Primr

CI PyPI Python 3.12+ License: Apache 2.0 OpenSSF Scorecard

Company URL → sourced strategic brief. Built for agent hosts and the CLI: structured collection, confidence labels, and durable artifacts—not a free-form chat essay.

Primr gathers public site pages, DNS/recon, hiring signals, and other open sources, then produces a consultant-style Strategic Overview (and optional strategy modules) with citations and Confirmed / Reported / Estimated / Hypothesis labels. Point an agent at the repo, or run the CLI; the product is the same job either way.

_{Placeholder demo data (ExampleCo), not a live company capture.}

primr "ExampleCo" https://example.co

In an agent chat, that request defaults to Primr Zero: keyless evidence collection in Primr, research and writing in the host (when the host plan does not bill API usage). When a human runs the command directly in a terminal, it retains the provider-backed CLI path after a dry-run estimate and approval.

What it is for

Use Primr when you need a serious first draft for discovery, account planning, diligence, competitive analysis, or strategy work—not a two-paragraph pre-call blurb (use normal web search for that).

• Structured brief with uncertainty labels, not scattered notes
• Research grounded in public evidence, not only search summaries
• Cost-aware local execution: dry-run before billable work
• Reusable Markdown/DOCX artifacts for humans, agents, and downstream tools

Primr is not a generic crawler, a SaaS collaboration app, a model-serving platform, or a tool for bypassing authentication, paywalls, or site restrictions.

Start here

Where you run it	Default path	Spend	Result
Agent chat pointed at Primr	Primr Zero	No Primr model API spend; verify host plan allowance	Evidence bundle + host-written sourced dossier
Terminal or script	Provider-backed	Billable after --dry-run + approval	Primr Strategic Overview + strategy artifacts

Same deliverable set either way: Strategic Overview and AI Strategy as Markdown and DOCX (on the Zero path, primr render <file>.md converts host Markdown to DOCX at $0). A configured API key is capability, not consent to spend.

Agent path

Point a capable agent at this repository:

primr "ExampleCo" https://example.co

The agent uses Primr Zero unless you explicitly request paid, metered, provider-backed, or premium execution. Details, MCP setup, and host handoff: Agent Integration · Zero-Cost / Primr Zero.

Terminal path

primr "ExampleCo" https://example.co --dry-run   # always first
primr "ExampleCo" https://example.co             # after you approve

Mode matrix, platforms, strategy types, and cost controls: Run Modes and Costs.

Install

• Python 3.12+
• No API key or GPU for primr recon / primr prep
• Keys only for provider-backed research (measured default: xAI + Gemini)
• primr init installs browser deps for scrape tiers

pipx install primr
primr --version

Plain pip install primr also works. On Windows, prefer pipx or the installer if primr is missing from PATH after pip.

The convenience installers set up pipx and common PATH issues. Download and inspect the script before executing it:

$primrInstaller = Join-Path $env:TEMP "primr-install.ps1"
Invoke-WebRequest https://raw.githubusercontent.com/blisspixel/primr/main/scripts/install.ps1 -OutFile $primrInstaller
Get-Content $primrInstaller
powershell -ExecutionPolicy Bypass -File $primrInstaller

primr_installer="$(mktemp)"
trap 'rm -f "$primr_installer"' EXIT
curl -fsSL https://raw.githubusercontent.com/blisspixel/primr/main/scripts/install.sh -o "$primr_installer"
cat "$primr_installer"
bash "$primr_installer"

Provider-backed setup only when you want billable runs:

primr init
primr doctor

Keys and full config: API Key Setup · Configuration.

Common commands

Need	Command
Agent-host dossier (Zero by default)	primr "Company" https://company.com
Keyless evidence bundle	primr prep "Company" https://company.com
Estimate a paid run	primr "Company" https://company.com --dry-run
Strategic Overview only	primr "Company" https://company.com --no-ai-strategy
Site corpus only	primr "Company" https://company.com --mode scrape
DNS only (no keys)	primr recon company.com
Skills pack	primr skills "Company" https://company.com
Markdown → DOCX/TXT ($0)	primr render "output/report.md"
Strategy on existing report	primr --ai-strategy-only "output/report.md" --dry-run

Focused help: primr --help. Everything: primr --help-all.

Cost gate

Billable runs need a fresh estimate and explicit approval. --budget N refuses to start above the cap. Batch, enrichment, vendor research, and standalone strategy each have their own quote path—see Run Modes and Costs.

Outputs

Default: customer-facing files under output/, diagnostics under working/.

• <Company>_Strategic_Overview_<date>.md / .docx
• <Company>_AI_Strategy_<date>.md (unless --no-ai-strategy)
• run_manifest.json (estimate, approval, audit)

Agent inventory (paths/roles only, no report body): primr://output/artifacts/by_job/{job_id}. Full artifact and recovery guides: Artifacts · Recovery.

Docs

Topic	Guide
Run modes and costs	RUN_MODES
Primr Zero / host-assisted	ZERO_COST
Agent / MCP / A2A	AGENT_INTEGRATION · API
API keys	API_KEYS
Configuration	CONFIG
Artifacts	ARTIFACTS
Skill packs	SKILL_PACK
Security	SECURITY
Contributing / architecture	CONTRIBUTING · ARCHITECTURE
Roadmap	ROADMAP

Docs site index: docs/README.md.

Disclaimer

Primr retrieves and analyzes public web content. You are responsible for site terms, provider costs, output accuracy, and legal fit. AI-generated analysis can be wrong or outdated—verify important findings before acting on them.

License

Apache 2.0. See LICENSE.