Rule of thumb · Pick Glean if you're 100+ seats with enterprise procurement, an Okta, and a SOC2 audit on the roadmap. Pick Bcontext if you're under that floor.
Markdown export at any time. Re-imports are idempotent — running the migration again updates in-place instead of duplicating.
Most tools support a markdown or JSON export. Drop the folder into the bcontext importer — sub-folders become folder nodes, pages become docs.
Run the auto-typer to suggest kinds — tasks, decisions, runbooks, meetings — based on title patterns and frontmatter. Review the diffs as proposals.
Side-by-side view of original + bcontext-typed nodes. Accept what's right, reject what's noise. The whole thing exports back to clean markdown anytime.
Glean's enterprise positioning means their pricing, contract length, and procurement cycle exclude entire segments where AI-first productivity is being invented. The 1-person indie hacker doing $50k/mo on a sprint of Claude Code, the 4-person AI consultancy with three clients in flight, the 12-person YC-batch startup — none of these can buy Glean. Bcontext exists because that segment generates real demand and there is no shipping product in the band.
The technical bet is that the underlying primitives — typed graph, hybrid retrieval, MCP, agent writes — generalise across segments. The enterprise wrappers (SSO, audit, advanced connectors) come later, at the Business tier. The hard-to-replicate part is the agent ergonomics: 60-second MCP setup, idempotent writes, AGENTS.md generation, skill nodes. That's what makes Bcontext sticky at the indie tier even after Glean releases MCP.
Pricing is the other axis. Glean is enterprise-priced with annual contracts; Bcontext is monthly, no minimums, free at the entry tier. That alone disqualifies Glean for the segment Bcontext targets.
The importer runs both ways. Keep your existing tool live, add bcontext as the agent surface, decide later.