The best ai coding agents, according to hackers
18 ai coding agents recommended in Hacker News comments over the past year, ranked by how many separate people recommend each one.
- Most recommendedClaude Code4522 people recommend it
- Built to lastClineowners report a median of 1 years
- Least regretCrush by Charmbracelet39 recommend, 8 criticize
All ai coding agents
- Claude CodeAn agentic coding tool that writes, runs and tests code on its own, often replacing hand-coding entirely, though many report quality regressions after updates and broken code on complex work.4522recommend
- OpenAI CodexA coding agent many find as good as or better than Claude Code, thorough on hard problems, with generous $20-plan limits, though its output needs careful review.2474recommend
- OpenCodeAn open-source coding agent recommended for mixing models and providers, including cheap or local ones, with a good-value Go plan; critics cite prompt privacy, security holes and bloat.1060recommend
- Gemini CLIGoogle's terminal coding agent is liked for its generous free tier, polished interface and strong one-shot results, but critics cite rate limits, bugs, eager code edits and its planned discontinuation.172recommend
- ClineFree open-source VS Code agent that works with your own API key, billed per token. Critics note context loss in long sessions.63recommend
- Mistral VibeA terminal coding agent people recommend for cheap subscription value and an open-source CLI; the most common caveat is weaker models and data-use defaults on Team plans.57recommend
- Amp coding agentPopular AI coding agent that people find capable and fast on hard tasks, with a free tier that shows ads. Caveat: usage costs can add up quickly.50recommend
- Kilo CodeOpen-source VS Code extension for switching between many AI models and providers, a model-agnostic alternative to Cursor. Critics mainly flag background npm package downloads.46recommend
- Crush by CharmbraceletFree open-source terminal coding agent that works with any AI provider, praised for its polished interface and language server support. Main caveat: docs are thin for local models.39recommend
- JetBrains JunieRecommended for an IDE-integrated agent that works well out of the box and is cheap or included with subscriptions. Critics cite few curated models and quotas running out.35recommend
- DevinPeople recommend it for delegating small, well-scoped coding tasks and getting pull requests back. Critics say it is expensive and that debugging its output takes longer than generating it.33recommend
- Goose by BlockOpen-source coding agent praised for lean context and working with many model providers; critics say setup is hard and it trails big-brand tools.29recommend
- ZCodePeople like its clean UI, Linux support and solid coding quality for GLM models, but critics warn it uploads project folders and git history to a Chinese-owned server.19recommend
- Factory DroidPeople recommend Droid as a capable coding agent that pairs well with Claude Opus and needs little hand-holding. Critics dislike its pushy, cringe marketing.16recommend
- Dirge CodeA free Rust coding agent that people recommend for its batteries-included setup, plugin customization, and noticeable gains in model capability.8recommend
- Astra for CodingCapable AI coding agent that people use to finish multi-step programming tasks; critics say it overengineers code and costs more in usage.8recommend
- Muse Code by MetaRecommended for a cheap subscription that unlocks strong contributor model usage. Critics most often warn about data sharing, unreliable payments and rough edges.7recommend
- Claw CodeFree coding agent that runs any model and claims around 30% average token savings; critics say it copies Claude Code under a clean-room label.6recommend