Aider
Also known as: aider.chat, aider-chat, Aider-AI
Open source, model agnostic terminal coding agent that edits your local git repo directly, with a tree-sitter repository map for whole project context and an architect mode pairing a reasoning model with a cheaper editor model.
Aider is an open source AI pair programming tool that runs entirely in your terminal and edits code directly in your local Git repository. Instead of replacing your editor, it works alongside your existing command line and Git workflow. You add the files you want to change and describe the change in plain English, and Aider writes the edits across one or more files and commits each change to Git with a descriptive commit message. Because every edit is a normal Git commit, you can diff, review, undo or revert anything the AI does using the Git tools you already use.
A defining feature is its repository map. It uses tree-sitter parsing to build an index of the whole codebase, ranked with PageRank and covering function signatures, class definitions and references across files, so the model understands how a large project fits together without loading every file into context. Aider is model agnostic.
Through LiteLLM it connects to almost any LLM, including Anthropic's Claude, OpenAI's GPT and o series, DeepSeek, Google Gemini, xAI Grok and local models run via Ollama, so you bring your own API key and switch providers based on cost or capability. Its Architect mode pairs an expensive reasoning model for planning with a cheaper model for the actual file edits to lower session cost.
Beyond core editing, Aider supports 100+ programming languages, can lint and test code automatically and fix the problems it finds, accepts images and web pages as context, and takes voice input. It works alongside editors such as VS Code, JetBrains, Vim and Emacs through its --watch mode and 'AI?' comments in the code. Created in 2023 by independent developer Paul Gauthier and released under the Apache 2.0 license, Aider has grown to 44,000+ GitHub stars and 6.8 million installs, and it maintains the widely cited Aider polyglot leaderboard for benchmarking how well LLMs edit code. It is free to use. The only cost is the token spend on whichever model provider you choose.
Vendor details
Canonical URL
https://aider.chat
Category
Coding agent
Subcategory
Coding — CLI agent (OSS)
Funding status
Independent open-source project; no external/VC funding disclosed.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Connects to 100+ LLMs through LiteLLM, including Claude, OpenAI GPT and o-series, DeepSeek, Gemini, xAI Grok, and local models via Ollama, with bring-your-own-API-key routing. Git-native (automatic commits, diff, undo). Editor-agnostic integration with VS Code, JetBrains, Vim, and Emacs via --watch mode and in-code 'AI?' comments. Installs via pip/pipx or Homebrew, supports 100+ programming languages, and can run your linters and test suites automatically.
In practice
You want AI editing your actual codebase, not pasting snippets from a chat window. Aider works in your terminal, edits files directly in your local Git repo, and commits each change with a descriptive message.
On a big codebase the AI loses track of how files connect. Aider builds a repository map with tree-sitter, so the model understands your project's structure without loading every file into context.
You don't want to be locked to one model's pricing. Aider is model-agnostic through LiteLLM, so you bring your own key and switch between Claude, GPT, Gemini, or a local model as cost dictates.
Sources & related URLs
Related / legacy domains
Research sources
Agentic Index coverage score
9.5 / 14 capabilities · 68%
| Integrations & Tool Calling | Partial |
|---|---|
|
The agent works through git, runs configurable lint and test commands, offers to run shell commands it suggests, scrapes web pages into the chat with /web, and takes image and voice input. There is no MCP client, plugin system or integration surface for external services. Sourceaider.chat/docs/config/options.html and usage/commands.html; aider.chat/docs/usage/commands.htmlread 2026-09-29 |
|
| Workflow Orchestration | Full |
|
Architect mode hands a change from an architect model, which proposes it, to a separate editor model, which turns it into file edits. After edits aider lints and optionally tests, then tries to fix the errors whenever a command returns a non zero exit code, a condition built into the flow. Sourceaider.chat/docs/usage/modes.html and usage/lint-test.htmlread 2026-09-29 |
|
| Knowledge Grounding & RAG | Full |
|
A repository map lists the repo's files with the key symbols each defines and their critical definition lines. A graph ranking over a file dependency graph selects the most relevant parts to fit a token budget set by --map-tokens. Read only reference files and scraped web pages can be added as further context. Sourceaider.chat/docs/repomap.htmlread 2026-09-29 |
|
| Human Oversight & Guardrails | Full |
|
Aider asks for confirmation before it runs a shell command it suggests, adds a file to the chat or fetches a URL. Bulk accept or reject covers a series of confirmations, and a --yes-always flag is off by default. In ask mode nothing is edited, and /undo reverts the last aider commit. Sourceaider.chat/HISTORY, docs/faq.html and config/options.html; aider.chat/history.htmlread 2026-09-29 |
|
| Security, Identity & Governance | Not documented |
|
As a local CLI, Aider has no hosted service, accounts or organization layer, so it offers and claims no SSO, role based access, audit logging or attestation. An .aiderignore file limits what enters the AI's context, and analytics can be switched off. Sourceaider.chat/docs/config/options.htmlread 2026-09-29 |
|
| Observability & Auditability | Full |
|
Every AI edit is committed to git with a generated message, so each change is a diffable record that /diff shows and /undo reverts. The session is written to a chat history file by default, with an option to log the full conversation with the LLM, and together these show what the agent changed and why. Sourceaider.chat/docs/usage.html and config/options.html; aider.chat/docs/config/options.htmlread 2026-09-29 |
|
| Memory & State Persistence | Partial |
|
The chat is written to .aider.chat.history.md, and --restore-chat-history reloads the prior conversation on launch so work can continue, which is state the agent writes and carries across sessions. There is no stated lifetime or purge path beyond clearing the chat. Git commits record the code's changes and do not serve as memory. Sourceaider.chat/docs/config/options.html and HISTORYread 2026-09-29 |
|
| Deployment & Data Residency | Full |
|
Aider is an Apache 2.0 CLI that runs on the developer's own machine and edits the local git repository. It works with local models through Ollama or any OpenAI compatible local server, so code and inference can stay on the customer's hardware. Sourceaider.chat/docs/llms.html and github.com/Aider-AI/aiderread 2026-09-29 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
An official Aider-AI conventions repository holds a community collection of ready made conventions files (Bash scripts, Flutter, functional programming, Go, Next.js with TypeScript and others), loaded with /read to steer the agent. These are guidance files, not prebuilt agents or task templates, and there is no further library. Sourceaider.chat/docs/usage/conventions.html and github.com/Aider-AI/conventionsread 2026-09-29 |
|
| Triggers & Channel Coverage | Partial |
|
Work starts from the person, through the interactive terminal chat, a one shot --message flag for scripts, and a watch mode that acts when the developer writes an AI! or AI? comment in any file. Nothing runs on a schedule, webhook or repository event. Sourceaider.chat/docs/usage/watch.html and scripting.htmlread 2026-09-29 |
|
| Model Flexibility & Routing | Full |
|
On the customer's own keys, Aider connects to OpenAI, Anthropic, Gemini, Groq, xAI, Azure, Cohere, DeepSeek, OpenRouter, GitHub Copilot, Vertex AI, Amazon Bedrock and any OpenAI compatible API, plus local models through Ollama and LM Studio. Main, editor and weak models are set separately, and /model switches mid session. Sourceaider.chat/docs/llms.html and config/options.htmlread 2026-09-29 |
|
| APIs, SDKs & MCP Extensibility | Partial |
|
Scripting works from the command line with --message and from Python through the Coder class. The Python API is not officially supported or documented and may change without notice, and there is no HTTP API, SDK or MCP server. Sourceaider.chat/docs/scripting.htmlread 2026-09-29 |
|
| Testing, Debugging & Optimization | Full |
|
The repository ships a benchmark harness with setup and run instructions. It measures how well aider and a chosen model turn coding requests into code that passes unit tests, with custom models and edit formats and a YAML report of pass rates, cost and timing. The project publishes its polyglot leaderboard of 225 exercises in six languages from it. Sourcegithub.com/Aider-AI/aider/benchmark and aider.chat/docs/leaderboards; github.com/aider-ai/aider/blob/main/benchmark/readme.mdread 2026-09-29 |
|
| Browser & Computer Use | Not documented |
|
Aider edits files, runs shell commands and scrapes web pages into markdown with /web, but it does not drive a browser or operate software through a graphical interface. Sourceaider.chat/docs/usage/commands.htmlread 2026-09-29 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Pricing
Free. Open source under Apache 2.0, with no paid tier.
Aider bills nothing. The only spend is model API token usage, paid directly to the chosen model provider.
What is public
Aider is 100% free and open source (a terminal CLI tool) with no subscription, paid tiers, or premium features. You bring your own LLM API key (Anthropic, OpenAI, OpenRouter, Google, xAI, DeepSeek, or local models via Ollama). The only cost is whatever your model provider charges per token.
Billing mechanics
There is no Aider billing, and the tool is free. All cost is model API token spend passed straight through to whatever provider and model the user routes to. Aider is model agnostic with explicit per request model routing, so cost comes down by choosing cheaper models (for example DeepSeek) or running local models for $0 inference.
Cost watchouts
The model API bill is the real cost. Frontier models (Opus, GPT-5) cost far more than budget models, and a commit for every edit plus codebase mapping add token overhead.
Variable cost rationale
Aider itself costs nothing, so the only metered cost is the model provider's token charges, passed straight through. That bill grows with how much code each session sends and edits and with the model chosen, and codebase mapping plus a git commit for every edit add tokens to each session. Aider sets no cap, so heavy use runs up the API bill with no limit from the tool. The levers are the model choice, since budget models such as DeepSeek cost far less than frontier models, and local models through Ollama, which run at $0 inference cost.
Additional watchouts
There is no managed offering, SLA or markup. The user owns all API cost management and setup, and Aider's model guidance lags the newest frontier models.
Sales call required
No, self serve available
Free / trial
Free and open source, self hosted
Lowest paid plan
No paid plan
Commercial notes
Apache 2.0 open source that runs locally in the repository with no vendor account and commits each edit to git. Releases have slowed, and the latest stable version is v0.86.2.
Key ambiguities
Actual cost depends entirely on the model and provider chosen and on usage volume. Aider sets no price.
Cancellation / refund
No contract or subscription, so there is nothing to cancel. Model API billing runs directly with the chosen model provider.
Support SLA / resale
Community support on GitHub. No vendor SLA or enterprise tier.
Missing data
There is no vendor pricing to publish, and the only cost is token spend with the user's own model provider.
Related vendors
- Cognition — Maker of Devin, an autonomous AI software engineer
- 10Web — Agentic website platform whose AI agents build, host and manage…
- AgentUI — Managed AI app builder for operations teams that generates and hosts…
- Amp — Amp is a coding agent from Amp Frontier Corporation that runs each…
- Anthropic Claude Code — Anthropic's agentic coding system across terminal, desktop, IDE, web…
- Anything — Anything is an AI app builder whose agent turns a plain language…
Alternatives to Aider
The closest documented capability profiles to Aider among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- ThinkReview8.5 / 14Fuller documented coverage on APIs, SDKs & MCP Extensibility
- CodeGPT10.0 / 14Adds documented Security, Identity & Governance
- Blitzy8.5 / 14Adds documented Security, Identity & Governance
- Embedder11.5 / 14Adds documented Security, Identity & Governance
- Emergent10.5 / 14Adds documented Security, Identity & Governance and Browser & Computer Use
- Figma Make11.5 / 14Adds documented Security, Identity & Governance and Browser & Computer Use
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded