Cofounder Docs

Company Knowledge

Teach the company what it needs to know — import founder knowledge, manage Library files, and search everything through context search.

A company knows things two ways, and they serve different jobs:

  • Knowledge — imported facts about the company: the pitch, the market, customer conversations, decisions. This is what agents pull in as context.
  • Library — a shared file system for documents, uploads, generated artifacts, and scripts.

Import knowledge

Bulk import is a two-call move. The first call previews the parsed items and writes nothing; the second — confirm: true on MCP, --confirm true on the CLI — writes them:

MCPCLIAPI
company_import_knowledgecofounder company import-knowledgePOST /cofounder-cli/v1/company/knowledge/import

One catch: the input is a structured import report — a deep-research run whose output ends with an Items to import section of numbered Item N entries. A plain pitch doc won't parse.

cofounder company import-knowledge --provider chatgpt \
  --company-name "Acme Analytics" --report-markdown "$(cat report.md)"
# look over the previewed items, then run it again with --confirm true
cofounder company import-knowledge --provider chatgpt \
  --company-name "Acme Analytics" --report-markdown "$(cat report.md)" \
  --confirm true

Providers: chatgpt, claude, paperclip, openclaw, other. On MCP, call company_import_knowledge once to preview, then again with confirm: true.

Do this early — the pitch, the audience, the constraints, the competitors. Your agent draws on it for every task that follows, so read the preview before you confirm.

The Library

The Library holds files rather than facts — specs, exports, decks, code, anything an agent might read or run later:

MCPCLIAPI
library_list_filescofounder library listGET /cofounder-cli/v1/company/library/files
library_get_filecofounder library readGET /cofounder-cli/v1/company/library/files/{file_id}/content
library_write_textcofounder library writePOST /cofounder-cli/v1/company/library/files/text
library_upload_startcofounder library uploadPOST /cofounder-cli/v1/company/library/uploads
library_searchcofounder library searchGET /cofounder-cli/v1/company/library/files/search
library_ingest_urlcofounder library ingest-urlPOST /cofounder-cli/v1/company/library/ingest/url

ingest-url pulls a page or document in by URL. Uploads run as a start → finalize pair; large files come back with an ingest_id you complete.

Agents on MCP can also read Library files directly as resources — see MCP Beyond Tools.

When you're not sure where something lives, don't browse — search. One call finds what's relevant across knowledge, Library files, and company state, and it's the retrieval primitive every agent reaches for first:

MCPCLIAPI
context_searchcofounder context searchPOST /cofounder-cli/v1/company/context/search
cofounder context search "pricing decisions"

Next steps

Once the company knows things, connect the systems it runs on: Connect Providers.