Amp
AI coding agent from Sourcegraph for the terminal and editors.
HN commenters like Amp for solid results and fast turnaround on quick changes,123 along with context handoff, shareable threads and its UI.456 The main caveat raised is cost, with one fan calling it a bit expensive.7
Why people recommend it
Result quality · 3
Commenters say it delivers better results than many other agents.
“Amp for a little bit that I used it, is really solid agent and delivered much better results than many others.”
“I love AMP, it delivers great results.”
Show 1 more
“Amp is an amazing product that I love recommending for so many reasons.”
Handoff and threads · 2
Context handoff and thread sharing are singled out as strong features.
“Amp is an amazing product that I love recommending for so many reasons.”
“I love AMP, it delivers great results.”
Speed · 1
One user finds it finishes quick changes while Codex is still building context.
“Almost every time I need a quick change, Amp finishes the task in the time it takes Codex to build context.”
Curated models · 1
A user likes not being tied to one model, with model choice evaluated for them.
“I love AMP, it delivers great results.”
UI/UX · 1
A developer building their own harness praises its UI and UX.
“I loved Amp Codes UI/UX and was incredibly inspired by iy”
Value · 1
One subscriber says the agent alone is worth $20 a month.
Caveats and dissent
Price · 1
A recommender warns that it may be a bit expensive.
“AmpCode is not popular here but I recommend it”
Flash for search · 1
One fan notes it reportedly only uses Flash for search.
Sandboxing advised · 1
A commenter recommends running agents like Amp in a sandbox, away from $HOME and SSH keys.
“Sandboxes are a good measure for things like Claude Code or Amp.”
Often compared with
Threads where it came up
- Show HN: Bough, the agent I built to replace Claude Code at work 1 mention
- Orbs 1 mention
- Our decision on Cursor following its acquisition by SpaceX 1 mention
- "That's not SoC 2 compliant" 1 mention
- Claude Sonnet 5 1 mention
- Semgrep: GLM 5.2 beats Claude in our Cyber Benchmarks 1 mention
Also written as Amp Code. Data: amp.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 12
“I loved Amp Codes UI/UX and was incredibly inspired by iy”
“the Amp coding agent in itself is worth that much”
“AmpCode is not popular here but I recommend it”
“No disrespect, I love what they do.”
“You might want to check out Amp: https://ampcode.com/”
“Big fan of Amp”
“Yes I use Claude, Coded, Amp and Cursor agents every day”
“Sandboxes are a good measure for things like Claude Code or Amp.”
“Amp is an amazing product that I love recommending for so many reasons.”
“Almost every time I need a quick change, Amp finishes the task in the time it takes Codex to build context.”
“Amp for a little bit that I used it, is really solid agent and delivered much better results than many others.”
“I love AMP, it delivers great results.”