Dataconto: who buys company records and code

Counts code the way pre.dev's public script does (code files in full, text files up to 10x the code, minified and bundle-named files skipped, 4 bytes per token) and prices it at Pangea's published non-exclusive list rates per million tokens of source and of git history. Give files (path and size in bytes, e.g. from `git ls-tree -r -l HEAD`), or code_bytes and text_bytes, or source_tokens. History is optional. A list price, not an offer.

For a company canceling its tools or closing: the last day to export from each tool once the account ends, by plan, from what each vendor's own terms say happens after cancellation (export window in days, kept with no export, or nothing). Each row quotes the vendor's words with the date read. With no plan given, the plan with the shortest window is used and flagged. Tool ids as in get_tool_terms.

What micro1's, Telegraph's and Grepped's own public estimators give for a company's records, from team size, years in business and headquarters (revenue optional, Grepped only). Each range is the buyer's formula, checked against its live page on the date given; none is an offer and Dataconto adds no figure of its own. Pass offer_usd (and offer_from) to place an offer the owner received against each range and the offering buyer's published range. Also returns the other listed buyers these answers don't rule out.

Runs Dataconto's fit check: each listed buyer's published criteria against the owner's answers. Returns, per buyer program, a verdict (strong = every criterion met, possible = none failed but some unknown, none = a criterion failed), each criterion as met, failed or unknown, the reasons for a miss, the buyer's published figure with the date checked and its Dataconto page. Unanswered questions count as unknown; `missing` lists the ones worth asking.

One program with its current facts: what it takes, who qualifies, payout, fees, exclusivity, payment timing and process, each quoted from the buyer's page with the date read.

Dated, sourced facts across programs: payout ranges, per-token rates, payout caps, platform fees, payment timing, eligibility. History is kept when a term changes (current=false rows). Press-only figures are flagged with source_type press.

For business tools companies keep records in (chat, email, tickets, docs, CRM, call recordings, code hosts): who owns the customer's data, whether the vendor trains AI on it (generative and other models, by plan), whether it keeps aggregated use, what can be exported on which plan and by whom, how much history the plan keeps, and how long data stays after cancellation. Each answer is quoted word for word from the vendor's own terms, AI page, data processing addendum or help article, with the date read. "The terms don't say" means every contract was read and none answers; "Not read yet" means a document is still unread. Answers marked inferred are a reading of the text, not its words. Not legal advice.

Programs that pay owners for company records (email, chat, tickets, docs, CRM, databases) or private code, including from closed or winding-down companies. Returns each program's summary, who qualifies, published payout range or rates, countries and its Dataconto page. Programs listed on Dataconto's buyer pages come first.

Dataconto's rights check: from who can sign, customer contracts, personal data, staff and contractor IP and the tools the company uses, a verdict (ready = nothing in the way, work = steps to finish before signing, not_yet = nobody known who can sign for a closing or closed company) and the steps, each with its level (block, work, note, ok) and the Dataconto page that holds its source. Unanswered questions count as not sure and are listed in `missing`. With tools, also returns what each tool's terms say on ownership, export and AI training, each quote dated. Sums up published sources; not legal advice. Tool ids as in get_tool_terms.