{"slug": "agy", "name": "agy", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 1, "commenters": 9, "warners": 4, "score": -1.696, "rising": 1.0, "first": "2026-07-21", "latest": "2026-10-01", "why": "the best thing about agy is the usage limit was very generous.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 1, "neutral": 4, "compare": 0, "warn": 4}, "spark": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0], "listed": false, "loved": [], "caveat": "", "short_quote": "the best thing about agy is the usage limit was very generous.", "icon": false, "domain": null, "github_repo": null, "official_url": "", "pricing": "", "aliases": ["agy", "AGY", "Agy"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 798645041, "item_id": 49915315, "url": "https://news.ycombinator.com/item?id=49915315", "by": "huydotnet", "date": "2026-09-30", "stance": "recommend", "quote": "the best thing about agy is the usage limit was very generous.", "excerpt": "I recently subscribed to Claude, and was very unhappy about the usage limit of the $20 pro plan. Then I found a trick, since I got free Google AI Pro via my phone carrier, I use Opus 5.5 High for planning, and then dispatching agy to do works. Most of the time 3.8 works fine, but it's a bit slow if compare to 3.7 Flash. If there's already a detailed plan, 3.7 can complete the task much faster. And the best thing abou", "context": "", "use_case": "executing planned tasks", "switched_from": "", "story": "Gemini 4 Argon"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 798642049, "item_id": 49915128, "url": "https://news.ycombinator.com/item?id=49915128", "by": "moecables", "date": "2026-09-30", "stance": "warn", "quote": "`agy` in the command line feels very bad/incapable of doing things", "excerpt": "I use Antigravity but for some reason, `agy` in the command line feels very bad/incapable of doing things. I can't quite explain it but the most common issue I run into it is just hanging on being unable to finish a tool call", "context": "", "use_case": "command line coding agent", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798633376, "item_id": 49914586, "url": "https://news.ycombinator.com/item?id=49914586", "by": "imshaikot", "date": "2026-09-30", "stance": "warn", "quote": "I'm not gonna use AGY again.", "excerpt": "Whatever it is - I'm not gonna use AGY again. I'd rather use claude-code-router instead, to give gemini-4 a shot.", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 784005393, "item_id": 49000337, "url": "https://news.ycombinator.com/item?id=49000337", "by": "dudeinhawaii", "date": "2026-07-21", "stance": "warn", "quote": "Gemini is terrible at agentic coding, primarily because Agy is terrible.", "excerpt": "I use all of the major providers daily and I tend to go to Gemini for \"fast lookups\" where a good enough answer is probably OK. I use ChatGPT and Claude for anything where it matters and generally when I invoke all three -- Gemini is the most surface level with responses, and also sycophantic. It gets worse from there. Gemini is terrible at agentic coding, primarily because Agy is terrible. I noticed Google updated A", "context": "", "use_case": "agentic coding", "switched_from": "", "story": "Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber"}, {"id": 783935297, "item_id": 48995956, "url": "https://news.ycombinator.com/item?id=48995956", "by": "nxdmum", "date": "2026-07-21", "stance": "warn", "quote": "Google Gemini agy is not allowing you to use your token via your own harness.", "excerpt": "Google Gemini agy is not allowing you to use your token via your own harness. My own harness is far more efficient than agy. They can take a simple stance - if you exceed your token limit they block you - with the 5 hr limit they are already doing this . so there should be no reason to block you from using your own harness - if you are more efficient - you gain - if you are less you lose . They are not allowing me to", "context": "built their own harness", "use_case": "coding agent client", "switched_from": "", "story": "Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber"}]}], "who": [], "tags": [], "use_cases": ["gemini coding agent harness", "executing planned tasks", "command line coding agent", "second-opinion false positive elimination", "coding harness for gemini", "generating sonic pi code"], "compared": [{"slug": "gemini", "name": "Gemini", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "claude-code-router", "name": "Claude Code Router", "co": 1, "switched_from": 0, "switched_to": 1}, {"slug": "codex", "name": "Codex", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "opencode", "name": "OpenCode", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49913571", "title": "Gemini 4 Argon", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=48993414", "title": "Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49703003", "title": "GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49537553", "title": "Gemini 3.8 Flash and 3.8 Flash Cyber", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49208296", "title": "Sonic Pi v5 Released", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {"warn": 2}, "2026-08": {"neutral": 1}, "2026-09": {"neutral": 2, "warn": 2, "recommend": 1}, "2026-10": {"neutral": 1}}, "quotes": [{"id": 798701312, "item_id": 49918832, "url": "https://news.ycombinator.com/item?id=49918832", "by": "crossroadsguy", "date": "2026-10-01", "stance": "neutral", "quote": "I use agy, because no other harness can be used for subscription plan", "excerpt": "So Gemini Pro (I use agy, because no other harness can be used for subscription plan) was supposed to get Gemini 3.5 Pro, at some point (it was planned, right?), but instead Argon arrives and I am pretty sure it will only be in Ultra sub and don't think 3.5 Pro is coming anymore.", "context": "", "use_case": "Gemini coding agent harness", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798645041, "item_id": 49915315, "url": "https://news.ycombinator.com/item?id=49915315", "by": "huydotnet", "date": "2026-09-30", "stance": "recommend", "quote": "the best thing about agy is the usage limit was very generous.", "excerpt": "I recently subscribed to Claude, and was very unhappy about the usage limit of the $20 pro plan. Then I found a trick, since I got free Google AI Pro via my phone carrier, I use Opus 5.5 High for planning, and then dispatching agy to do works. Most of the time 3.8 works fine, but it's a bit slow if compare to 3.7 Flash. If there's already a detailed plan, 3.7 can complete the task much faster. And the best thing abou", "context": "", "use_case": "executing planned tasks", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798642049, "item_id": 49915128, "url": "https://news.ycombinator.com/item?id=49915128", "by": "moecables", "date": "2026-09-30", "stance": "warn", "quote": "`agy` in the command line feels very bad/incapable of doing things", "excerpt": "I use Antigravity but for some reason, `agy` in the command line feels very bad/incapable of doing things. I can't quite explain it but the most common issue I run into it is just hanging on being unable to finish a tool call", "context": "", "use_case": "command line coding agent", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798633376, "item_id": 49914586, "url": "https://news.ycombinator.com/item?id=49914586", "by": "imshaikot", "date": "2026-09-30", "stance": "warn", "quote": "I'm not gonna use AGY again.", "excerpt": "Whatever it is - I'm not gonna use AGY again. I'd rather use claude-code-router instead, to give gemini-4 a shot.", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 795263493, "item_id": 49703968, "url": "https://news.ycombinator.com/item?id=49703968", "by": "dlahoda", "date": "2026-09-14", "stance": "neutral", "quote": "I use agy 200usd sub for second-opinion", "excerpt": "I would and do. works perfect https://github.com/dzmitry-lahoda/dz/tree/main/agents/skills/code-review burns half of day sub of astra for 200 USD. runs 1 hour on our repo. finds bugs missed by coderabitai, devin-integration-bot, codex and copilot (I ask them first until nothing found, yet my orchestration finds more). I do not hardcode our application in orchestration, but run subagent for applicationdomainproduct de", "context": "", "use_case": "second-opinion false positive elimination", "switched_from": "", "story": "GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?"}, {"id": 792791153, "item_id": 49549447, "url": "https://news.ycombinator.com/item?id=49549447", "by": "mark_l_watson", "date": "2026-09-03", "stance": "neutral", "quote": "for Gemini I use Google\u2019s agy coding harness (or my own)", "excerpt": "I usually use OpenCode for all open weight models but for Gemini I use Google\u2019s agy coding harness (or my own). Venders coupling coding harnesses with their own models is usually a good thing. Poolside.ai has a combined harness with their own models that works well locally, and the DeepSeek harness with their models is very interesting.", "context": "", "use_case": "coding harness for Gemini", "switched_from": "", "story": "Gemini 3.8 Flash and 3.8 Flash Cyber"}, {"id": 788148514, "item_id": 49259282, "url": "https://news.ycombinator.com/item?id=49259282", "by": "xrd", "date": "2026-08-11", "stance": "neutral", "quote": "I have been using agy to generate sonicpi code", "excerpt": "I think I was not using sonipic buffers correctly (I guess they are called \"tabs\" in the UI). I've been using them without saving the files. I have struggled to think of it as an \"editor\" only because of things I'm used to with emacs: git+magit, elisp, customizable hotkeys, etc. My problems are not unique to Sonic Pi: as I use AI more for experimentation, I'm struggling with how I pipe AI output to an editor, whether", "context": "", "use_case": "generating Sonic Pi code", "switched_from": "", "story": "Sonic Pi v5 Released"}, {"id": 784005393, "item_id": 49000337, "url": "https://news.ycombinator.com/item?id=49000337", "by": "dudeinhawaii", "date": "2026-07-21", "stance": "warn", "quote": "Gemini is terrible at agentic coding, primarily because Agy is terrible.", "excerpt": "I use all of the major providers daily and I tend to go to Gemini for \"fast lookups\" where a good enough answer is probably OK. I use ChatGPT and Claude for anything where it matters and generally when I invoke all three -- Gemini is the most surface level with responses, and also sycophantic. It gets worse from there. Gemini is terrible at agentic coding, primarily because Agy is terrible. I noticed Google updated A", "context": "", "use_case": "agentic coding", "switched_from": "", "story": "Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber"}, {"id": 783935297, "item_id": 48995956, "url": "https://news.ycombinator.com/item?id=48995956", "by": "nxdmum", "date": "2026-07-21", "stance": "warn", "quote": "Google Gemini agy is not allowing you to use your token via your own harness.", "excerpt": "Google Gemini agy is not allowing you to use your token via your own harness. My own harness is far more efficient than agy. They can take a simple stance - if you exceed your token limit they block you - with the 5 hr limit they are already doing this . so there should be no reason to block you from using your own harness - if you are more efficient - you gain - if you are less you lose . They are not allowing me to", "context": "built their own harness", "use_case": "coding agent client", "switched_from": "", "story": "Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber"}]}