Pillar · Token Economics
One observed session burned 8.59M tokens — 90% re-reading files. Memory is how you stop paying that tax every session.
Direct answer
To reduce AI coding token usage, attack the three costs that dominate every session: stale conversation history (re-billed every turn), whole-file reads (tens of thousands of tokens for one-line answers), and re-learning project knowledge from zero each session. The canonical waste case is an observed 8.59M-token session — 97.2% cache, ~90% re-reading, 175:1 input-to-output. Anvaya's answer is compounding memory: session outcomes become typed nodes that compress 12–25x per type (files ~20x, decisions ~16x, bugfixes ~24x, threads ~25x), and each turn assembles 2–4K packed tokens instead of ~50K raw. Sessions get cheaper and sharper with use, prompt caching covers the stable layers at ~10% price, and open measurement trials land Q3 2026.
Per-Node Ratios
Design estimates per memory node type, measured in the Mind repos — not benchmark runs.
Three Levers
Works with any agent, including Claude Code and Cursor — no new tools required.
Questions
Three levers dominate: split work into focused sessions (stale history is re-paid every turn), retrieve just-in-time instead of dumping files (spans, not whole files), and persist durable knowledge in a memory layer so sessions stop re-learning. Anvaya adds the compounding lever: calibrated memory that shrinks per-turn context from ~50K raw to 2–4K packed.
Per-node design estimates from the Anvaya Mind repos: each memory node type stores a fraction of the raw tokens that produced it (files ~20x, decisions ~16x, bugfixes ~24x, patterns ~24x, threads ~25x). A typical turn assembles 2–4K curated tokens instead of ~50K raw — the 12–25x range. These are engineering estimates, not benchmark runs; open trials arrive Q3 2026.
Caching cuts the price of repeated tokens ~90% but doesn't shrink what the model must attend to — noise still dilutes attention and degrades answers. Cache the stable layers (system prompt, conventions) and engineer the dynamic layers (retrieval, memory). Anvaya does both: cacheable system context plus packed per-turn memory.
Every token loaded is re-billed on every subsequent turn until compaction. A 10K file read at turn 3 costs another 10K at turns 4, 5, 6… A 30-message thread carries 29 dead messages into every call. Early-session discipline compounds across the whole session.
At 2026 Claude pricing (~$2–5 per million input tokens), an 8.59M-token session is roughly $17–43 of input — ~90% of it re-reading files. Multiply by sessions per week per developer and the memory layer pays for itself in attention alone, before counting accuracy.
One binary. 11+9 Rust crates. 545 tests. Hand-written HNSW index. Three transport modes. Four providers, Ollama, Anthropic, OpenAI, Siemens. Zero API keys required to start. Mind remembers everything after the first session.