{"slug": "goose", "name": "Goose", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 3, "commenters": 10, "warners": 0, "score": 4.516, "rising": 0.35, "first": "2025-11-02", "latest": "2026-10-26", "why": "Goose was the only harness that didnt bloat context too much with system prompts", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 6, "compare": 1, "warn": 0}, "spark": [1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Goose was the only harness that didnt bloat context too much with system prompts", "icon": true, "domain": null, "github_repo": "github.com/aaif-goose/goose", "official_url": "https://github.com/pressly/goose", "pricing": "", "aliases": ["Goose", "goose"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 787934048, "item_id": 49245878, "url": "https://news.ycombinator.com/item?id=49245878", "by": "seanmcdirmid", "date": "2026-08-10", "stance": "recommend", "quote": "Goose was the only harness that didnt bloat context too much with system prompts", "excerpt": "Not parent, but I use Goose for my non-handcrafted Qwen use cases, I\u2019m also working on handcrafting as well. Goose was the only harness that didnt bloat context too much with system prompts (like openclaw) and I could get reasonable web search working with Qwen.", "context": "", "use_case": "harness for local Qwen models", "switched_from": "", "story": "Meta Muse Glimmer \u2013 open weights 30B local coding model"}, {"id": 772160432, "item_id": 48260027, "url": "https://news.ycombinator.com/item?id=48260027", "by": "eikenberry", "date": "2026-05-24", "stance": "recommend", "quote": "Maybe check out Goose.", "excerpt": "Maybe check out Goose. It is the standard agent harness being developed by The Linux Foundation under the AAIF. Under active development and the implementation seems to have a good leg up on the other popular agents. https://github.com/aaif-goose/goose https://goose-docs.ai/", "context": "", "use_case": "agent harness for DeepSeek", "switched_from": "", "story": "DeepSeek reasonix, engineered for low token cost during long running sessions"}, {"id": 732623984, "item_id": 45788999, "url": "https://news.ycombinator.com/item?id=45788999", "by": "leosanchez", "date": "2025-11-02", "stance": "recommend", "quote": "I use goose[1] for db migrations.", "excerpt": "I use goose[1] for db migrations. [1]: https://github.com/pressly/goose", "context": "", "use_case": "database migrations", "switched_from": "", "story": "CLI to manage your SQL database schemas and migrations"}]}], "caveats": [], "who": [{"by": "phillc73", "context": "Mistral user", "url": "https://news.ycombinator.com/item?id=49932202", "date": "2026-10-02"}], "tags": [], "use_cases": ["foss coding harness", "agent harness backend", "desktop ai client", "harness for local qwen models", "agentic coding", "agent in buzz"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 5, "switched_from": 0, "switched_to": 0}, {"slug": "codex", "name": "Codex", "co": 5, "switched_from": 0, "switched_to": 0}, {"slug": "pi", "name": "Pi", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "opencode", "name": "OpenCode", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 762251968, "item_id": 47640748, "url": "https://news.ycombinator.com/item?id=47640748", "by": "mmargenot", "date": "2026-04-04", "stance": "neutral", "quote": "I've done this with Goose at Block with more classic post-training approaches", "excerpt": "It is more common now to improve models in agentic systems \"in the loop\" with reinforcement learning. Anthropic is [very likely] doing this in the backend to systematically improve the performance of their models specifically with their tools. I've done this with Goose at Block with more classic post-training approaches because it was before RL really hit the mainstream as an approach for this. If you want to look at", "context": "worked at Block on Goose", "use_case": "agent post-training", "switched_from": "", "story": "Components of a Coding Agent"}], "threads": [{"url": "https://news.ycombinator.com/item?id=50236102", "title": "OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50225695", "title": "We should be more ambitious with the software we build", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49929489", "title": "DeepSeek Harness Desktop for macOS and Windows", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49241679", "title": "Meta Muse Glimmer \u2013 open weights 30B local coding model", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48771515", "title": "Ask HN: Is anyone experimenting with different ways of using LLMs for coding?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48632977", "title": "Show HN: Block/buzz: a workspace built for teams of humans and agents", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {"compare": 1}, "2026-01": {}, "2026-02": {}, "2026-03": {"neutral": 1}, "2026-04": {}, "2026-05": {"recommend": 1}, "2026-06": {"neutral": 1}, "2026-07": {"neutral": 1}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {"neutral": 3}}, "quotes": [{"id": 803856546, "item_id": 50241034, "url": "https://news.ycombinator.com/item?id=50241034", "by": "crossroadsguy", "date": "2026-10-26", "stance": "neutral", "quote": "", "excerpt": "At this point I'd rather try to invest effort and usage in a harness that is FOSS and is actually steered by a non-profit. Goose comes to mind and to be honest I haven't tried it beyond installing and giving it a prompt or two. Comiong to harnesses, even Pi seems like a weird choice. I mean Pi, until it's \"your own customised Pi\", is pretty useless and pointless. Besides they are also starting to have their own model", "context": "", "use_case": "FOSS coding harness", "switched_from": "", "story": "OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?"}, {"id": 803669393, "item_id": 50229337, "url": "https://news.ycombinator.com/item?id=50229337", "by": "apatheticonion", "date": "2026-10-25", "stance": "neutral", "quote": "I've embedded the Goose harness as a back end", "excerpt": "Agreed. I started writing a desktop GUI harness in Rust using native desktop GUI APIs. Claude, Codex, Opencode, everything is Electron. With agents and solid engineering fundamentals, I set out to prove that we don't need to take that shortcut any more and we can, in fact, ship high quality/performance applications. It's still early days - but I got something basic working. I've embedded the Goose harness as a back e", "context": "", "use_case": "agent harness backend", "switched_from": "", "story": "We should be more ambitious with the software we build"}, {"id": 798915235, "item_id": 49932202, "url": "https://news.ycombinator.com/item?id=49932202", "by": "phillc73", "date": "2026-10-02", "stance": "neutral", "quote": "I have Goose installed which I have no real complaints about.", "excerpt": "I've been with Mistral for a while now. Their hosted GLM-5.3 has been a game changer in Vibe CLI over the last couple of weeks. The Vibe CLI harness has been improving for a while, but is still a little sluggish and I feel lacks token minimisation strategies. I recently changed to Maki and have been reasonably satisfied so far. However, I also use the Mistral Vibe chat in my browser. I think they only switched to GLM", "context": "Mistral user", "use_case": "desktop AI client", "switched_from": "", "story": "DeepSeek Harness Desktop for macOS and Windows"}, {"id": 787934048, "item_id": 49245878, "url": "https://news.ycombinator.com/item?id=49245878", "by": "seanmcdirmid", "date": "2026-08-10", "stance": "recommend", "quote": "Goose was the only harness that didnt bloat context too much with system prompts", "excerpt": "Not parent, but I use Goose for my non-handcrafted Qwen use cases, I\u2019m also working on handcrafting as well. Goose was the only harness that didnt bloat context too much with system prompts (like openclaw) and I could get reasonable web search working with Qwen.", "context": "", "use_case": "harness for local Qwen models", "switched_from": "", "story": "Meta Muse Glimmer \u2013 open weights 30B local coding model"}, {"id": 780469394, "item_id": 48779337, "url": "https://news.ycombinator.com/item?id=48779337", "by": "kosolam", "date": "2026-07-03", "stance": "neutral", "quote": "Started with running all the usual suspects pi, claude code, codex, goose", "excerpt": "Ha I\u2019m doing the same. 2 months in or so, lost track of time a bit. Started with running all the usual suspects pi, claude code, codex, goose, but mostly migrated to own agent (ha!) for greater level of control. Also doing it in python for C lang as first target (ha!). Anyhow post a link if you\u2019d release yours I\u2019d be interested to take a look at adjacent work.", "context": "", "use_case": "agentic coding", "switched_from": "", "story": "Ask HN: Is anyone experimenting with different ways of using LLMs for coding?"}, {"id": 778127873, "item_id": 48632992, "url": "https://news.ycombinator.com/item?id=48632992", "by": "tlongwell-block", "date": "2026-06-22", "stance": "neutral", "quote": "our team uses goose, Claude Code, Codex, and other agents", "excerpt": "quickstart (docker required): git clone https://github.com/block/buzz; cd buzz; just dev; Buzz is a channel-driven workspace for teams of humans and their agents to work together in. It should look vaguely similar to whatever you're used to chatting with your team in. Written in Rust. Apache 2 licensed. Nostr-shaped. To work in Buzz, I'll spin up a new channel, add my team and my agents, and start brainstorming the b", "context": "", "use_case": "agent in Buzz", "switched_from": "", "story": "Show HN: Block/buzz: a workspace built for teams of humans and agents"}, {"id": 772160432, "item_id": 48260027, "url": "https://news.ycombinator.com/item?id=48260027", "by": "eikenberry", "date": "2026-05-24", "stance": "recommend", "quote": "Maybe check out Goose.", "excerpt": "Maybe check out Goose. It is the standard agent harness being developed by The Linux Foundation under the AAIF. Under active development and the implementation seems to have a good leg up on the other popular agents. https://github.com/aaif-goose/goose https://goose-docs.ai/", "context": "", "use_case": "agent harness for DeepSeek", "switched_from": "", "story": "DeepSeek reasonix, engineered for low token cost during long running sessions"}, {"id": 757582017, "item_id": 47348876, "url": "https://news.ycombinator.com/item?id=47348876", "by": "DrAwdeOccarim", "date": "2026-03-12", "stance": "neutral", "quote": "Does Goose AI aspire/do this?", "excerpt": "I want this, but using Nemotron Super 3 running local (128gb M5 Max macbook pro) that I use the computer \u201cthrough\u201d. Does Goose AI aspire/do this? I just started working on this yesterday.", "context": "", "use_case": "local AI computer control", "switched_from": "", "story": "Personal Computer by Perplexity"}, {"id": 739376928, "item_id": 46211058, "url": "https://news.ycombinator.com/item?id=46211058", "by": "flakiness", "date": "2025-12-09", "stance": "compare", "quote": "I tried it a few months back and it was pretty crappy.", "excerpt": "So I'll focus on the block's contribtution, which is goose: https://github.com/block/goose Has it gotten better and good enough? I tried it a few months back and it was pretty crappy. And it's not because of bad models (I used it with the latest Claude at that time) but because of poor harness implementation and UI. Is it worth trying the latest version to see how it compares with Claude Code? I want OSS, model agnos", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "Agentic AI Foundation"}, {"id": 732623984, "item_id": 45788999, "url": "https://news.ycombinator.com/item?id=45788999", "by": "leosanchez", "date": "2025-11-02", "stance": "recommend", "quote": "I use goose[1] for db migrations.", "excerpt": "I use goose[1] for db migrations. [1]: https://github.com/pressly/goose", "context": "", "use_case": "database migrations", "switched_from": "", "story": "CLI to manage your SQL database schemas and migrations"}]}