Knowledge graph CLI for managing features, ADRs, and test criteria as MCP-discoverable artifacts.
A knowledge graph for LLM-driven development. You give Claude (or Cursor, or Codex) too much code and not enough decisions, and it builds the wrong thing. Product fixes the context problem at the root: it manages your features, architectural decisions, and test criteria as a structured graph of markdown files, then assembles the exact context bundle an agent needs — feature plus the ADRs that…
La vérification confirme l’identité de l’éditeur (la propriété du dépôt), pas la sûreté du code. L’analyse de sécurité couvre les CVE connues et les scripts d’installation suspects.
Forge n’a aucune analyse enregistrée pour cette entrée et n’a donc aucune observation de sa surface d’outils. C’est une absence de preuve, pas la preuve qu’elle n’expose aucun outil.
A knowledge graph for LLM-driven development. You give Claude (or Cursor, or Codex) too much code and not enough decisions, and it builds the wrong thing. Product fixes the context problem at the root: it manages your features, architectural decisions, and test criteria as a structured graph of markdown files, then assembles the exact context bundle an agent needs — feature plus the ADRs that govern it plus the tests that validate it — in one command. No database. No service. Just markdown with…