workspace chat
ask in natural language, get answers cited to specific files and notion pages. intent detection routes between explain and generate paths.
- streaming sse with retrieval inline
- per-message intent tags
- conversation history, follow-ups
engram is an engineering intelligence platform. it ingests your github repos and notion workspaces, cross-validates docs against code, and answers grounded in the verified org knowledge that actually shipped. no hallucinated tribal lore.
eu-west-1 times out because the celery worker pulls the embedding model on first boot [1]. the deploy script doesn't warm the cache before health-check[2]. the runbook in notion calls for a 90s grace period; current k8s manifest sets 30s [3]— that's the mismatch.# k8s/eu-west.yaml — patch grace period readinessProbe: httpGet: { path: /healthz, port: 8000 } initialDelaySeconds: 90 # was 30 periodSeconds: 10
ask in natural language, get answers cited to specific files and notion pages. intent detection routes between explain and generate paths.
github oauth + notion oauth. periodic re-index via celery. one-click connect, progress in-line.
browse indexed sources, inspect chunk boundaries, drop pages that shouldn't be retrieved.
watch celery queues, inspect failed re-indexes, retry with one click. operator-grade observability.
save any answer as a durable artifact — code snippet, summary, or report. shareable, citeable, versioned.
cross-validate notion docs against the code they describe. flag stale runbooks before they cost an oncall.
auth, integrations, model preferences, mcp tokens. per-conversation provider overrides on the roadmap.
same retrieval, same answers — exposed via the model context protocol. plug engram into claude desktop, cursor, zed.
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐ │ github repos │ │ notion pages │ │ other sources │ │ oauth · webhook│ │ oauth · poll │ │ v1.5 surface │ └────────┬────────┘ └────────┬────────┘ └────────┬────────┘ │ │ │ └─────────────┬─────────────┘ │ │ │ [ celery ingest ] ──── chunk · embed · upsert ───── │ │ │ ▼ │ ┌─────────────────────────────────────┐ │ │ postgres + pgvector │ ◄── code is the truth │ chunks · embeddings · meta │ └─────────────────┬───────────────────┘ │ [ retriever ] ─── topK + rerank + intent shaping │ ▼ [ cross-validator ] flags notion ↔ code drift │ ▼ claude sonnet grounded generation │ ▼ ┌─────────────────┴───────────────────┐ │ web ui │ mcp plugin │ api │ └─────────────────────────────────────┘
engram is a thin, opinionated stack assembled from boring components and one interesting idea — that cross-validation between code and docs catches staleness before it hurts.
the chat engine detects intent (explain vs. generate) and adjusts the prompt accordingly; the retrieval pipeline is shared. all llm calls route through a single provider abstraction so we can swap models without touching routes.
start with one github repo and one notion workspace. engram indexes both, surfaces drift, and gives you cited answers in under six seconds from connect.