Knownbase vs Marginal

Stop re-explaining your codebase to AI. Knownbase gives Claude Code, Codex and MCP agents persistent project memory that survives every session.

Track every LLM call's cost and slice it by customer, feature, model, any field you define.

About Knownbase

Stop re-explaining your codebase to AI. Knownbase gives Claude Code, Codex and MCP agents persistent project memory that survives every session. Knownbase gives your AI coding agents persistent, searchable project knowledge, so architecture decisions, debugging discoveries, conventions and lessons survive across sessions and tools. Works with Claude Code, Codex, Cursor, ChatGPT and any MCP-compatible agent. They're storage failures: the agent learned something real and had nowhere durable to put it. Compaction loses the discoveries The context gets compacted mid-task and the hard-won finding from two hours ago is summarized down to nothing.

About Marginal

Track every LLM call's cost and slice it by customer, feature, model, any field you define. Marginal tracks the cost of every LLM call and slices it by the fields you care about, customer, feature, model. Cost is computed server-side, usage in, dollars out. Every API request is logged with its outcome, accepted counts, rejected events and why, stripped keys, unpriced models. The SDKs are zero-dependency, buffered, fire-and-forget: track() never throws and never blocks your request path.