Amp

byAmplisted Nov 16, 2026

Coding AgentsFreemiumEasy setupMulti-model, incl. Claude Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, GLM-5.3-Flash

Coding agent from Amp, a company spun out of Sourcegraph in December 2025. It runs as a CLI, on the web, and in desktop and mobile apps. Agents can work locally or in 'orbs', cloud sandboxes that keep running unattended, and users choose between frontier models from several providers.

Freshness note: AI-agent behavior can change after model releases, client updates, pricing changes, or new default settings. Use the aggregate score as a historical baseline and check recent reviews plus model/runtime context before deciding.

Pricing
Hobby: free. Use your own ChatGPT/Claude subscription or API keys with no Amp token fees, or buy Amp credits. Amp-hosted orbs (cloud sandboxes) are pay-as-you-go; self-hosted orbs are free. Megawatt: $20/month with 750 hours of small orbs and included Amp credits ($10/month for students and teachers). Higher tiers and Enterprise pricing are custom.
Model backbone
Multi-model, incl. Claude Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, GLM-5.3-Flash
Setup complexity
Easy setup
Last reviewed
Awaiting reviews
Recent signal
Awaiting reviews
Evidence sources: No published editorial evaluation is available yet. Editorial evaluations are Ruling research, not community testimonials, and do not contribute to the community score.

Build Amp? Get a claim link →

What reviewers consistently say.

No reviewer patterns for Amp yet.

No consensus yet

Once people review Amp, Ruling will summarize recurring strengths and limitations here.

Write the first review

No community reviews yet.

Used Amp? Your field report can seed the first Ruling signal.

Be the first to review Amp

Share where it worked, where it failed, and whether it deserves a spot in a real team workflow.

Write a review
Write a review