macrostack
Best of · 8 tools ranked

The best AI Coding Assistants

Every option ranked — open-source, self-hostable, and commercial — by our transparent Sovereignty Score, with honest trade-offs so you choose what fits you, not us.

AI pair programmers and autonomous coding agents — the tools that read your repository, write and refactor code, and run commands on your behalf. Compare editor-integrated agents, terminal agents and self-hosted platforms on licence, model choice, whether they can run against a model on your own hardware, and what a month actually costs.

L5Applications — layer 5 of the AI stack
  1. 1

    opencode

    Top pickOpen source

    The MIT terminal agent that picks up your CLAUDE.md where you left it.

    Free and open source (MIT); you pay your own model provider. Optional OpenCode Go at $10/month (Go Plus $40/month) for open-source models, or the pay-as-you-go Zen gateway. Verified on opencode.ai 2026-10-03. · in our Claude Code comparison →

    93
    sovereignty
    What is opencode? →
  2. 2

    Cline

    Top pickOpen source

    The open-source agent that lives in the editor you already have.

    Free and open source (Apache-2.0) — you pay only your model provider. Optional prepaid Cline credits and a paid enterprise tier exist; bring-your-own-key needs no account. · in our Cursor comparison →

    92
    sovereignty
    What is Cline? →
  3. 3

    goose

    Open source

    A general-purpose open agent (desktop app, CLI and API) governed at the Linux Foundation.

    Free and open source (Apache-2.0); you pay only your model provider, or nothing beyond hardware with a local model. · in our Claude Code comparison →

    93
    sovereignty
    What is goose? →
  4. 4

    OpenHands

    Open source

    Self-hosted, sandboxed coding agents — the whole stack runs on infrastructure you control.

    Free and open source (MIT) to self-host — you pay only your model provider. Managed OpenHands Cloud and a licensed enterprise self-host are the paid tiers. · in our Cursor comparison →

    91
    sovereignty
    What is OpenHands? →
  5. 5

    Qwen Code

    Open source

    An Apache-2.0 agent that measures itself against Claude Code and runs on any provider.

    Free and open source (Apache-2.0); you pay your chosen provider, or nothing beyond hardware with a local model. · in our Claude Code comparison →

    91
    sovereignty
    What is Qwen Code? →
  6. 6

    Aider

    Open source

    Git-native pair programming in the terminal — every change lands as a commit.

    Free and open source (Apache-2.0) — you pay only your model provider. No account, no hosted tier, no credits. · in our Cursor comparison →

    89
    sovereignty
    What is Aider? →
  7. 7

    Codex CLI

    Open source

    OpenAI's Apache-2.0 terminal agent, included in the ChatGPT plan you may already pay for.

    Free, open-source client (Apache-2.0). Included with ChatGPT plans, with the CLI listed from Plus ($20/month) and Pro from $100/month; or an API key at API rates. Local models via --oss cost nothing extra. Verified on OpenAI's Codex pricing page 2026-10-03. · in our Claude Code comparison →

    79
    sovereignty
    What is Codex CLI? →
  8. 8

    GitHub Copilot

    Commercial

    The polished commercial option at half the price — and for many readers the honest answer.

    Free tier (2,000 completions/month); Pro $10/mo; Pro+ $39/mo; Max $100/mo; Business $19/seat/mo; Enterprise $39/seat/mo. Verified on GitHub's own plans documentation 2026-07-29. · in our Cursor comparison →

    28
    sovereignty
    What is GitHub Copilot? →

Is it free?

The free tier, its real limits and where you start paying — read from each vendor's own pricing page and dated.

Run these yourself

What each one actually needs — real RAM, honest running cost, and the setup time nobody quotes.

  • Self-hosting Cline 32 GB for a local model that actually works. Cline's tested minimum is Qwen3 Coder 30B at 4-bit (~17 GB download, 32K context, Compact Prompt on). 64 GB runs the 8-bit version (~32 GB) with 128K context and every feature. With an API key, any machine that runs VS Code is enough.
  • Self-hosting Aider With an API key: any laptop. Locally, to be usable: enough GPU or unified memory for a ~20 GB model plus its context (qwen2.5-coder:32b at 4-bit). In practice that means a 24 GB GPU or a 32 GB+ Apple Silicon Mac. The fp16 build named in aider's own config example is 66 GB.

Replacing a specific tool?

Head-to-head comparisons for each popular ai coding assistants product.

Straight head-to-heads

Two ai coding assistants tools, side by side — verified facts and a plain verdict.

The Macrostack brief

New swaps, worth your inbox.

A short, occasional email when we add a high-intent alternative or ship a new head-to-head. No spam, no selling your address — unsubscribe in one click.