Tokenminning: saving tokens (PostHog)
PostHog's newsletter piece on optimizing AI token spend: track usage, trim AGENTS.md, audit MCP schemas, understand prompt caching, pick the right model and separate working from long-term memory.
Similar in the index
- Codegraph A code knowledge graph that stays in sync, so coding agents navigate faster.
- ocache Composable caching with TTL, stale-while-revalidate and request deduplication.
- Fanout Sequenced courses on AI research, system design and ML math for developers.
- Gisting: compressing LLM agent context (Shopify) Shopify Engineering on compressing agent context to raise throughput and cut cost.
- Learn Inference An interactive guide to serving generative models in production.