Actual.ai CLI
CLI that answers architecture questions from ADRs and writes agent context files.
Tested on macOS and LinuxKnown vulnerabilities
Use it
Before you install: known vulnerabilities
pickfit found 4 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.
crates:zip 2.4.2zip: Critical Parser Differential & Security Control Bypass via Dual-Header Inconsistencies (Zip Cloaking) Leading to Arbitrary File Overwrite & RCE (GHSA-m665-v7pm-7grj, critical, fixed in 9.0.5)
See 3 more
crates:zip 2.4.2— RUSTSEC-2026-0369 (critical), fixed in 9.0.0crates:zip 2.4.2— GHSA-q7v9-x93c-xqv3 (high), fixed in 9.0.0crates:zip 2.4.2— RUSTSEC-2026-0367 (high), fixed in 9.0.0
macOS arm64
You need first
- Keys or accounts: Actual AI account
brew install actual-software/actual/actual
brew install actual-software/actual/actual
Where the README and reality differ
- README: actual adr-bot --dry-run works with no account or API key (ADR-backed context needs no account or API key)
What worked: needs a runner (claude-cli or ANTHROPIC_API_KEY); without it exits 2 with No runner available
Check that it works
actual --version 2>&1The output should contain “actual 0.11.0”.
First thing to try
mkdir -p /tmp/test-adr && cd /tmp/test-adr && git init -q && git config user.email "test@test.com" && git config user.name "test" && echo "# test" > README.md && git add . && git commit -qm init && echo done && ls -lacd /tmp/test-adr && actual advisor "Should new services talk over gRPC or REST?" 2>&1Run actual advisor "<your question>" inside a repository to ask an architecture question.
Linux x86_64
You need first
- Keys or accounts: Actual AI account
install actual CLI via npm
npm install -g @actualai/actual
Where the README and reality differ
- README: actual adr-bot --dry-run preview without writing
What worked: install a runner (e.g. npm install -g @anthropic-ai/claude-code) or set ANTHROPIC_API_KEY/OPENAI_API_KEY; without it adr-bot --dry-run exits 2 with No runner available - README: actual rules ls list rule documents
What worked: rule bullets must be - **<id>** LEVEL: text (e.g. - **cache-redis** MUST: ...); without it rules ls reports no parseable Rules and plan-check finds no rules
Check that it works
actual --versionThe output should contain “actual 0.10.0”.
First thing to try
mkdir -p /tmp/actual-test && cd /tmp/actual-test && git init -q 2>&1; echo "# test repo" > README.md; echo "console.log('hi')" > app.js; git add . 2>&1; git -c user.email=test@test.com -c user.name=test commit -qm init 2>&1; pwd; ls -la; git log --oneline | catcd /tmp/actual-test && actual status 2>&1Run actual advisor "<your question>" inside a repository to ask an architecture question.
What it does
- Ask architecture questions answered from your ADRsNot tested
- Write ADR guidance to agent context filesNot tested
- Check plans and changes against architecture rulesNot tested
How far pickfit got
macOS arm64
- Installs
- Starts
- 0 of 3 features work
- Works offline
Linux x86_64
- Installs
- Starts
- 0 of 3 features work
- Works offline
Other systems
Good for
- Ask an architecture question grounded in team ADRs
- Preview ADR guidance for a repository
- Write ADR-based context to CLAUDE.md
- Check an agent plan against architecture rules
- Check working tree changes against architecture rules
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
macOS arm64
Its main function works
- Replayed from scratch
- Works offline
- Checked on 1 Nov 2026
- Version 0.11.0
Linux x86_64
Its main function works
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version actual 0.10.0
Differences the test machine hit
- README: actual plan-check --plan-file plan.md
In the test: actual plan-check with a matching rule and no runner exits 0 with Could not check: no runner available (documented not_checked outcome, only conflicting exits non-zero)