How to use the CMEM commands: long-term agent memory
CMEMSET stores a fact scoped to (agent, user); CMEMGET recalls by meaning, recency-blended; consolidation retires contradictions automatically.
Notes from the nest · 980 posts
Engineering notes written by the people building Crowkis. Comparisons, use cases, economics, internals, security, operations, and nothing written just to rank.
CMEMSET stores a fact scoped to (agent, user); CMEMGET recalls by meaning, recency-blended; consolidation retires contradictions automatically.
Building API documentation bots on the Mistral SDK? Add a semantic cache so the same endpoint questions from every developer stop costing full price.
Building AI search on Ollama? Add a semantic cache so popular queries hit again and again stop costing full price.
Building voice assistants on Semantic Kernel? Add a semantic cache so latency-sensitive, repetitive spoken queries stop costing full price.
Building sales enablement tools on LangChain? Add a semantic cache so reps asking the same product questions stop costing full price.
In-process HNSW vector index, keeps a custom, persistent HNSW graph in the same process as the store, so a lookup and its scoring never cross a network hop, sub-millisecond search. Here's how Crowkis does it and why it matters for cost and safety.
Injected instructions in one response become served truth for every similar query, unless the cache can smell an answer that doesn't answer.
Take your daily query volume, multiply by the repeat fraction, multiply by your blended price per call. That number, twelve times a year, is the cache argument.
CGUARD checks a prompt for jailbreaks and injections, normalizing leetspeak and zero-width tricks first, and returns a verdict, category, and match.
Version a prompt, split traffic across versions with sticky per-user bucketing, render variables, and roll back, without a deploy or a feature-flag service.
Building customer support bots on LangChain.js? Add a semantic cache so repeat questions from every customer, all day stop costing full price.
Building ecommerce assistants on Ollama? Add a semantic cache so the same product and policy questions across shoppers stop costing full price.
Building email drafting tools on Semantic Kernel? Add a semantic cache so similar drafts requested over and over stop costing full price.
Building knowledge base assistants on LangChain? Add a semantic cache so the same lookups across a team all day stop costing full price.
Group-commit WAL, batches fsyncs on a timer instead of per write, for materially higher write throughput when you enable it. Here's how Crowkis does it and why it matters for cost and safety.
Cached answers derive from sources, a doc, a config, an API. CSOURCE ties answers to their origin so that when the source changes, every answer built on it can be purged in one move.
docker pull, restart, done, no schema migrations, no export/import, no upgrade runbook. The on-disk format is a stability promise, not an implementation detail.
COUTCHECK scans a response for PII and toxicity, optionally validating JSON, and returns the entities found so you can redact, block, or regenerate.
Building coding assistants on LangChain.js? Add a semantic cache so the same explanations and boilerplate reasoning, dozens of times a day stop costing full price.
Building healthcare Q&A assistants on Ollama? Add a semantic cache so recurring policy and triage questions stop costing full price.