Claude Code costs up to $200 a month. Goose does the same thing for free.
Goose, a free open-source AI coding agent from Block, rivals Claude Code ($20–200/mo) with local execution, no subscriptions, and no rate limits. It has 26K+ GitHub stars and 102 releases since launch.

Signal Snapshot
Briefing Notes
What happened and why it matters
Summary
Goose, a free open-source AI coding agent from Block, rivals Claude Code ($20–200/mo) with local execution, no subscriptions, and no rate limits. It has 26K+ GitHub stars and 102 releases since launch.
Why it matters
The emergence of free, open-source alternatives like Goose challenges the subscription-based pricing model of commercial AI coding tools. By offering local execution and no rate limits, Goose lowers the barrier for developers who want to experiment with AI-assisted coding without ongoing costs. This could accelerate adoption of AI coding agents in smaller teams and individual projects, and put pressure on paid services to justify their pricing.
Related tools
- Claude – The commercial AI coding agent from Anthropic that Goose competes with.
- Browse AI tools – Explore other AI coding assistants and development tools.
Impact on AI tools/models
Goose's open-source nature and zero-cost model may force commercial AI coding tools to rethink their pricing strategies. It also demonstrates that high-quality AI coding agents can be built and distributed freely, potentially leading to more innovation in the open-source AI space. The large GitHub community (26K+ stars) indicates strong interest and rapid iteration (102 releases).
What to watch
- How Claude and other paid coding agents respond to the free alternative.
- The growth of Goose's feature set and community contributions on GitHub.
- Adoption of open-source AI agents in enterprise environments, which may prefer local execution for security.
- For more AI tool comparisons, check AI news and rankings.
FAQ
What is Goose? Goose is a free open-source AI coding agent from Block that rivals Claude Code.
How much does Goose cost? Goose is free with no subscriptions and no rate limits.
How does Goose compare to Claude Code? Goose offers local execution and no rate limits, while Claude Code costs $20–200 per month.
Search FAQ
Frequently asked questions
FAQ
What is Goose?
How much does Goose cost?
How does Goose compare to Claude Code?
Keep Tracking
Related AI news

Agentic orchestration: Enterprise AI organizations have a deployment problem, not a platform problem — and most are calling chatbots agents
VentureBeat research reveals 71% of enterprise AI agents are merely chatbot wrappers lacking real-time cost controls, highlighting a critical deployment gap despite robust orchestration foundations.

The AI context gap: Enterprise AI organizations have a trust problem, not a retrieval problem — and most are still building the fix
VentureBeat research finds 57% of enterprises face agent hallucinations due to trust gaps rather than retrieval failures, with most organizations still developing solutions to close the AI context gap.

The AI compute gap: Enterprises are buying infrastructure faster than they can measure what it costs
Enterprises face an AI compute gap: while infrastructure spending accelerates, 83% underutilize GPUs and only 44% track costs effectively, highlighting urgent needs for better management solutions.

The agent security gap: 54% of enterprises have already had an AI agent incident, and most still let agents share credentials
VentureBeat research reveals 54% of enterprises faced AI agent security incidents, primarily due to shared credentials and lack of isolation mechanisms.

The agent evaluation gap: Enterprise AI organizations have a reality-alignment problem, not a coverage problem — and most are shipping to production anyway
VentureBeat research reveals a critical evaluation gap in enterprise AI: half of firms ship agents that fail customers despite passing internal tests, while two-thirds allow zero-human-in-the-loop deployments.

Nous Research's NousCoder-14B is an open-source coding model landing right in the Claude Code moment
Nous Research released NousCoder-14B, an open-source coding model matching larger proprietary systems, trained in 4 days on 48 Nvidia B200 GPUs. It achieves 67.87% on LiveCodeBench v6, a 7.08% improvement over Qwen3-14B. The release includes full training stack for reproducibility.
Site Discovery
Keep exploring the AI ecosystem
After this brief, continue into related tools, models, and rankings to understand whether the story affects your choices.