{"slug": "aider", "name": "Aider", "category": "ai-coding", "category_name": "AI coding tools", "description": "Open-source terminal AI pair-programming tool that edits code in your local git repo.", "recommenders": 12, "commenters": 21, "warners": 0, "score": 12.644, "rising": -3.93, "first": "2025-11-03", "latest": "2026-10-13", "why": "Liked for accurate, controllable code edits that commenters say match or beat Copilot, and for working with whichever open, local or frontier model you choose.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 13, "neutral": 9, "compare": 1, "warn": 0}, "spark": [1, 1, 2, 4, 1, 3, 1, 0, 0, 0, 0, 0], "listed": true, "loved": ["Code quality", "Model choice"], "caveat": "Token cost", "short_quote": "But I like aider. I had better capabilities and is controllable", "icon": false, "domain": "aider.chat", "github_repo": null, "official_url": "https://aider.chat/", "pricing": "open source", "aliases": ["Aider", "aider"], "verdict": [{"text": "Liked for accurate, controllable code edits that commenters say match or beat Copilot,", "cites": [{"id": 740169680, "item_id": 46260605, "url": "https://news.ycombinator.com/item?id=46260605", "by": "devdp430", "date": "2025-12-13", "stance": "recommend", "quote": "But I like aider. I had better capabilities and is controllable", "excerpt": "I use AI at work. We have a huge codebase in Golang. 1000s of files. I had tried cursor, claude code, gemini cli, openai codex and all sorts of vscode based idea (like windsurf, antigravity etc). All of them get overwhelmed when there is something to implement or change in the codebase primarily due to the amount of code. But I like aider. I had better capabilities and is controllable, you can try. And if you use it ", "context": "works on a huge Golang codebase with thousands of files", "use_case": "coding in huge Golang codebase", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}, {"id": 745241491, "item_id": 46577593, "url": "https://news.ycombinator.com/item?id=46577593", "by": "kasey_junk", "date": "2026-01-11", "stance": "recommend", "quote": "Several of the open source agents will out perform copilot regularly (try aider, open code or cline if you can).", "excerpt": "It is not the same. The agents (Claude code, codex) are the actual processes you\u2019d interact with instead of copilot. The choices those processes make about tool calls, using subagents, etc make a huge difference in the quality of result you\u2019ll get. Copilot is just an extremely bad agent compared to the sota agents. Several of the open source agents will out perform copilot regularly (try aider, open code or cline if ", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "Ask HN: Senior software engineers, how do you use Claude Code?"}, {"id": 760359968, "item_id": 47522498, "url": "https://news.ycombinator.com/item?id=47522498", "by": "Hackbraten", "date": "2026-03-25", "stance": "recommend", "quote": "I use Aider on my private computers and Copilot at work. Both feel equally powerful when configured with a decent frontier model.", "excerpt": "> There were precursors like Aider and early Cursor, but they were more assistant than agent. I use Aider on my private computers and Copilot at work. Both feel equally powerful when configured with a decent frontier model. Are they really generations apart? What am I missing?", "context": "", "use_case": "personal AI coding", "switched_from": "", "story": "Thoughts on Slowing the Fuck Down"}, {"id": 762722146, "item_id": 47670134, "url": "https://news.ycombinator.com/item?id=47670134", "by": "another_twist", "date": "2026-04-06", "stance": "recommend", "quote": "Even aider gets good results this way.", "excerpt": "Is it just me that I simply don't care ? I never one-shot these tasks, always provide a breakdown and always give the AI straightforward tasks that would take too much typing. The approach seems to work just fine regardless of the model. If it gets stuck, I usually take over and do the task myself. Also allows me to plan for throughput rather than latency - i.e. start 2-3 small tasks in parallel and do 1 complicated ", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Claude Code is unusable for complex engineering tasks with the Feb updates"}]}, {"text": " and for working with whichever open, local or frontier model you choose.", "cites": [{"id": 766356960, "item_id": 47897310, "url": "https://news.ycombinator.com/item?id=47897310", "by": "arikrahman", "date": "2026-04-24", "stance": "recommend", "quote": "I find using Aider with the new open models and using Open Spec to negotiate requirements before the handoff, has helped me a lot.", "excerpt": "I use Aider nowadays, and will probably cancel my Github multi AI bundle subscription due to the new training policy. I find using Aider with the new open models and using Open Spec to negotiate requirements before the handoff, has helped me a lot.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"}, {"id": 776731350, "item_id": 48545709, "url": "https://news.ycombinator.com/item?id=48545709", "by": "shironnnn_", "date": "2026-06-15", "stance": "neutral", "quote": "serve OpenAPI endpoints compatible for Aider (CLI) or Visual Studio Code", "excerpt": "I use SpecKit to create a very detailed plan with a high amount of specificity using paid Claude plan. Then I give it to local LLM (eg: Qwen / Gemma 4) via CLI. This is possible through usage of llm-mlx on Mac (or ollama on any machine given sufficient on hardware) which serve OpenAPI endpoints compatible for Aider (CLI) or Visual Studio Code to vibe along with the agentic coding assistant. The paid products have an ", "context": "", "use_case": "agentic coding CLI", "switched_from": "", "story": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"}, {"id": 740169680, "item_id": 46260605, "url": "https://news.ycombinator.com/item?id=46260605", "by": "devdp430", "date": "2025-12-13", "stance": "recommend", "quote": "But I like aider. I had better capabilities and is controllable", "excerpt": "I use AI at work. We have a huge codebase in Golang. 1000s of files. I had tried cursor, claude code, gemini cli, openai codex and all sorts of vscode based idea (like windsurf, antigravity etc). All of them get overwhelmed when there is something to implement or change in the codebase primarily due to the amount of code. But I like aider. I had better capabilities and is controllable, you can try. And if you use it ", "context": "works on a huge Golang codebase with thousands of files", "use_case": "coding in huge Golang codebase", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}]}, {"text": " The most common complaint is heavy token use and API cost,", "cites": [{"id": 790987616, "item_id": 49436726, "url": "https://news.ycombinator.com/item?id=49436726", "by": "joshstrange", "date": "2026-08-25", "stance": "neutral", "quote": "The results were good, but not worth the price for me.", "excerpt": "In the last 30 days my LLM spend, if paid at API rates, would be $19,431 (and that doesn't track online chats or my Github Action reviews). Now I wish I was making $200K/mo but I'm not, no where close. I got all that for $220 on subscriptions. Yes, LLMs are awesome and let me do things faster but I would be using them far less if my only option was the API. I used coding agents prior to subscriptions (Aider) and spen", "context": "", "use_case": "API-billed coding agent", "switched_from": "", "story": "OpenAI restores 5-hour Codex and Work limits for ChatGPT Plus users"}, {"id": 792977424, "item_id": 49561089, "url": "https://news.ycombinator.com/item?id=49561089", "by": "aitchnyu", "date": "2026-09-04", "stance": "neutral", "quote": "I used Aider on a Python project which had string references", "excerpt": "Which language and agent? I used Aider on a Python project which had string references (as opposed to module tree) and cross-repo references. LSP lookups were fast and I hated it when Aider used 2M tokens a day, but grep was more complete.", "context": "", "use_case": "AI coding on Python project", "switched_from": "", "story": "Grep beats LSP? Why coding agents ignore your fancier tools"}]}, {"text": " and some users have since moved to newer agents such as Claude Code.", "cites": [{"id": 775317665, "item_id": 48457354, "url": "https://news.ycombinator.com/item?id=48457354", "by": "noufalibrahim", "date": "2026-06-08", "stance": "neutral", "quote": "About 40% of the program was done using Aider", "excerpt": "I needed something to help me stay off the computer (sites and applications) at certain times of the day with enforcement and in a way that's hard to remove. I had some ideas but was able to systematize all that into a proper program that I use daily. It's been very effective and it's much better (for me) than any of the commercial solutions that I've found for Linux. About 40% of the program was done using Aider (be", "context": "", "use_case": "building the program", "switched_from": "", "story": "Ask HN: What are tools you have made for yourself since the advent of AI"}, {"id": 801288384, "item_id": 50080524, "url": "https://news.ycombinator.com/item?id=50080524", "by": "guyomes", "date": "2026-10-13", "stance": "neutral", "quote": "I used Aider before, and consider switching to a more recent tool.", "excerpt": "Out of curiosity, which harness do you use for this kind of task, and how do you sandbox it? I used Aider before, and consider switching to a more recent tool.", "context": "", "use_case": "AI coding assistant", "switched_from": "", "story": "Gemini 4 Argon"}]}], "praise": [{"label": "Code quality", "summary": "Commenters report good, accurate results that hold up against Copilot and other agents.", "quotes": [{"id": 740169680, "item_id": 46260605, "url": "https://news.ycombinator.com/item?id=46260605", "by": "devdp430", "date": "2025-12-13", "stance": "recommend", "quote": "But I like aider. I had better capabilities and is controllable", "excerpt": "I use AI at work. We have a huge codebase in Golang. 1000s of files. I had tried cursor, claude code, gemini cli, openai codex and all sorts of vscode based idea (like windsurf, antigravity etc). All of them get overwhelmed when there is something to implement or change in the codebase primarily due to the amount of code. But I like aider. I had better capabilities and is controllable, you can try. And if you use it ", "context": "works on a huge Golang codebase with thousands of files", "use_case": "coding in huge Golang codebase", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}, {"id": 745241491, "item_id": 46577593, "url": "https://news.ycombinator.com/item?id=46577593", "by": "kasey_junk", "date": "2026-01-11", "stance": "recommend", "quote": "Several of the open source agents will out perform copilot regularly (try aider, open code or cline if you can).", "excerpt": "It is not the same. The agents (Claude code, codex) are the actual processes you\u2019d interact with instead of copilot. The choices those processes make about tool calls, using subagents, etc make a huge difference in the quality of result you\u2019ll get. Copilot is just an extremely bad agent compared to the sota agents. Several of the open source agents will out perform copilot regularly (try aider, open code or cline if ", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "Ask HN: Senior software engineers, how do you use Claude Code?"}, {"id": 762722146, "item_id": 47670134, "url": "https://news.ycombinator.com/item?id=47670134", "by": "another_twist", "date": "2026-04-06", "stance": "recommend", "quote": "Even aider gets good results this way.", "excerpt": "Is it just me that I simply don't care ? I never one-shot these tasks, always provide a breakdown and always give the AI straightforward tasks that would take too much typing. The approach seems to work just fine regardless of the model. If it gets stuck, I usually take over and do the task myself. Also allows me to plan for throughput rather than latency - i.e. start 2-3 small tasks in parallel and do 1 complicated ", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Claude Code is unusable for complex engineering tasks with the Feb updates"}]}, {"label": "Model choice", "summary": "Works with open models, local LLMs via compatible endpoints, or frontier models like Claude Sonnet and Gemini.", "quotes": [{"id": 766356960, "item_id": 47897310, "url": "https://news.ycombinator.com/item?id=47897310", "by": "arikrahman", "date": "2026-04-24", "stance": "recommend", "quote": "I find using Aider with the new open models and using Open Spec to negotiate requirements before the handoff, has helped me a lot.", "excerpt": "I use Aider nowadays, and will probably cancel my Github multi AI bundle subscription due to the new training policy. I find using Aider with the new open models and using Open Spec to negotiate requirements before the handoff, has helped me a lot.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"}, {"id": 776731350, "item_id": 48545709, "url": "https://news.ycombinator.com/item?id=48545709", "by": "shironnnn_", "date": "2026-06-15", "stance": "neutral", "quote": "serve OpenAPI endpoints compatible for Aider (CLI) or Visual Studio Code", "excerpt": "I use SpecKit to create a very detailed plan with a high amount of specificity using paid Claude plan. Then I give it to local LLM (eg: Qwen / Gemma 4) via CLI. This is possible through usage of llm-mlx on Mac (or ollama on any machine given sufficient on hardware) which serve OpenAPI endpoints compatible for Aider (CLI) or Visual Studio Code to vibe along with the agentic coding assistant. The paid products have an ", "context": "", "use_case": "agentic coding CLI", "switched_from": "", "story": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"}, {"id": 760359968, "item_id": 47522498, "url": "https://news.ycombinator.com/item?id=47522498", "by": "Hackbraten", "date": "2026-03-25", "stance": "recommend", "quote": "I use Aider on my private computers and Copilot at work. Both feel equally powerful when configured with a decent frontier model.", "excerpt": "> There were precursors like Aider and early Cursor, but they were more assistant than agent. I use Aider on my private computers and Copilot at work. Both feel equally powerful when configured with a decent frontier model. Are they really generations apart? What am I missing?", "context": "", "use_case": "personal AI coding", "switched_from": "", "story": "Thoughts on Slowing the Fuck Down"}]}, {"label": "Productivity", "summary": "Users credit it with record commit counts and large shares of real programs, and some use it daily.", "quotes": [{"id": 754182896, "item_id": 47136431, "url": "https://news.ycombinator.com/item?id=47136431", "by": "chr15m", "date": "2026-02-24", "stance": "recommend", "quote": "I started using aider at the end of 2024 and in 2025 I again hit my highest commits ever at 2,900.", "excerpt": "That's a good point. Myself is the easiest person to fool. I knocked together a quick analysis of my commit graphs going back several years, if you're interested: https://mccormick.cx/gh/ My average leading up to 2023 was around 2k commits per year. 2023 I started using ChatGPT and I hit my highest commits so far that year at 2,600. 2024 I moved to a different country, which broke my productivity. I started using aid", "context": "freelancer, full stack", "use_case": "AI-assisted coding", "switched_from": "ChatGPT", "story": "Writing code is cheap now"}, {"id": 775317665, "item_id": 48457354, "url": "https://news.ycombinator.com/item?id=48457354", "by": "noufalibrahim", "date": "2026-06-08", "stance": "neutral", "quote": "About 40% of the program was done using Aider", "excerpt": "I needed something to help me stay off the computer (sites and applications) at certain times of the day with enforcement and in a way that's hard to remove. I had some ideas but was able to systematize all that into a proper program that I use daily. It's been very effective and it's much better (for me) than any of the commercial solutions that I've found for Linux. About 40% of the program was done using Aider (be", "context": "", "use_case": "building the program", "switched_from": "", "story": "Ask HN: What are tools you have made for yourself since the advent of AI"}, {"id": 763043603, "item_id": 47690225, "url": "https://news.ycombinator.com/item?id=47690225", "by": "Jignesh_1313", "date": "2026-04-08", "stance": "recommend", "quote": "I use Aider + Claude Code + Cursor as daily drivers", "excerpt": "The multi-agent + RAG combo is what I'm living in right now. At AmberFlux EdgeAI I'm building SHEELA \u2014 an intelligence layer that crawls, scores, and runs controlled self-improvement loops on top of a FastAPI/PostgreSQL infrastructure backbone I architected from scratch. LangGraph for the agent orchestration, async pipelines throughout. But the project that feels most relevant to what you're describing is something I", "context": "final-year engineer building AI projects", "use_case": "daily AI coding", "switched_from": "", "story": "Ask HN: Who is hiring? (April 2026)"}]}, {"label": "Control", "summary": "Seen as controllable on a large codebase, and one user says it lets them keep their own way of working.", "quotes": [{"id": 740169680, "item_id": 46260605, "url": "https://news.ycombinator.com/item?id=46260605", "by": "devdp430", "date": "2025-12-13", "stance": "recommend", "quote": "But I like aider. I had better capabilities and is controllable", "excerpt": "I use AI at work. We have a huge codebase in Golang. 1000s of files. I had tried cursor, claude code, gemini cli, openai codex and all sorts of vscode based idea (like windsurf, antigravity etc). All of them get overwhelmed when there is something to implement or change in the codebase primarily due to the amount of code. But I like aider. I had better capabilities and is controllable, you can try. And if you use it ", "context": "works on a huge Golang codebase with thousands of files", "use_case": "coding in huge Golang codebase", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}, {"id": 750170080, "item_id": 46885630, "url": "https://news.ycombinator.com/item?id=46885630", "by": "melodyogonna", "date": "2026-02-04", "stance": "recommend", "quote": "It truly is the best assistant I've used.", "excerpt": "I use Aider because it allows me to retain both personalities and still benefit from AI. It truly is the best assistant I've used.", "context": "", "use_case": "AI coding assistance", "switched_from": "", "story": "I Miss Thinking Hard"}]}, {"label": "Editor workflow", "summary": "Its watch mode and IDE mode let you drive it from comments in your own editor.", "quotes": [{"id": 752300816, "item_id": 47018801, "url": "https://news.ycombinator.com/item?id=47018801", "by": "troyvit", "date": "2026-02-14", "stance": "recommend", "quote": "aider has a watch mode that would be fun with vim", "excerpt": "I don't use it this way yet, but aider has a watch mode that would be fun with vim: https://aider.chat/docs/usage/watch.html I imagine with vim, from the document you're editing, you'd go: :ter to get a terminal. Fire up aider with --watch-files in the terminal. Hop back up to the file and start telling it what to do. Hit L when it's done to see the changes. That's just a guess but after writing it out I kinda want t", "context": "", "use_case": "AI coding alongside vim", "switched_from": "", "story": "Vim 9.2 Released"}, {"id": 751139904, "item_id": 46946244, "url": "https://news.ycombinator.com/item?id=46946244", "by": "nsm", "date": "2026-02-09", "stance": "recommend", "quote": "Aider has an ide mode close to this.", "excerpt": "Aider has an ide mode close to this. Check out https://nikhilism.com/post/2026/nudge-skill/ to add similar behavior to certain agents. I too, am waiting for IDEs to do this in a polished way. next tab edit is not quite it", "context": "", "use_case": "small voice-driven code edits", "switched_from": "", "story": "Nobody knows how the whole system works"}]}, {"label": "Low cost", "summary": "One user found prompts cost under $0.10 versus about $5 in OpenCode.", "quotes": [{"id": 732755329, "item_id": 45797208, "url": "https://news.ycombinator.com/item?id=45797208", "by": "ponyous", "date": "2025-11-03", "stance": "recommend", "quote": "while with aider I did it for <$0.1", "excerpt": "What kind of API subscription are you using? I found opencode to be incredibly expensive - prompts costing $5, while with aider I did it for <$0.1.", "context": "", "use_case": "AI coding at low cost", "switched_from": "OpenCode", "story": "Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop"}]}], "caveats": [{"label": "Token cost", "summary": "Some found token use and API-rate spending too high, and one user abandoned it over cost.", "quotes": [{"id": 790987616, "item_id": 49436726, "url": "https://news.ycombinator.com/item?id=49436726", "by": "joshstrange", "date": "2026-08-25", "stance": "neutral", "quote": "The results were good, but not worth the price for me.", "excerpt": "In the last 30 days my LLM spend, if paid at API rates, would be $19,431 (and that doesn't track online chats or my Github Action reviews). Now I wish I was making $200K/mo but I'm not, no where close. I got all that for $220 on subscriptions. Yes, LLMs are awesome and let me do things faster but I would be using them far less if my only option was the API. I used coding agents prior to subscriptions (Aider) and spen", "context": "", "use_case": "API-billed coding agent", "switched_from": "", "story": "OpenAI restores 5-hour Codex and Work limits for ChatGPT Plus users"}, {"id": 792977424, "item_id": 49561089, "url": "https://news.ycombinator.com/item?id=49561089", "by": "aitchnyu", "date": "2026-09-04", "stance": "neutral", "quote": "I used Aider on a Python project which had string references", "excerpt": "Which language and agent? I used Aider on a Python project which had string references (as opposed to module tree) and cross-repo references. LSP lookups were fast and I hated it when Aider used 2M tokens a day, but grep was more complete.", "context": "", "use_case": "AI coding on Python project", "switched_from": "", "story": "Grep beats LSP? Why coding agents ignore your fancier tools"}]}, {"label": "Newer alternatives", "summary": "Some users have switched or are considering switching to more recent agent tools.", "quotes": [{"id": 801288384, "item_id": 50080524, "url": "https://news.ycombinator.com/item?id=50080524", "by": "guyomes", "date": "2026-10-13", "stance": "neutral", "quote": "I used Aider before, and consider switching to a more recent tool.", "excerpt": "Out of curiosity, which harness do you use for this kind of task, and how do you sandbox it? I used Aider before, and consider switching to a more recent tool.", "context": "", "use_case": "AI coding assistant", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 775317665, "item_id": 48457354, "url": "https://news.ycombinator.com/item?id=48457354", "by": "noufalibrahim", "date": "2026-06-08", "stance": "neutral", "quote": "About 40% of the program was done using Aider", "excerpt": "I needed something to help me stay off the computer (sites and applications) at certain times of the day with enforcement and in a way that's hard to remove. I had some ideas but was able to systematize all that into a proper program that I use daily. It's been very effective and it's much better (for me) than any of the commercial solutions that I've found for Linux. About 40% of the program was done using Aider (be", "context": "", "use_case": "building the program", "switched_from": "", "story": "Ask HN: What are tools you have made for yourself since the advent of AI"}]}, {"label": "Manual file adding", "summary": "You have to add files to the context by hand.", "quotes": [{"id": 740169680, "item_id": 46260605, "url": "https://news.ycombinator.com/item?id=46260605", "by": "devdp430", "date": "2025-12-13", "stance": "recommend", "quote": "But I like aider. I had better capabilities and is controllable", "excerpt": "I use AI at work. We have a huge codebase in Golang. 1000s of files. I had tried cursor, claude code, gemini cli, openai codex and all sorts of vscode based idea (like windsurf, antigravity etc). All of them get overwhelmed when there is something to implement or change in the codebase primarily due to the amount of code. But I like aider. I had better capabilities and is controllable, you can try. And if you use it ", "context": "works on a huge Golang codebase with thousands of files", "use_case": "coding in huge Golang codebase", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}]}], "who": [{"by": "mrothroc", "context": "built own agent orchestration framework", "url": "https://news.ycombinator.com/item?id=47780880", "date": "2026-04-15"}, {"by": "Jignesh_1313", "context": "final-year engineer building AI projects", "url": "https://news.ycombinator.com/item?id=47690225", "date": "2026-04-08"}, {"by": "chr15m", "context": "freelancer, full stack", "url": "https://news.ycombinator.com/item?id=47136431", "date": "2026-02-24"}, {"by": "devdp430", "context": "works on a huge Golang codebase with thousands of files", "url": "https://news.ycombinator.com/item?id=46260605", "date": "2025-12-13"}], "tags": ["for local LLMs", "for large codebases", "for terminal users", "for multi-agent setups"], "use_cases": ["ai coding", "ai-assisted coding", "ai coding agent", "ai coding assistant", "ai coding on python project", "ai coding tool evaluation"], "compared": [{"slug": "opencode", "name": "OpenCode", "co": 4, "switched_from": 1, "switched_to": 1}, {"slug": "claude-code", "name": "Claude Code", "co": 6, "switched_from": 0, "switched_to": 1}, {"slug": "cursor", "name": "Cursor", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "codex", "name": "Codex", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "chatgpt", "name": "ChatGPT", "co": 1, "switched_from": 1, "switched_to": 0}, {"slug": "cline", "name": "Cline", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48542100", "title": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50073879", "title": "Gemini 4 Argon", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49560260", "title": "Grep beats LSP? Why coding agents ignore your fancier tools", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49522896", "title": "Ask HN: Who wants to be hired? (September 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49432879", "title": "OpenAI restores 5-hour Codex and Work limits for ChatGPT Plus users", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48704571", "title": "Small Teams Will Ship More Software Than They Can Maintain", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1, "neutral": 1}, "2025-12": {"recommend": 1}, "2026-01": {"recommend": 2}, "2026-02": {"recommend": 4}, "2026-03": {"recommend": 1}, "2026-04": {"recommend": 3, "neutral": 1}, "2026-05": {"recommend": 1}, "2026-06": {"neutral": 4}, "2026-07": {}, "2026-08": {"neutral": 1}, "2026-09": {"compare": 1, "neutral": 1}, "2026-10": {"neutral": 1}}, "quotes": [{"id": 801288384, "item_id": 50080524, "url": "https://news.ycombinator.com/item?id=50080524", "by": "guyomes", "date": "2026-10-13", "stance": "neutral", "quote": "I used Aider before, and consider switching to a more recent tool.", "excerpt": "Out of curiosity, which harness do you use for this kind of task, and how do you sandbox it? I used Aider before, and consider switching to a more recent tool.", "context": "", "use_case": "AI coding assistant", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 792977424, "item_id": 49561089, "url": "https://news.ycombinator.com/item?id=49561089", "by": "aitchnyu", "date": "2026-09-04", "stance": "neutral", "quote": "I used Aider on a Python project which had string references", "excerpt": "Which language and agent? I used Aider on a Python project which had string references (as opposed to module tree) and cross-repo references. LSP lookups were fast and I hated it when Aider used 2M tokens a day, but grep was more complete.", "context": "", "use_case": "AI coding on Python project", "switched_from": "", "story": "Grep beats LSP? Why coding agents ignore your fancier tools"}, {"id": 792544193, "item_id": 49534012, "url": "https://news.ycombinator.com/item?id=49534012", "by": "dan_voronov", "date": "2026-09-02", "stance": "compare", "quote": "AI coding tool evaluations (Cursor, Aider, Cline, Windsurf, etc.)", "excerpt": "I\u2019ve been researching how LLMs generate code since summer 2023. My main public artifact is this repository: https://github.com/danvoronov/CodeWithLLM-Updates It\u2019s a living research collection with 400+ commits covering practical experiments, usage patterns, step-by-step guides, model comparisons, AI coding tool evaluations (Cursor, Aider, Cline, Windsurf, etc.). A large part of my work is *exploratory*: navigating la", "context": "researching LLM code generation since 2023", "use_case": "AI coding tool evaluation", "switched_from": "", "story": "Ask HN: Who wants to be hired? (September 2026)"}, {"id": 790987616, "item_id": 49436726, "url": "https://news.ycombinator.com/item?id=49436726", "by": "joshstrange", "date": "2026-08-25", "stance": "neutral", "quote": "The results were good, but not worth the price for me.", "excerpt": "In the last 30 days my LLM spend, if paid at API rates, would be $19,431 (and that doesn't track online chats or my Github Action reviews). Now I wish I was making $200K/mo but I'm not, no where close. I got all that for $220 on subscriptions. Yes, LLMs are awesome and let me do things faster but I would be using them far less if my only option was the API. I used coding agents prior to subscriptions (Aider) and spen", "context": "", "use_case": "API-billed coding agent", "switched_from": "", "story": "OpenAI restores 5-hour Codex and Work limits for ChatGPT Plus users"}, {"id": 779301248, "item_id": 48706328, "url": "https://news.ycombinator.com/item?id=48706328", "by": "joshstrange", "date": "2026-06-28", "stance": "neutral", "quote": "used tools like Aider before coding agent harnesses we really \u201ca thing\u201d", "excerpt": "The unresolved question is: Can LLMs improve faster than the tech debt catches up to you. A lot of people/companies are betting on \u201cyes\u201d. I honestly don\u2019t know where I stand. I can\u2019t, in good conscience, yolo code into my company\u2019s code base. I use LLMs extensively but I\u2019m not ready to abdicate my understanding and review of new code. I have 100% vibed little prototypes or side projects for myself where I\u2019ve never lo", "context": "", "use_case": "AI-assisted coding", "switched_from": "", "story": "Small Teams Will Ship More Software Than They Can Maintain"}, {"id": 776731350, "item_id": 48545709, "url": "https://news.ycombinator.com/item?id=48545709", "by": "shironnnn_", "date": "2026-06-15", "stance": "neutral", "quote": "serve OpenAPI endpoints compatible for Aider (CLI) or Visual Studio Code", "excerpt": "I use SpecKit to create a very detailed plan with a high amount of specificity using paid Claude plan. Then I give it to local LLM (eg: Qwen / Gemma 4) via CLI. This is possible through usage of llm-mlx on Mac (or ollama on any machine given sufficient on hardware) which serve OpenAPI endpoints compatible for Aider (CLI) or Visual Studio Code to vibe along with the agentic coding assistant. The paid products have an ", "context": "", "use_case": "agentic coding CLI", "switched_from": "", "story": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"}, {"id": 776726386, "item_id": 48545399, "url": "https://news.ycombinator.com/item?id=48545399", "by": "twothreeone", "date": "2026-06-15", "stance": "neutral", "quote": "I used \"aider\" to replace claude CLI, which maybe that's also sub-optimal", "excerpt": "> unsloth/Qwen3.6-35B-A3B-MTP-GGUF I've actually tried this exact same model locally as well.. albeit on just a single 3090 at 128k context and I got around 40-60tok/s with Q4_K quantization. The thing that bugged me the most was really the quality of the output on moderately complex real-world coding tasks. Having to switch between \"prompt/vibe\" and \"manually implement\" is such a big context switch burden, because y", "context": "", "use_case": "local coding harness", "switched_from": "Claude CLI", "story": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"}, {"id": 775317665, "item_id": 48457354, "url": "https://news.ycombinator.com/item?id=48457354", "by": "noufalibrahim", "date": "2026-06-08", "stance": "neutral", "quote": "About 40% of the program was done using Aider", "excerpt": "I needed something to help me stay off the computer (sites and applications) at certain times of the day with enforcement and in a way that's hard to remove. I had some ideas but was able to systematize all that into a proper program that I use daily. It's been very effective and it's much better (for me) than any of the commercial solutions that I've found for Linux. About 40% of the program was done using Aider (be", "context": "", "use_case": "building the program", "switched_from": "", "story": "Ask HN: What are tools you have made for yourself since the advent of AI"}, {"id": 771136051, "item_id": 48196003, "url": "https://news.ycombinator.com/item?id=48196003", "by": "m24927605", "date": "2026-05-19", "stance": "recommend", "quote": "the AI coding agents I use daily \u2014 Claude Code, Codex CLI, Aider", "excerpt": "I built ait because the AI coding agents I use daily \u2014 Claude Code, Codex CLI, Aider \u2014 are fast individually, but no tool lets me put two of them in the same loop. You pick one. It runs. You hope it's right. That's not multi-agent \u2014 that's single-agent with chat history. ait is a local control plane that runs Claude Code, Codex, Aider, Gemini CLI, and Cursor as a team on the same task. One agent investigates, hands t", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Show HN: Ait \u2013 Claude, Codex, and Aider as a team, on your laptop"}, {"id": 766356960, "item_id": 47897310, "url": "https://news.ycombinator.com/item?id=47897310", "by": "arikrahman", "date": "2026-04-24", "stance": "recommend", "quote": "I find using Aider with the new open models and using Open Spec to negotiate requirements before the handoff, has helped me a lot.", "excerpt": "I use Aider nowadays, and will probably cancel my Github multi AI bundle subscription due to the new training policy. I find using Aider with the new open models and using Open Spec to negotiate requirements before the handoff, has helped me a lot.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"}, {"id": 764494080, "item_id": 47780880, "url": "https://news.ycombinator.com/item?id=47780880", "by": "mrothroc", "date": "2026-04-15", "stance": "neutral", "quote": "Long ago it started as shell scripts that I used in conjunction with aider.", "excerpt": "I created my own framework. Long ago it started as shell scripts that I used in conjunction with aider. It was a very manual process. It's grown over time to be a full MCP and CLI with stages and gates defined in YAML. I was thinking about open sourcing it but since the code grew organically I would need to do extensive cleanup to make it presentable. But I do walk through the process on page 9: https://michael.roth.", "context": "built own agent orchestration framework", "use_case": "early agent workflow", "switched_from": "", "story": "Multi-Agentic Software Development Is a Distributed Systems Problem"}, {"id": 763043603, "item_id": 47690225, "url": "https://news.ycombinator.com/item?id=47690225", "by": "Jignesh_1313", "date": "2026-04-08", "stance": "recommend", "quote": "I use Aider + Claude Code + Cursor as daily drivers", "excerpt": "The multi-agent + RAG combo is what I'm living in right now. At AmberFlux EdgeAI I'm building SHEELA \u2014 an intelligence layer that crawls, scores, and runs controlled self-improvement loops on top of a FastAPI/PostgreSQL infrastructure backbone I architected from scratch. LangGraph for the agent orchestration, async pipelines throughout. But the project that feels most relevant to what you're describing is something I", "context": "final-year engineer building AI projects", "use_case": "daily AI coding", "switched_from": "", "story": "Ask HN: Who is hiring? (April 2026)"}, {"id": 762722146, "item_id": 47670134, "url": "https://news.ycombinator.com/item?id=47670134", "by": "another_twist", "date": "2026-04-06", "stance": "recommend", "quote": "Even aider gets good results this way.", "excerpt": "Is it just me that I simply don't care ? I never one-shot these tasks, always provide a breakdown and always give the AI straightforward tasks that would take too much typing. The approach seems to work just fine regardless of the model. If it gets stuck, I usually take over and do the task myself. Also allows me to plan for throughput rather than latency - i.e. start 2-3 small tasks in parallel and do 1 complicated ", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Claude Code is unusable for complex engineering tasks with the Feb updates"}, {"id": 760359968, "item_id": 47522498, "url": "https://news.ycombinator.com/item?id=47522498", "by": "Hackbraten", "date": "2026-03-25", "stance": "recommend", "quote": "I use Aider on my private computers and Copilot at work. Both feel equally powerful when configured with a decent frontier model.", "excerpt": "> There were precursors like Aider and early Cursor, but they were more assistant than agent. I use Aider on my private computers and Copilot at work. Both feel equally powerful when configured with a decent frontier model. Are they really generations apart? What am I missing?", "context": "", "use_case": "personal AI coding", "switched_from": "", "story": "Thoughts on Slowing the Fuck Down"}, {"id": 754182896, "item_id": 47136431, "url": "https://news.ycombinator.com/item?id=47136431", "by": "chr15m", "date": "2026-02-24", "stance": "recommend", "quote": "I started using aider at the end of 2024 and in 2025 I again hit my highest commits ever at 2,900.", "excerpt": "That's a good point. Myself is the easiest person to fool. I knocked together a quick analysis of my commit graphs going back several years, if you're interested: https://mccormick.cx/gh/ My average leading up to 2023 was around 2k commits per year. 2023 I started using ChatGPT and I hit my highest commits so far that year at 2,600. 2024 I moved to a different country, which broke my productivity. I started using aid", "context": "freelancer, full stack", "use_case": "AI-assisted coding", "switched_from": "ChatGPT", "story": "Writing code is cheap now"}, {"id": 752300816, "item_id": 47018801, "url": "https://news.ycombinator.com/item?id=47018801", "by": "troyvit", "date": "2026-02-14", "stance": "recommend", "quote": "aider has a watch mode that would be fun with vim", "excerpt": "I don't use it this way yet, but aider has a watch mode that would be fun with vim: https://aider.chat/docs/usage/watch.html I imagine with vim, from the document you're editing, you'd go: :ter to get a terminal. Fire up aider with --watch-files in the terminal. Hop back up to the file and start telling it what to do. Hit L when it's done to see the changes. That's just a guess but after writing it out I kinda want t", "context": "", "use_case": "AI coding alongside vim", "switched_from": "", "story": "Vim 9.2 Released"}, {"id": 751139904, "item_id": 46946244, "url": "https://news.ycombinator.com/item?id=46946244", "by": "nsm", "date": "2026-02-09", "stance": "recommend", "quote": "Aider has an ide mode close to this.", "excerpt": "Aider has an ide mode close to this. Check out https://nikhilism.com/post/2026/nudge-skill/ to add similar behavior to certain agents. I too, am waiting for IDEs to do this in a polished way. next tab edit is not quite it", "context": "", "use_case": "small voice-driven code edits", "switched_from": "", "story": "Nobody knows how the whole system works"}, {"id": 750170080, "item_id": 46885630, "url": "https://news.ycombinator.com/item?id=46885630", "by": "melodyogonna", "date": "2026-02-04", "stance": "recommend", "quote": "It truly is the best assistant I've used.", "excerpt": "I use Aider because it allows me to retain both personalities and still benefit from AI. It truly is the best assistant I've used.", "context": "", "use_case": "AI coding assistance", "switched_from": "", "story": "I Miss Thinking Hard"}, {"id": 745544560, "item_id": 46596535, "url": "https://news.ycombinator.com/item?id=46596535", "by": "troyvit", "date": "2026-01-12", "stance": "recommend", "quote": "If you want to have some fun check out aider.chat.", "excerpt": "If you want to have some fun check out aider.chat. They actually log how much of each version was built by aider itself: https://github.com/Aider-AI/aider/releases", "context": "", "use_case": "AI coding CLI", "switched_from": "", "story": "Remote Code Execution in OpenCode, update now"}, {"id": 745241491, "item_id": 46577593, "url": "https://news.ycombinator.com/item?id=46577593", "by": "kasey_junk", "date": "2026-01-11", "stance": "recommend", "quote": "Several of the open source agents will out perform copilot regularly (try aider, open code or cline if you can).", "excerpt": "It is not the same. The agents (Claude code, codex) are the actual processes you\u2019d interact with instead of copilot. The choices those processes make about tool calls, using subagents, etc make a huge difference in the quality of result you\u2019ll get. Copilot is just an extremely bad agent compared to the sota agents. Several of the open source agents will out perform copilot regularly (try aider, open code or cline if ", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "Ask HN: Senior software engineers, how do you use Claude Code?"}, {"id": 740169680, "item_id": 46260605, "url": "https://news.ycombinator.com/item?id=46260605", "by": "devdp430", "date": "2025-12-13", "stance": "recommend", "quote": "But I like aider. I had better capabilities and is controllable", "excerpt": "I use AI at work. We have a huge codebase in Golang. 1000s of files. I had tried cursor, claude code, gemini cli, openai codex and all sorts of vscode based idea (like windsurf, antigravity etc). All of them get overwhelmed when there is something to implement or change in the codebase primarily due to the amount of code. But I like aider. I had better capabilities and is controllable, you can try. And if you use it ", "context": "works on a huge Golang codebase with thousands of files", "use_case": "coding in huge Golang codebase", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}, {"id": 737293266, "item_id": 46080829, "url": "https://news.ycombinator.com/item?id=46080829", "by": "jauntywundrkind", "date": "2025-11-28", "stance": "neutral", "quote": "With both Aider and OpenCode, there's a nice history.", "excerpt": "Somewhat aside but I love the data architrcture. Jsonl lines checked into git, and a sqlite local cache. Auto-sync to replicate changes between the canonical and cache. https://github.com/steveyegge/beads?tab=readme-ov-file#the-magic-distributed-database-via-git I finally started digging in to OpenCode for real these past couple weeks. It has a planning mode, which nicely builds out a plan on text chat as usual, but ", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "Beads \u2013 A memory upgrade for your coding agent"}, {"id": 732755329, "item_id": 45797208, "url": "https://news.ycombinator.com/item?id=45797208", "by": "ponyous", "date": "2025-11-03", "stance": "recommend", "quote": "while with aider I did it for <$0.1", "excerpt": "What kind of API subscription are you using? I found opencode to be incredibly expensive - prompts costing $5, while with aider I did it for <$0.1.", "context": "", "use_case": "AI coding at low cost", "switched_from": "OpenCode", "story": "Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop"}]}