Open-source AI pair programming CLI. The only tool in the coding CLI category with a fully verifiable, independent download number: 191,828/week PyPI installs, 5.7M lifetime, 15B tokens/week (homepage stat). Multi-model, git-native, no vendor lock-in. v0.86.2 released 2026-02-12.
Shipped last month
Aider promoted to #4 in coding-clis (was #10)
5.7M total installs, 200-250K/month, 15B tokens/week, and battle-tested reliability earn Aider a Tier 2 placement. Category pioneer with the strongest open-source terminal coding track record. · 2026-03-25
Where it wins
191,828/week PyPI installs (verified 2026-03-18) — 5.7M lifetime, 15B tokens/week: the most independently verifiable usage metric outside Claude Code
Multi-model: any OpenAI-compatible API — no vendor lock-in
Git-native: auto-commits changes with clean diffs, surgical refactor workflow
Most cost-efficient agent tested: 52.7% accuracy at 3x fewer tokens than Claude Code (AIMultiple)
Hosts the Aider Polyglot benchmark — category's neutral standard-setter
Where to be skeptical
Latest release v0.86.2 (2026-02-12) — slower shipping cadence than daily-release competitors
Less agentic autonomy than Claude Code or Codex CLI — chat-loop rather than full agent loop
No published SWE-bench Pro standardized score
Star growth (42K) lower than Gemini CLI (98K) and Codex CLI (66K)
Category pressure: HN thread 'Claude Code with Sonnet 4 is so good I have stopped using Aider' (#44154020) signals community migration to higher-autonomy tools
Editorial verdict
#7 coding CLI — strong verification story (191K PyPI/week, 5.7M lifetime), but Codex CLI at 2.49M npm/week and Gemini CLI at 678K/week have overtaken Aider's download rank. Category pressure is real: HN thread 'Claude Code with Sonnet 4 is so good I have stopped using Aider' (#44154020). Best for Python devs who want fine-grained model control and git-native workflow. v0.86.2 (2026-02-12) is 5 weeks behind competitors shipping daily.
Source
Videos
Reviews, tutorials, and comparisons from the community.
My aider AI dev setup
Aider is SUPER Powerful BUT...
I Let Aider AI Refactor My App
Related
Coding CLIs / Code Agents
Git-heavy workflows, multi-provider flexibility, mature battle-tested tool
Software Factories
CLI power users wanting open-source, multi-model, git-native pair programming with zero lock-in
Claude Code
98Anthropic's official agentic coding CLI. v2.1.81 (Mar 20) shipped `--bare`, smarter worktree resume, and improved MCP OAuth while the repo crossed 82,204 stars and logged ~14 commits/week across 10+ maintainers. Terminal-native, tool-use-driven, with deep file system + shell access, #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue. 8M+ npm weekly downloads. Opus 4.6 with 1M context.
OpenHands
88Category leader in multi-agent orchestration — 69,352 stars (verified), $18.8M Series A, AMD hardware partnership, 455 contributors, 1M downloads/month PyPI (3.4M all-time). SWE-Bench Verified 72% with Claude 4.5 Extended Thinking (updated 2026-03-19), Multi-SWE-Bench #1 across 8 languages. Gap to #2 is enormous on every axis.
OpenCode
88Open-source AI coding agent from SST. v1.2.27 active (2026-03-16) — development resumed after a gap. OpenAI official partnership following the Anthropic OAuth block controversy. 126K+ GitHub stars (star surge driven by Anthropic controversy). Known unauthenticated RCE fixed in v1.1.10+ (CVE, 432 HN pts). CVE-2026-22812 (CVSS 8.8-10.0) is a second serious security incident.
Gemini CLI
88Google's open-source terminal agent with Gemini 3 models, 1M token context, built-in Google Search grounding, and the best free tier in the category (60 req/min, 1K req/day). v0.35.0 (Mar 24) shipped keybinding, policy, and telemetry fixes while the repo hit 98,957 stars and 12,593 forks. Terminal-Bench 2.0: 78.4% (#1). SWE-bench Pro standardized 43.30% (#3). Plan Mode added March 2026. First-pass correctness ~50-60% (Educative.io).
Public evidence
The only tool in the coding CLI category with a fully verifiable, independent download number. 5.7M lifetime installs and 15B tokens/week are public artifacts, not self-reported impressions. Strongest non-Anthropic usage signal in the category.
Aider scored 52.7% accuracy in 257s using 126K tokens — only 2.8 points below Claude Code's 55.5% while consuming 3x fewer tokens. Most cost-efficient agent tested.
Front-page HN thread signaling broad developer awareness. Strong technical discussion around model flexibility and git-native workflow.
v0.86.2 released 2026-02-12. Homepage displays live PyPI stats (191K+/week, 5.7M total, 15B tokens/week). Multi-model support: any OpenAI-compatible API, Anthropic, Google, local models via Ollama.
Raw GitHub source
Constrained peek so you can sanity-check the source material without leaving the site.
<a href="https://aider.chat/docs/llms.html"><img src="https://aider.chat/assets/icons/brain.svg" width="32" height="32" align="left" valign="middle" style="margin-right:10px"></a> Aider works best with Claude 3.7 Sonnet, DeepSeek R1 & Chat V3, OpenAI o1, o3-mini & GPT-4o, but can connect to almost any LLM, including local models.
<br><a href="https://aider.chat/docs/repomap.html"><img src="https://aider.chat/assets/icons/map-outline.svg" width="32" height="32" align="left" valign="middle" style="margin-right:10px"></a> Aider makes a map of your entire codebase, which helps it work well in larger projects.
<br><a href="https://aider.chat/docs/languages.html"><img src="https://aider.chat/assets/icons/code-tags.svg" width="32" height="32" align="left" valign="middle" style="margin-right:10px"></a> Aider works with most popular programming languages: python, javascript, rust, ruby, go, cpp, php, html, css, and dozens more.
<br><a href="https://aider.chat/docs/git.html"><img src="https://aider.chat/assets/icons/source-branch.svg" width="32" height="32" align="left" valign="middle" style="margin-right:10px"></a> Aider automatically commits changes with sensible commit messages. Use familiar git tools to easily diff, manage and undo AI changes.
<br><a href="https://aider.chat/docs/usage/watch.html"><img src="https://aider.chat/assets/icons/monitor.svg" width="32" height="32" align="left" valign="middle" style="margin-right:10px"></a> Use aider from within your favorite IDE or editor. Ask for changes by adding comments to your code and aider will get to work.
<br><a href="https://aider.chat/docs/usage/images-urls.html"><img src="https://aider.chat/assets/icons/image-multiple.svg" width="32" height="32" align="left" valign="middle" style="margin-right:10px"></a> Add images and web pages to the chat to provide visual context, screenshots, reference docs, etc.
<br><a href="https://aider.chat/docs/usage/voice.html"><img src="https://aider.chat/assets/icons/microphone.svg" width="32" height="32" align="left" valign="middle" style="margin-right:10px"></a> Speak with aider about your code! Request new features, test cases or bug fixes using your voice and let aider implement the changes.
<br><a href="https://aider.chat/docs/usage/lint-test.html"><img src="https://aider.chat/assets/icons/check-all.svg" width="32" height="32" align="left" valign="middle" style="margin-right:10px"></a> Automatically lint and test your code every time aider makes changes. Aider can fix problems detected by your linters and test suites.
<br><a href="https://aider.chat/docs/usage/copypaste.html"><img src="https://aider.chat/assets/icons/content-copy.svg" width="32" height="32" align="left" valign="middle" style="margin-right:10px"></a> Work with any LLM via its web chat interface. Aider streamlines copy/pasting code context and edits back and forth with a browser.
python -m pip install aider-install
aider-install
# Change directory into your codebase
cd /to/your/project
# DeepSeek
aider --model deepseek --api-key deepseek=<key>
# Claude 3.7 Sonnet
aider --model sonnet --api-key anthropic=<key>
# o3-mini
aider --model o3-mini --api-key openai=<key>
See the installation instructions and usage documentation for more details.