Context vs Memory
Snipara separates source truth from durable state. Context is where documents live. Memory is where decisions, learnings, preferences, and short-lived carryover live.
Rule of thumb
Context first. Memory second. Task commit last.
Quick split
| You need to know... | Use | Why |
|---|---|---|
| What does this RFP, spec, PDF, or client doc say? | rlm_context_query or rlm_load_document | Those are source documents and current truth. |
| What are the team standards or reusable business playbooks? | rlm_shared_context | Shared collections are still document context, not memory. |
| What did we decide last week about pricing, UX, or architecture? | rlm_recall | That is durable memory, not a raw document lookup. |
| What preferences or learnings should follow the next session? | rlm_session_memories / session-bootstrap | That restores durable memory state and optional short carryover. |
| What should become reusable memory after this task? | rlm_end_of_task_commit / task-commit | That persists only durable outcomes instead of whole transcripts. |
Context surfaces
rlm_context_queryfor ranked document retrieval across project docs, parsed business files, and linked context.rlm_shared_contextfor project-linked standards, best practices, and business playbooks.rlm_load_documentwhen you already know the path and need exact source text.rlm_code_*tools for structural code truth that should not be treated as generic document search.
Memory surfaces
rlm_recallfor past decisions, preferences, validated learnings, and scoped memory questions.rlm_session_memoriesfor session bootstrap.rlm_end_of_task_commitfor durable outcomes after work is complete.rlm_rememberorrlm_remember_bulkonly when you are explicitly storing a durable memory, not uploading source documents.
Default agent workflow
- Start with context retrieval.
- Pull shared standards only when the task needs them.
- Recall memory only for decisions, learnings, preferences, or carryover.
- Do the work.
- Commit only durable outcomes back into memory.
Anti-patterns
- Do not use memory as a substitute for reading a spec, PDF, or client file.
- Do not upload whole source documents into memory.
- Do not treat shared context collections as memory; they are still documents.
- Do not persist noisy task transcripts when a compact task summary is enough.