On this page
- Project status (checked 2026-09-29)
- Aider vs Cline, Cursor, and Copilot
- The Aider Polyglot Benchmark
- Five Features Worth Your Terminal Time
- Install Aider
- Connecting Aider to Free LLM APIs
- Cost Reality: 60 Hours a Month
- Production Tips: Don't Burn Tokens
- Frequently Asked Questions
- When to Use Aider vs Cline vs Cursor
Project status (checked 2026-09-29)
We check the health of every open-source tool we recommend. These numbers come from the public GitHub API (repository, latest-commit and latest-release endpoints), pulled on 2026-09-29, next to two actively developed free alternatives:
| Aider | OpenCode | Cline | |
|---|---|---|---|
| Last commit | 2026-05-22 (130 days) | 2026-09-28 | 2026-09-29 |
| Latest release | v0.86.0, 2025-08-09 (416 days) | v1.18.33, 2026-09-28 | 2026-09-29 |
| Open issues + PRs | 1,903 | 6,238 | 1,484 |
| Stars | 49k | 210k | 69k |
| License | Apache 2.0 | MIT | Apache 2.0 |
| Where it runs | Terminal | Terminal | VS Code extension |
| Archived? | No | No | No |
The open-issue figure is GitHub's own count, which includes open pull requests. Popular projects collect a lot of them either way, so the dates are the more useful signal.
What this means for you. Nothing has been switched off: Aider is a local Python program under Apache 2.0, it still installs from PyPI, and it talks to whatever API you give it. What has stopped is maintenance. The last merged change was an expansion of Aider's list of Anthropic model names, and anything a provider has released or retired since the last tagged release is not reflected in the version you install. In practice:
- Name your model explicitly with
--modelinstead of relying on defaults. Aider may warn that it doesn't know a newer model's context size or price; that warning is about its bundled metadata, not the provider. - Provider-side changes won't be patched. Example: in our own test on 2026-09-29, a new Gemini API key got "no longer available to new users" for the Gemini 2.5 models, which older Aider guides (including an earlier version of this page) used as the free default. The model examples below have been updated.
- Bugs are yours to work around. Issues keep being filed, and no new release has shipped to fix them.
Actively maintained free alternatives. Both are open source and bring-your-own-key, and both had commits and releases within two days of our check:
- OpenCode (MIT) — the closest match if you picked Aider because it lives in the terminal. Its provider docs list 75+ LLM providers and show how to point it at local runners such as Ollama. It is an agent with separate build and read-only plan modes rather than Aider's propose-edit-commit loop, so expect a different workflow.
- Cline (Apache 2.0) — if you're happy to work inside VS Code. See our Cline review for which free models actually finish tasks in it, or the wider list of free AI coding assistants.
We checked Continue too; its last commit was 2026-07-21, so we left it off the "actively maintained" list for now. If Aider development resumes, we'll update this page. Verify the numbers yourself:
curl -s https://api.github.com/repos/Aider-AI/aider | grep -E '"pushed_at"|"open_issues_count"|"archived"'
curl -s https://api.github.com/repos/Aider-AI/aider/releases/latest | grep -E '"tag_name"|"published_at"'
Aider launches inside a Git repo and turns every code change into a conversation. Unlike editor-based agents like Cline, Cursor, and Windsurf, it keeps everything text — so it fits tmux, SSH, and vim/emacs workflows with no extension or IDE lock-in. Created in 2023 by Paul Gauthier (tens of thousands of GitHub stars), it's also one of the few tools that published a real, reproducible benchmark.
Aider vs Cline, Cursor, and Copilot
These tools share the same backbone — an LLM that reads files and proposes edits — but differ in where they live, how they edit, and how they treat Git.
| Feature | Aider | Cline | Cursor | Copilot |
|---|---|---|---|---|
| Price | Free (BYOK) | Free (BYOK) | $20/mo Pro | $10/mo |
| Surface | Terminal CLI | VS Code ext | Forked VS Code | Editor plugin |
| Open source | Yes (Apache 2.0) | Yes (Apache 2.0) | No | No |
| Choose model | Any (LiteLLM, 100+) | 15+ providers | Cursor-managed | Mostly OpenAI |
| Free model option | Yes (any free API/Ollama) | Yes | Limited | No |
| Git auto-commit | Yes (semantic msg) | Optional | No | No |
| Repo context map | Yes (tree-sitter) | Workspace search | Codebase index | Workspace search |
| Architect/Editor split | Yes | Plan/Act (one model) | Partial | No |
Bottom line: if you live in an editor, Cline or Cursor fit naturally. If you live in a terminal — SSH into remote boxes, work in tmux, pair with vim/emacs, or run on a GUI-less server — Aider is the only tool in this table built for that from day one (OpenCode, covered above, is the maintained terminal option).
The Aider Polyglot Benchmark
Instead of marketing copy, Aider publishes a benchmark. The Aider Polyglot leaderboard tests every major model against 225 hand-curated exercises across C++, Go, Java, JavaScript, Python, and Rust. Each has hidden unit tests; a model passes only when its edits make tests go green, with at most one self-correction round.
It tests the full pipeline — reading the problem, locating files, producing a valid edit, getting the diff format right, and writing code that passes. It's multi-language (a model strong in Python but weak in Rust won't top it). With the project quiet since May 2026, check whether a recently released model has been tested before relying on the table. The practical use is choosing a model: sort by the latest column and check its current API cost. For a free API tier, consider Gemini Flash on Google AI Studio or open models on Groq.
Five Features Worth Your Terminal Time
1. The Repo-Map
Instead of dumping every file into the prompt, Aider uses tree-sitter to parse each source file and extract a structured summary (class names, function signatures, exported types), then ranks symbols by relevance using a PageRank-style graph. The result is a compact map — a few hundred lines for most projects. See it with /map, cap it with --map-tokens, and scope large monorepos with .aiderignore (same syntax as .gitignore).
2. Multiple Edit Formats
Most agents use one edit format; Aider supports four, because models differ at each: whole (full file — highest token cost, lowest failure), diff (SEARCH/REPLACE blocks), udiff (unified-diff hunks — compact), and diff-fenced. Aider auto-picks per model from benchmark history; override with --edit-format if edits keep failing to apply.
3. Architect Mode
Frontier reasoning models plan well but produce messy edits; cheap fast models are the reverse. Architect mode assigns a model to each role:
aider --architect \
--model openrouter/z-ai/glm-5.2 \
--editor-model openrouter/anthropic/claude-sonnet-5.5
The architect produces a plan; the editor emits the actual SEARCH/REPLACE blocks. This two-stage approach consistently beats single-model runs on the polyglot benchmark, often by ten-plus points on harder languages.
4. Auto-Commit With Real Messages
Aider commits after every accepted change with a one-line message from the diff. This sounds cosmetic until your first git bisect on AI-generated code — granular commits turn a debugging nightmare into a five-minute regression hunt. Pass --no-auto-commits to stage changes instead, or let Aider git init for you on first run.
5. /web: Drop a URL Into the Chat
Type /web https://docs.example.com/api and Aider scrapes the page, converts it to clean Markdown, and adds it as context — giving the LLM the actual current API reference instead of stale training knowledge, without a separate RAG pipeline.
Install Aider
Aider is a Python package. The official installer handles version and dependency isolation via uv:
python -m pip install aider-install
aider-install
Prefer your own venv? pipx install aider-chat (or pip install aider-chat). Then set a key for your provider — Aider reads env vars and a project .env:
export OPENROUTER_API_KEY=sk-or-v1-...
# or GEMINI_API_KEY / DEEPSEEK_API_KEY
That's it. cd into a Git repo, run aider, start typing.
Connecting Aider to Free LLM APIs
Aider speaks LiteLLM, so it supports nearly every provider with one --model flag. Four zero-cost setups for 2026:
- Gemini free tier — the Gemini Flash models, no card on file:
aider --model gemini/gemini-3.5-flash-lite. In our 2026-09-29 test with a new free key,gemini-3.5-flash-liteanswered, the Gemini 2.5 models returned "no longer available to new users", and the Pro models hit the free-tier quota on the first call. Google doesn't publish the free-tier limits, and we have not re-tested these IDs inside Aider itself — expect an "unknown model" warning from Aider v0.86.0. - OpenRouter free models — OpenRouter exposes
:freemodels behind one endpoint:aider --model openrouter/cohere/north-mini-code:free(answered on 2026-09-29; the:freelist changes often, so check it, or use theopenrouter/openrouter/freerouter). Tighter limits, wide variety, good fallback. - Ollama (fully local) — Ollama runs on your own GPU:
aider --model ollama_chat/qwen2.5-coder:14b. Quality drops below frontier, but no tokens leave your machine — useful for NDA code. - DeepSeek direct — near-frontier quality with off-peak discounts, but no free credit for new accounts since 2026-08-31 (calls return 402 until you top up):
aider --model deepseek/deepseek-v4-flash(thinking effort is switchable on V4).
Mix free tiers with architect mode — Gemini for the plan, OpenRouter's free router for the edit, total cost zero:
aider --architect \
--model gemini/gemini-3.5-flash-lite \
--editor-model openrouter/openrouter/free
Cost Reality: 60 Hours a Month
| Setup | Monthly Cost | Quality |
|---|---|---|
| Aider + Gemini Flash free tier | $0 | Good; free-tier limits unpublished |
| Aider + OpenRouter free models | $0 | Strong open-source |
| Aider + Ollama Qwen2.5-Coder 14B | $0 | Mid, fully offline, needs GPU |
| Aider + DeepSeek V4 Flash (paid) | ~$2–8 | Cheapest paid frontier ($0.14/$0.28 per M tokens) |
| Aider + Claude Sonnet (paid) | ~$10–40 | Top of leaderboard most months |
| Cursor Pro | $20 | Mixed, fewer choices |
| GitHub Copilot Individual | $10 | Mid, no autonomous mode |
The first three rows are the point: a serious engineering workflow at $0/month is just a matter of pairing a free tool with a free API.
Production Tips: Don't Burn Tokens
/dropaggressively — files stay in context until removed; drop them once Aider has edited them.- Add
.aiderignorefor noise (node_modules, generated code, large fixtures). The repo-map respects it. - Cap the map —
--map-tokens 1024is plenty for most repos. /clearbetween unrelated tasks to flush chat history — can halve token cost.- Auto-test only at task boundaries —
--auto-testafter every edit adds up on large suites; run/run pytestmanually instead.
Frequently Asked Questions
Is Aider really free?
The tool itself is free and open-source under Apache 2.0. Model calls go through whichever provider you point it at, and you can run it for $0/month with free providers (Gemini, OpenRouter free tier, Ollama). You only pay, optionally, to upgrade to a paid model when free-tier limits slow you down.
Does Aider work without Git?
Technically yes, with --no-git, but you lose auto-commit, the diff-aware repo-map, and easy rollback. On a fresh project Aider offers to git init for you — one keypress. Just let it.
Is Aider an autonomous agent like Cline's Act mode?
No, by design. Aider treats you as the loop: it proposes edits, you approve, it commits, you run tests, you describe the next step. For codebases where every line matters, that's a feature. If you want fully autonomous "fix this issue" workflows, pair it with Cline.
Does Aider support MCP?
Not in its released versions. Aider's tools are file editing, /run, and /web, and with no release since v0.86.0 (August 2025) you shouldn't plan around MCP support arriving. Much of what MCP servers provide can be done via /run and shell pipes; if you need MCP itself, OpenCode and Cline both support it.
When to Use Aider vs Cline vs Cursor
- You live in vim/emacs/a terminal multiplexer or SSH into remote boxes: Aider, or OpenCode if you want a terminal tool that is still receiving updates.
- You want autonomous, multi-step "go fix this issue" with browser verification: Cline.
- You want a managed product with one bill and polished UI: Cursor — less friction, less cost transparency and model choice.
- You want Git-aware, surgical edits with a full audit trail: Aider.
Many serious developers in 2026 use both — Aider for terminal-native pairing, Cline or Cursor for autonomous IDE work. They fit different parts of the day. If you've never tried a terminal-native AI pair programmer, give Aider an afternoon on a small side project; there's no lock-in and no sunk cost.