engram

EngramX — the cached context spine for AI coding agents.

Your AI coding agent keeps re-reading the same files. EveryRead, everyEdit, everycatre-loads context that's already in your window.

EngramX is the spine.It intercepts every file read at the tool boundary, answers from a pre-assembled context packet held inthree layers of cache— a knowledge graph the agent has already "paid" to build, a per-provider SQLite cache of external lookups, and an in-memory LRU of recent queries — and hands the agent a single ~500-token response instead of a raw file.

The agent gets what it needs, structured. Andevery plugin you add extends what engram can surface— Serena for LSP symbols, GitHub MCP for issue context, Sentry MCP for production errors, Supabase / Neon for schema. Each one closes a context gap the agent would otherwise spend turns researching. (More providers = more capability; whether they net fewer tokens on a given task depends on the task — measure it on yours.)

Per-file structural reduction on a reproducible benchmark: up to ~89%(engramx's own codebase; structural token reduction, not agent-loop cost). On the committed 87-file run, 85 of 87 real source files saw reduced per-file token cost, best case 98.4% (18,820 tokens → 306); a fresh sample of 50 files reduces ~89.5% aggregate. Your per-repo numbers vary — run it on yours.

What this number is (and isn't):~89% is aper-file structural context reductionmeasured on engramx's own repo with all 9 providers active — it measures how much smaller engram's context packet is than reading the full files raw. It isnotan agent-loop cost-savings figure and will differ on your codebase. Your actual dollar saving depends on your prompt-caching setup and workload — run the benchmark on your own repo (see](https://github.com/NickCirv/engram/blob/HEAD/docs/integrations/continue.md)[Benchmark) to get your structural number.

npm install -g engramx cd ~/my-project engram setup

That's the install.engram setuprunsengram init(builds the graph),engram install-hook(wires the Sentinel into your AI tool), detects your IDE, dual-emitsAGENTS.md+CLAUDE.md, then runsengram doctorto verify everything green. Under 30 seconds on most projects. Works in Claude Code, Cursor, Codex CLI, Windsurf, GitHub Copilot Chat, JetBrains Junie, Aider, Zed, Continue — any agent that readsAGENTS.mdor uses MCP.

Thenext sessionyou open starts with the spine pre-loaded: project brief already in context, file reads intercepted, a live HUD showing cumulative savings, bi-temporal mistakes waiting to warn you, and any plugins you've added already answering their domains.