Amp
Sourcegraph's agentic coding tool, a frontier agent across the terminal, editors and Slack.
- Starting price
- Megawatt $20 / month
- Commercial use
- Yes
- Output
- Autonomous, multi-step coding across the terminal, editors and Slack
Overview
Amp is an agentic coding tool from Sourcegraph that runs autonomously across a repository: it reads code, runs tests and shell commands, and edits files to carry out tasks like fixing failing tests or clearing type errors. It works from a CLI, inside VS Code and compatible editors, Neovim and Zed, from the web to steer CLI threads remotely, and as a Slack bot for teams. Rather than fixing one model, Amp routes between frontier and fast models for what each is best at, offers modes from low through high and ultra, and can draw on a linked ChatGPT subscription for extended high-mode usage.
Best for developers and teams who want an agent-first coding workflow across the terminal, their editor and Slack.
Amp suits developers who are ready to work through an agent rather than alongside one, and Sourcegraph has committed to that reading of where coding is going hard enough to drop the alternative. Anyone who wants autocomplete first and an agent second is looking at the wrong tool. Billing follows consumed model usage rather than seats, which cuts both ways: an occasional user pays less than a flat seat price, a team that delegates heavily pays more and cannot forecast it from headcount. The spread across terminal, editor, web and Slack earns its keep where several people follow the same agent run; a solo developer who lives in one IDE gets less out of it.
Key Facts
| Category | |
|---|---|
| Starting price | Megawatt $20 / month Includes $20 of agent usage and 750 hours of orbs. Gigawatt $200 per month. Students and teachers $10 per month. Unconstrained is pay-as-you-go at API pricing, with the option to bring your own inference keys. |
| Commercial use | Yes |
| Output | Autonomous, multi-step coding across the terminal, editors and Slack |
| API | N/A |
Screenshots
Placeholders. They are replaced as soon as the vendor sends material, and both open the same short form.
Features
- Where it runs
- CLI, VS Code and compatible editors (including Cursor and Windsurf), Neovim, Zed, the web and Slack
- Inline completions
- No, the Amp Tab completion engine was retired at the end of January 2026; Sourcegraph points to Cursor, Copilot or Zed for inline completions
- Agent mode
- Yes, an autonomous agent that reads code, runs tests and commands and edits files across multi-step tasks
- Model choice
- Yes, Amp routes between frontier and fast models per task; an optional linked ChatGPT subscription extends high-mode usage
- Data control
- Enterprise adds SSO, directory sync and admin controls
- Ecosystem fit
- Sourcegraph; integrates with existing editors and Slack rather than replacing them
- API
- N/A
Integrations
- Visual Studio Code
- Cursor
- Windsurf
- Neovim
- Zed
- Slack
Deployment and Support
- Deployment
-
- Cloud (SaaS)
- Browser-based
- Support
-
- Email helpdesk
- Community forum
- Onboarding
-
- Documentation and knowledge base
- Company size
-
- Freelancers
- Small and mid-sized
- Enterprise
Suitability
| Industry | Freelancers | Small and mid-sized | Enterprise |
|---|---|---|---|
| Agencies | Not stated | Not stated | Not stated |
| Architecture & Engineering | Not stated | Not stated | Not stated |
| Consulting | Not stated | Not stated | Not stated |
| Media & Creative | Not stated | Not stated | Not stated |
| Technology | Stated as a fit | Stated as a fit | Stated as a fit |
The table combines the industries the vendor addresses with the company sizes the tool is aimed at. An empty cell means the combination is not stated, not that it is ruled out.
Pros and Cons
Strengths
- Agent-first workflow that spans the terminal, multiple editors, the web and Slack
- Routes between frontier and fast models instead of locking to one
- Thread sharing makes agent work collaborative across a team
Limitations
- Usage-based pricing can be harder to predict than a flat seat price
- Built around an autonomous agent rather than inline autocomplete
Pricing
-
Megawatt
$20
Per month. $20 included agent usage and 750 hours of orbs; low and medium modes, plus high mode with a linked ChatGPT subscription.
-
Gigawatt
$200
Per month. $200 included agent usage; all modes, including high and ultra.
-
Students and teachers
$10
Per month, discounted rate.
-
Unconstrained
Usage-based
Pay-as-you-go at API pricing for model tokens and orbs, with the option to bring your own inference keys. For teams and enterprises.
Best For
Alternatives and Comparisons
What users say
Reviews
-
0 reviews
- Ease of use
- Not rated yet
- User interface
- Not rated yet
- Onboarding
- Not rated yet
- Support and service
- Not rated yet
- Value for money
- Not rated yet
- Features
- Not rated yet
No reviews yet. Be the first to review this tool. Every review is checked for fairness before it appears, and the vendor cannot have one removed.
Share your experience
Write a Review
Ready to take a closer look at Amp
The link goes straight to the vendor. Some links on this site are affiliate links.
Visit Amp