# Aider 75 Hacker News commenters recommended Aider and 31 criticized it, November 2025 to November 2026. It was recommended in 12 of 13 months; owners who said how long report a median of 1 years (7 owners). It meets the Hacker Approved badge rule. **Verdict:** Free terminal tool for targeted code edits in a chat loop, with you controlling files and context. Caveat: weak at heavy, multi-step edits. ## Why people recommend it - Tight control over files and context (5 comments): "Having tight control over the context and only giving it small tasks makes all the difference." ([source](https://news.ycombinator.com/item?id=46542942)) "It lets you be completely precise down to a single file, and sit in chat/code/review loop" ([source](https://news.ycombinator.com/item?id=46519354)) "Good with Aider since you can keep it on a tighter leash than with a fully agentic tool." ([source](https://news.ycombinator.com/item?id=46210025)) - Not fully agentic, less autonomous (3 comments): "I was able to ship with Aider before as it uses less autonomous approach than the current wave of agentic tools." ([source](https://news.ycombinator.com/item?id=46702469)) "the only tool that even produced decent results that far back, it wasn't fully agentic" ([source](https://news.ycombinator.com/item?id=46904853)) "It is deliberately NOT a fully agentic tool and this really oftentimes is a benefit." ([source](https://news.ycombinator.com/item?id=46260755)) - Uses tokens efficiently (4 comments): "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." ([source](https://news.ycombinator.com/item?id=46728800)) "with Aider you include relevant files up front and use your tokens for the real work" ([source](https://news.ycombinator.com/item?id=46084069)) "Using Aider with Claude Sonnet I am eating much less tokens than CC does." ([source](https://news.ycombinator.com/item?id=46552068)) - Works well with strong models (3 comments): "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." ([source](https://news.ycombinator.com/item?id=46881162)) "Aider+Gemini 3 or other good model. May be in some specific cases it actually better" ([source](https://news.ycombinator.com/item?id=46527501)) "I have good success with free gemini used either via the web UI or with aider." ([source](https://news.ycombinator.com/item?id=47287182)) ## What people warn about - Terminal rendering and layout problems (3 comments): "Things like aider use prompt toolkit and loses the layout when you resize window" ([source](https://news.ycombinator.com/item?id=47528115)) "thats an issue with aider. using a proper framework in the alternate terminal buffer would have greatly benefitted them" ([source](https://news.ycombinator.com/item?id=46215072)) "struggling to display text as fast as the llm is spitting it out" ([source](https://news.ycombinator.com/item?id=46211528)) - Development stalled, no recent releases (3 comments): "Aider development has completely stopped. There had been an MCP support PR that was open for over half a year" ([source](https://news.ycombinator.com/item?id=46350735)) "now dealing with its relative abandonment and deciding if I want to invest time in a fork" ([source](https://news.ycombinator.com/item?id=46647458)) "has been no release in half a year, is missing major features (e.g. MCP server)" ([source](https://news.ycombinator.com/item?id=47570014)) - Context drift and agents conflicting (2 comments): "the model kept suffering from severe context drift, hitting a hard ceiling of a 20% pass rate on multi-step tasks" ([source](https://news.ycombinator.com/item?id=47401193)) "my experience with Gemini and aider is that multiple instances of agents will absolutely stomp over each other" ([source](https://news.ycombinator.com/item?id=46524024)) ## Cite as Hacker Approved, "Aider", https://hackerapproved.com/p/aider/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).