Aider: AI agent (CLI agent) in 2026
Terminal pair programmer that maps your repo and commits each change to git.
Sourced facts checked 2026-10-17 Rank 13 of 16 in CLI agent. Source: Official site or docs, checked 2026-10-17.
Key facts
| Type | AI agent |
|---|---|
| Category | CLI agent |
| Maker | Aider-AI (Paul Gauthier) |
| Interface | CLI |
| Licence | Apache-2.0 (Open source) |
| GitHub stars | 49,593 (as of 2026-10-17) |
| Supported models | Any LLM incl. local |
| Headless mode | Yes |
| Pricing (official) | No paid plan listed; bring your own LLM API key. (checked 2026-10-16) |
| Website | https://aider.chat/ |
| Repository | https://github.com/Aider-AI/aider |
| Source | https://aider.chat/ (checked 2026-10-17) |
| Vibe Shipped harness page | https://vibeshipped.io/harness/aider |
| Vibe Shipped toolbox page | https://vibeshipped.io/agent-toolbox/aider |
Install
Install
This is an agent you run, not an MCP server. Install and setup: https://aider.chat/
Source: https://aider.chat/ (checked 2026-10-17).
Is this your ai agent? Claim this listing to correct facts, add a contact, or tell us you want the upcoming verified badge, downtime alerts and agent-demand analytics. Claiming never changes where it ranks.
Other cli agent ai agents
- Grok Build Sourced facts checked 2026-10-17 · #1 in CLI agent
xAI's terminal coding agent (the grok CLI): a full-screen TUI that also runs headless and over the Agent Client Protocol. - Claude Code Sourced facts checked 2026-10-17 · #2 in CLI agent
Anthropic's agent for the terminal, IDE and desktop that reads, edits and runs code in your repo. - Gemini CLI Sourced facts checked 2026-10-17 · #3 in CLI agent
Google's open-source terminal agent built around Gemini models. - Hermes Agent Sourced facts checked 2026-10-17 · #4 in CLI agent
Nous Research's self-improving terminal agent for coding and other tasks, with persistent memory, agent-made skills and a messaging gateway. - Kilo Code Sourced facts checked 2026-10-17 · #5 in CLI agent
Open-source coding agent for VS Code, JetBrains and CLI with a gateway to 500+ models.
Within a category, entries sort by (1) latest verification: verified working, then reachable but sign-in required, then failing; (2) share of daily checks that passed; (3) number of sourced facts attached to the entry; (4) median response time of passing checks; (5) name. Nothing else counts. Rankings are never for sale: sponsors and paid plans cannot change an entry's position. Markdown · JSON