Terminal agent · active
Aider
An open-source terminal pair programmer with repository maps, Git integration, and automated lint-and-test loops.
Visit Aider ↗Verified ·Jul 31, 2026
- Best for
- Developers who prefer a focused terminal workflow, direct model-provider control, and automatic Git checkpoints.
- Avoid if
- You want hosted background agents, visual task orchestration, or native inline autocomplete.
01 / Editorial view
Where it fits
Strengths
- Strong Git-native workflow
- Repository maps for large codebases
- Built-in lint and test feedback loops
Limitations
- Terminal-first interface
- Model setup, cost, and privacy remain provider-dependent
02 / Workflow
Surfaces and capabilities
- Autocomplete
- No
- Chat
- Yes
- Agent
- Yes
- Background agent
- No
- Review
- No
- Testing
- Yes
Editors
Any editor through watch mode
Operating systems
macOS, Windows, Linux
Repository hosts
GitHub
Languages
100+ programming languages
Bring your own key
Yes
Bring your own model
Yes
03 / Cost and deployment
What it costs to run
Individual
Free software; model API or local compute costs are separate.
Team
No separate team plan is documented.
Enterprise
Unknown
Cloud-model usage is billed by the selected provider.
04 / Privacy
Data handling
- Code processing
- Aider runs locally and sends selected code context to the configured model provider.
- Indexing
- A repository map is built locally to select relevant code context.
- Retention
- Optional analytics do not collect code, chat content, API keys, or personal information.
- Training policy
- Model-provider policies apply to prompts sent through the selected provider.
- Enterprise controls
- Analytics opt-out, Local model support
05 / Evidence
Primary sources
- Aider repository ↗Checked Jul 31, 2026classification, compatibility, capabilities, deployment
- Aider model and key documentation ↗Checked Jul 31, 2026models, pricing
- Aider analytics documentation ↗Checked Jul 31, 2026privacy
- Aider lint and test documentation ↗Checked Jul 31, 2026capabilities.testing
Next