Aider
Hacker ApprovedCoding assistant in Developer tools
Free terminal tool for targeted code edits in a chat loop, with you controlling files and context. Caveat: weak at heavy, multi-step edits.
Free terminal tool for targeted code edits in a chat loop, with you controlling files and context. Caveat: weak at heavy, multi-step edits.
106 people gave an opinion
- recommend it
- 75
- criticize it
- 31
- approval share
- 71%
Recommended in 12 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Owned for 1 year
Median of the 7 owners who said how long they have had it.
Each square is one year.
Why it carries the badge
- 75 people recommend itNeeds 10 or more, met.
- 2.4 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 12 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Tight control over files and context
“Having tight control over the context and only giving it small tasks makes all the difference.”
Comment from 8 Jan 2026 in “AI Coding Assistants Are Getting Worse” “It lets you be completely precise down to a single file, and sit in chat/code/review loop”
Comment from 6 Jan 2026 in “Opus 4.5 is going to change everything” “Good with Aider since you can keep it on a tighter leash than with a fully agentic tool.”
Comment from 9 Dec 2025 in “Mistral releases Devstral2 and Mistral Vibe CLI” - Comment from 29 Nov 2025 in “Gemini CLI tips and tricks for agentic coding”
- Comment from 21 Mar 2026 in “OpenCode – The open source AI coding agent”
Not fully agentic, less autonomous
“I was able to ship with Aider before as it uses less autonomous approach than the current wave of agentic tools.”
Comment from 21 Jan 2026 in “Ask HN: Do you have any evidence that agentic coding works?” “the only tool that even produced decent results that far back, it wasn't fully agentic”
Comment from 5 Feb 2026 in “Claude Code Agent Teams” “It is deliberately NOT a fully agentic tool and this really oftentimes is a benefit.”
Comment from 14 Dec 2025 in “Ask HN: How can I get better at using AI for programming?” Uses tokens efficiently
“Tools like aider and opencode (each in their own way) use separate tools build a map of the codebase that they can use to work with code using fewer tokens.”
Comment from 23 Jan 2026 in “I was banned from Claude for scaffolding a Claude.md file” “with Aider you include relevant files up front and use your tokens for the real work”
Comment from 29 Nov 2025 in “Gemini CLI tips and tricks for agentic coding” “Using Aider with Claude Sonnet I am eating much less tokens than CC does.”
Comment from 9 Jan 2026 in “Anthropic bans use of API in OpenCode CLI tool” - Comment from 15 Feb 2026 in “IBM Triples Entry Level Job Openings. Finds Limits to AI”
Works well with strong models
“Aider with Gemini 2.5 was way ahead of its time, and with O3 it was best in class until Claude Code with Sonnet 4.”
Comment from 4 Feb 2026 in “OpenClaw (a.k.a. Moltbot) Is Everywhere All at Once, and a Disaster” “Aider+Gemini 3 or other good model. May be in some specific cases it actually better”
Comment from 7 Jan 2026 in “Stop Doom Scrolling, Start Doom Coding: Build via the terminal from your phone” “I have good success with free gemini used either via the web UI or with aider.”
Comment from 7 Mar 2026 in “I'm 60 years old. Claude Code has ignited a passion again”
What people warn about
Each mark is one comment
Terminal rendering and layout problems
“Things like aider use prompt toolkit and loses the layout when you resize window”
Comment from 26 Mar 2026 in “Rendering complex scripts in terminal and OSC 66” “thats an issue with aider. using a proper framework in the alternate terminal buffer would have greatly benefitted them”
Comment from 10 Dec 2025 in “Mistral releases Devstral2 and Mistral Vibe CLI” “struggling to display text as fast as the llm is spitting it out”
Comment from 9 Dec 2025 in “Mistral releases Devstral2 and Mistral Vibe CLI” Development stalled, no recent releases
“Aider development has completely stopped. There had been an MCP support PR that was open for over half a year”
Comment from 22 Dec 2025 in “Claude in Chrome” “now dealing with its relative abandonment and deciding if I want to invest time in a fork”
Comment from 16 Jan 2026 on Hacker News “has been no release in half a year, is missing major features (e.g. MCP server)”
Comment from 30 Mar 2026 in “Neovim 0.12.0” Context drift and agents conflicting
“the model kept suffering from severe context drift, hitting a hard ceiling of a 20% pass rate on multi-step tasks”
Comment from 16 Mar 2026 in “Beating Aider's 20% pass rate on local Qwen 32B using deterministic RAG” “my experience with Gemini and aider is that multiple instances of agents will absolutely stomp over each other”
Comment from 7 Jan 2026 in “The creator of Claude Code's Claude setup”
What people said
40 of the 135 comments that mention it, newest first. Each links to the original comment.
“Aider in watching mode is almost this, but I'd have to insert and save actual "AI:" comments for it to replace.”
“Aider at least respects .gitignore and keeps everything local unless you explicitly configure a remote endpoint.”
“it was already decent and pretty close to the DX we consider coding agents to have”
“getting Sonnet 3.5 with Aider to boostrap an (albeit basic) project and getting it to work”
“all fell back to telling me about Aider or OpenCode and ignored my query completely”
“jumping straight into the terminal with Claude Code or Aider is easily 10x faster”
“has been no release in half a year, is missing major features (e.g. MCP server)”
“Things like aider use prompt toolkit and loses the layout when you resize window”
“One thing I like with Aider is the fact that I can control the context”
“the model kept suffering from severe context drift, hitting a hard ceiling of a 20% pass rate on multi-step tasks”
“I have good success with free gemini used either via the web UI or with aider.”
“I started using aider at the end of 2024 and in 2025 I again hit my highest commits ever”
“I don't have to worry about paying per token or hitting plan limits”
“Aider's benchmarks on practical applicability of model advancements vs. regressions in code editing observably drove both OpenAI and Anthropic to pay closer attention”
“The most useful AI dev workflow improvements I've seen (cursor rules, aider conventions, claude hooks) all succeeded precisely because they stayed close to existing tools.”
“the only tool that even produced decent results that far back, it wasn't fully agentic”
“Aider with Gemini 2.5 was way ahead of its time, and with O3 it was best in class until Claude Code with Sonnet 4.”
“You get three, in fact: an architect model, a code editor model, and a quick model for things like commit messages.”
“Tools like aider and opencode (each in their own way) use separate tools build a map of the codebase that they can use to work with code using fewer tokens.”
“I was able to ship with Aider before as it uses less autonomous approach than the current wave of agentic tools.”
“now dealing with its relative abandonment and deciding if I want to invest time in a fork”
“check out aider.chat. They actually log how much of each version was built by aider itself”
“Several of the open source agents will out perform copilot regularly (try aider, open code or cline if you can).”
“Using Aider with Claude Sonnet I am eating much less tokens than CC does.”
“I actually started to appreciate these constraints as a way to really familiarise myself”
“Having tight control over the context and only giving it small tasks makes all the difference.”
“Aider+Gemini 3 or other good model. May be in some specific cases it actually better”
“my experience with Gemini and aider is that multiple instances of agents will absolutely stomp over each other”
“what I found is that comprehensively writing up the documentation for a feature spec style before starting eliminates a huge amount”
“It lets you be completely precise down to a single file, and sit in chat/code/review loop”
“one of my favorite uses of Aider is telling it to edit config files/small utility scripts for me”
“Aider development has completely stopped. There had been an MCP support PR that was open for over half a year”
“It is deliberately NOT a fully agentic tool and this really oftentimes is a benefit.”
“thats an issue with aider. using a proper framework in the alternate terminal buffer would have greatly benefitted them”
“struggling to display text as fast as the llm is spitting it out”
“Good with Aider since you can keep it on a tighter leash than with a fully agentic tool.”
“If your goal is to edit code and not discuss it aider also supports a watch mode”
“I'm happy with the 2-3x improvement I get from lesser tools that still leave me in control.”
“with Aider you include relevant files up front and use your tokens for the real work”
“It's blazing fast and great for quick changes. It's not the greatest agent for doing heavy edits”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.