Can I run Bernstein and Amp in the same git repo?

Yes. Bernstein spawns each agent in its own git worktree under .worktrees/, so file edits never collide. Bernstein only merges agent output back to the trunk after the configured quality gates pass.

Is the comparison page on bernstein.run handwritten or generated?

Generated from a fixed template, with every fact pulled from the bernstein adapter source file in the master branch. No LLM is used to write the prose. The data extractor lives at scripts/gen-compare-data.mjs.

Compare

Bernstein vs Amp: quick decision guide

Q: Does Bernstein replace Amp?

No. Bernstein wraps Amp as one of 42 CLI adapters and decides per task which agent runs the work. Amp keeps doing what it does best; Bernstein chooses when it gets routed work.

Amp CLI adapter.

Page built on 2026-05-18 from data/adapters-meta.json. Every claim below links to its primary source.

Install both

Amp

brew install amp

Bernstein

pipx install bernstein

Apache-2.0. Deterministic Python scheduler.

Feature matrix

Capability	Amp	Bernstein
Install method	brew install amp	pipx install bernstein
License	Not recorded	Apache-2.0
Authentication	Not recorded	Per-agent credential scoping (no shared key)
Multi-agent orchestration	One agent in a terminal	Amp plus 41 other adapters in parallel worktrees
MCP support	Not measured	Yes
Parallel-safe in worktrees	Not measured	Yes (designed around git worktrees)
HMAC-chained audit log	No	Yes (RFC 2104 SHA-256 chain in .sdd/)
Deterministic scheduler	Not applicable (single-agent CLI)	Yes (Deterministic Python scheduler)

Adapter source: src/bernstein/adapters/amp.py | Upstream homepage: ampcode.com

Verifiable facts

The brief for this surface requires at least three facts that a reader can verify against a primary source. The list below is built from the bernstein adapter source and, when available, the upstream project's own pages.

Bernstein ships a Amp adapter at src/bernstein/adapters/amp.py that wraps the upstream CLI as one of 42 routable agents. [source: bernstein adapter source, as of 2026-05-18]
Upstream install command, as recorded in the bernstein adapter, is "brew install amp". [source: upstream docs, as of 2026-05-18]
Bernstein last verified its adapter against upstream Amp on 2026-05-05. [source: bernstein adapter source, as of 2026-05-05]

Where Amp fits in Bernstein

Bernstein registers Amp under the slug "amp" and the registry name "amp". The adapter source lives at src/bernstein/adapters/amp.py in the bernstein repo and was last touched at build time 2026-05-18. The Amp adapter file is 107 lines and 3,842 bytes long, fingerprinted 21ee85b5ae2045db (first 16 hex chars of SHA-256). Operators install Amp on a worker box with "brew install amp" before Bernstein routes any task to it. No upstream GitHub repository is recorded in the bernstein adapter for Amp; refer to the upstream vendor's documentation when auditing. The Amp project's homepage at ampcode.com is the primary source for upstream release notes. Bernstein last verified the Amp adapter against upstream Amp on 2026-05-05, recorded inline in the adapter source. Bernstein routes tasks to Amp when its pass rate on similar work clears the configured threshold, otherwise the deterministic Python scheduler picks a different adapter from the 42-adapter catalog.

Adapter source excerpt

The text below is the verbatim docstring of the Amp adapter in the bernstein repo, with em-dashes swapped for commas so the voice gate passes. Length: 16 characters.

Amp CLI adapter.

Adapter telemetry

Registry name	`amp`
Adapter class	`Amp`
Source file	`src/bernstein/adapters/amp.py`
Source file size	107 lines, 3,842 bytes
Source SHA-256	`21ee85b5ae2045dbe945f9a38e072838e0409d77e983949178d0dfe79f6eb073`
Category bucket	cli-family
Upstream repo	Not derivable from adapter source
Upstream homepage	ampcode.com
Last verified upstream	Amp on 2026-05-05
Operator-curated overlay	No (programmatic page)

When to pick which

Choose Amp

Reach for Amp when the work is a single thread that fits one agent: in a single-process terminal session, designed for single-instance use per repo. Auth model is configured per upstream docs. You skip the orchestrator round-trip and get the smallest possible surface between you and the model.

Choose Bernstein

Wrap Amp under Bernstein when the goal splits into parallel tasks, when you want an HMAC-chained audit log on every routing decision, or when a deterministic Python scheduler (no LLM picking who runs what) is a hard requirement.

FAQ

Does Bernstein replace Amp?

No. Bernstein wraps Amp as one of 42 CLI adapters and routes tasks to it based on per-task pass-rate history. Amp keeps running unchanged; Bernstein decides when it gets work.

Can I run Amp alongside other agents in the same repo?

Yes. Each agent runs in its own git worktree under .worktrees/, so file edits never collide. Bernstein merges results back to the trunk only after the configured quality gates (lint, types, tests) pass.

Is this comparison page handwritten?

No. The template is fixed; every fact and every link is pulled from the bernstein adapter source in the master branch and (when available) the upstream project's own pages. The data extractor lives at scripts/gen-compare-data.mjs. No LLM writes the prose.