Amp

Amp — Sourcegraph's opinionated agent with no model picker and an ad-supported free tier. Amp's defining choice is the absence of a choice: there is no model selector, because Sourcegraph would rather move everyone to whatever is currently best than support a matrix. It runs as a CLI and a VS Code extension with shared, linkable threads, and escalates hard problems to a stronger reasoning subagent. An ad-supported free tier launched in late 2025 alongside pay-as-you-go credits — a genuinely novel, and genuinely divisive, pricing experiment. Built by Sourcegraph. Licensed Proprietary.

We track it in 1 comparison — Coding agents — so every claim below is a cell in a table you can open and check rather than an impression. Across those rosters it sits against 16 other tools, and what follows is where it visibly separates from them.

Where it wins.

• Subagents — Yes, which only 5 of 14 tools here manage.
• Token markup — Yes, which only 3 of 16 tools here manage.

Each of those is ranked against the whole roster on its category page, not against a hand-picked subset, so a first place here means first of everything we list.

Where it gives ground.

• BYOK — No. Claude Code records Yes.
• Pricing model — opaque credits, 14th of 16. opencode records BYOK tokens only.
• Model breadth — no model choice, 15th of 16. opencode records any provider / router.
• Local models — No. Codex CLI records Yes.

None of these disqualify it on their own. They are the fields to check against your own requirements before you commit, because they are the ones where a competitor genuinely does better.

Provenance. 22 of 26 tracked fields carry a value for Amp, and 4 of those cite a document you can open. Last verified 2026-01-15. Every figure keeps its own provenance — measured by us, claimed by the vendor, inferred, or community-reported — and we would rather print a dash than a guess.

Its nearest neighbour in our data is Aider. Amp is ahead on MCP (Yes against No) and Subagents (Yes against No). Aider takes BYOK (Yes against No) and Model breadth (any provider / router against no model choice). That pattern repeats across the rest of the roster — see Amp alternatives for the other rivals, each compared the same way.

Company

Sourcegraph

Licence

Proprietary

Fields we track

22 of 26

Last verified

2026-01-15

Removing the model picker is a defensible product decision — most people choose badly and then blame the harness — but it means you control neither cost nor provider, and an ad-supported tier is an odd thing to sit next to a proprietary codebase. Subagent quality is genuinely good.

BYOK

○No15th of 16

Inferredverified 2026-01-15

Subagents

●Yes1st of 14

Inferredverified 2026-01-15

Pricing model

opaque credits14th of 16

Vendor-claimedsource

Model breadth

no model choice15th of 16

Inferredverified 2026-01-15

Token markup

●Yes1st of 16

Inferred

Local models

○No11th of 16

Inferredverified 2026-01-15

Opens PRs

○No10th of 16

Inferred

Headless / CI

●Yes1st of 16

Community-reported

Amp is the right call in these situations, each one drawn from a field we actually record:

• Teams who would rather not run a model-selection debate every quarter.
• Sourcegraph shops wanting shared, linkable agent threads.
• Subagents is your binding constraint. Amp records Yes, which only 5 of the 14 tools in the Coding agents roster do. We define that field as can the agent spawn child agents with their own context window and toolset, and collect their results? The main lever for keeping long tasks inside a context budget.
• Token markup is your binding constraint. Amp records Yes, which only 3 of the 16 tools in the Coding agents roster do.

Reach for something else when any of the following is a requirement rather than a nice-to-have:

• BYOK. Amp records No on the Coding agents table. Claude Code records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Pricing model. Amp records opaque credits, 14th of 16 in the Coding agents roster. opencode records BYOK tokens only on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Model breadth. Amp records no model choice, 15th of 16 in the Coding agents roster. opencode records any provider / router on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Local models. Amp records No on the Coding agents table. Codex CLI records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Opens PRs. Amp records No on the Coding agents table. Claude Code records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.

We publish this block because a comparison that only lists what a tool is good at is marketing. Every figure above sits on the same page as its source, and the field definitions are on the category tables if you want to check how we measured them.

What we don't know. 4 of the 26 fields we track for Amp are still blank: Hooks, GitHub stars, Terminal-Bench and Bench model. Those render as dashes rather than as zeroes or assumptions, because an empty cell and a bad cell are not the same thing and only one of them is honest. If you know any of these figures and can point at a document, tell us.