic: works with any LLM including local Ollama models
- Local-first privacy — code stays on machine
- Recipes system for repeatable, shareable workflows
- Deep MCP extensibility (70+ extensions, 3,000+ community servers)
- Apache 2.0 + Linux Foundation governance ensures long-term openness
- Parallel subagent orchestration for concurrent tasks
- Active community with 500+ contributors and rapid release cadence
Criticized
- Steep learning curve for the Recipes/YAML system
- Requires terminal comfort — not beginner-friendly
- No native IDE integration; runs alongside editor causing context-switching overhead
- Output quality depends entirely on the underlying LLM choice
- No SOC 2, HIPAA, or compliance certifications
- BYOK requires active API cost monitoring and billing management
- Desktop UI less polished than commercial alternatives like Cursor
- No commercial support tier or SLA
Community and analyst sentiment toward Goose is broadly positive, with most criticism focused on rough edges rather than fundamental capability gaps. Developers praise its model-agnostic flexibility, zero-cost licensing, privacy benefits from local execution, and the Recipes system as the standout differentiator. A common pattern in community discussions is users switching from Claude Code Max (up to $200/month) to Goose with a Claude API key and reducing monthly AI spend to roughly $30. Negative feedback centres on the learning curve for Recipes, mandatory terminal familiarity for power features, no native IDE integration (requiring context-switching), output quality varying by model choice, and the absence of enterprise compliance certifications. Analyst reviews rate it competitively against Claude Code on breadth of use cases and extensibility, while acknowledging that Claude Code and Cursor deliver tighter out-of-box polish and higher raw coding accuracy.
Pricing
Goose is entirely free and open-source under the Apache 2.0 license — no subscription, no usage caps, no paid tier. It follows a bring-your-own-key (BYOK) model: users supply their own LLM API credentials and pay providers directly. With local models via Ollama the total cost is zero beyond hardware. Cloud API costs depend on model and usage intensity; reviewed estimates range from approximately $5–$50 per month for typical developer workflows. By comparison, Claude Code Max is priced at up to $200/month and Cursor Ultra at $200/month. Enterprise or team pricing does not exist for Goose itself; organisations may incur costs for LLM API volume at scale.
Limitations
- No commercial support tier, SLA, or enterprise support contract — support depends on GitHub Issues and Discord community responsiveness.
- No SOC 2, HIPAA, or other compliance certifications, which is a hard constraint for regulated industries.
- BYOK model requires users to manage their own LLM API keys, monitor spending, configure billing limits, and handle rate-limit errors — more operational overhead than flat-subscription tools.
- Output quality is model-dependent; Goose does not compensate for weaknesses in the underlying LLM.
- No native IDE integration: runs alongside the editor rather than inside it, adding context-switching overhead.
- The Recipes system has a steep learning curve — YAML authoring, action ordering, and error diagnosis can take days to master.
- Desktop UI is considered less polished than commercial alternatives like Cursor.
- Windows support is functional but the best experience is on macOS and Linux.
Frequently asked questions
Topic coverageCoverage by buyer topic
Topic Coverage
Prompt-Level Results
| Prompt | Gemini Search | ChatGPT | Bing Copilot | Perplexity | Google AI Mode |
|---|---|---|---|---|---|
Capability1/5 cited (20%) | |||||
What AI coding agents handle multi-repo tasks well — making coordinated changes across a frontend and backend repo in a single session? | |||||
Which autonomous coding agents can reliably write and run tests, interpret failures, and self-correct without human intervention? | |||||
I'm looking for an agentic CLI that supports tool use like web search and shell execution during a coding task — what are my options? | |||||
What autonomous coding tools handle legacy codebases in dynamically typed languages best — Python 2 or older PHP specifically? | |||||
Which cloud coding agents are best for generating and merging pull requests asynchronously without a developer staying in the loop? | |||||
Developer Experience0/5 cited (0%) | |||||
Which autonomous coding agents give the best real-time feedback loop when running multi-step tasks so developers stay in control? | |||||
Which agentic IDEs have the smoothest experience for reviewing and approving AI-generated changes before they touch the main branch? | |||||
What AI coding agents do senior engineers prefer for refactoring large codebases without babysitting every intermediate step? | |||||
Which AI coding agents handle context window limitations most gracefully when working across dozens of files in an enterprise codebase? | |||||
What autonomous coding tools are best suited for a solo developer who wants to delegate routine feature work and focus on architecture? | |||||
Integrations & Ecosystem2/5 cited (40%) | |||||
Which cloud coding agents integrate with CI pipelines to automatically attempt fixes when a build or test suite fails? | |||||
Which autonomous coding agents integrate natively with popular code editors so devs can trigger agent tasks without leaving their IDE? | |||||
What AI coding agents support bring-your-own LLM provider so a platform team can route through an existing enterprise model contract? | |||||
Which agentic coding platforms integrate with project management tools so engineers can assign tickets directly to an AI agent to action? | |||||
What autonomous coding tools have the best ecosystem of community plugins for extending agent capabilities with custom tools and workflows? | |||||
Performance & Reliability0/5 cited (0%) | |||||
What autonomous coding agents run tasks inside a secure sandbox so a compromised prompt can't affect the host filesystem? | |||||
Which autonomous coding agents are most cost-efficient for high-volume use — minimising frontier LLM provider token spend per merged PR? | |||||
Which cloud coding agents have the best uptime and task success rates for a mid-size team running dozens of concurrent agent jobs daily? | |||||
Which AI coding agents complete multi-file tasks fastest without sacrificing correctness — benchmarks or real-world comparisons? | |||||
What agentic coding tools handle long-running tasks reliably — resuming after an interruption rather than starting over from scratch? | |||||
Setup & First Run0/5 cited (0%) | |||||
What are the best agentic IDEs for a team migrating from a traditional code editor that want AI-assisted multi-file editing from day one? | |||||
Which agentic CLI tools work out of the box on popular operating systems without requiring a container sandbox just to get started? | |||||
Which cloud coding agents can be connected to an existing private repo and start opening pull requests with minimal setup? | |||||
What's the easiest AI coding agent to get running locally on a large existing TypeScript monorepo without hours of configuration? | |||||
I'm evaluating autonomous coding agents for a 10-person startup — which ones can a new engineer get productive with in under an hour? | |||||
Turn this matrix into daily prompt monitoring.
Track prompt changesVertical Ranking
| # | Brand | PresencePres. | Share of VoiceSoV | DocsDocs | BlogBlog | MentionsMent. | Avg PosPos | Sentiment |
|---|---|---|---|---|---|---|---|---|
| 1 | Augment Code | 8.8% | 32.7% | 0.0% | 0.0% | 8.0% | #7.2 | +0.21 |
| 2 | Anthropic (Claude Code) | 3.2% | 12.7% | 0.0% | 0.0% | 3.2% | #3.9 | +0.35 |
| 3 | Block (Goose) | 3.2% | 12.7% | 0.0% | 0.0% | 3.2% | #4.9 | +0.54 |
| 4 | OpenAI (Codex CLI / Codex) | 3.2% | 10.9% | 0.8% | 0.0% | 2.4% | #7.7 | +0.25 |
| 5 | Factory (Droid) | 2.4% | 10.9% | 0.0% | 0.0% | 1.6% | #4.7 | +0.60 |
| 6 | Cursor (Anysphere) | 2.4% | 5.5% | 0.8% | 0.8% | 2.4% | #16.7 | +0.27 |
| 7 | Warp | 1.6% | 3.6% | 1.6% | 0.0% | 1.6% | #4.0 | +0.30 |
| 8 | All Hands AI (OpenHands) | 0.8% | 5.5% | 0.0% | 0.0% | 0.8% | #2.0 | +0.70 |
| 9 | OpenCode | 0.8% | 1.8% | 0.0% | 0.0% | 0.8% | #2.0 | +0.60 |
| 10 | Cognition (Devin) | 0.8% | 1.8% | 0.8% | 0.0% | 0.8% | #3.0 | +0.80 |
| 11 | Aider AI | 0.8% | 1.8% | 0.0% | 0.0% | 0.8% | #27.0 | +0.00 |
| 12 | Amp | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | — | — |
| 13 | Cline Bot Inc. | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | — | — |
| 14 | Lovable | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | — | — |
| 15 | Replit (Agent 3) | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | — | — |
| 16 | Roo Code (Roomote) | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | — | — |
| 17 | StackBlitz (Bolt.new) | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | — | — |
Turn this into your team dashboard
Sign up to unlock project-level analytics, daily tracking, actionable insights, custom prompt configurations, adoption tracking, AI traffic analytics and more.
Free trial. Setup comes pre-filled from this report.