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.
Local offline embeddings (CEMBED), turns text into vectors with the bundled local model, no API key and no egress, with a micro-cache so repeats are free. Here's how Crowkis does it and why it matters for cost and safety.
Every multi-tenant product says its tenants are isolated. The ones you can trust are the ones that try to break it on purpose. Here's how we prove no tenant can read another's data.
Building API documentation bots on Dify? Add a semantic cache so the same endpoint questions from every developer stop costing full price.
Building AI search on the Mistral SDK? Add a semantic cache so popular queries hit again and again stop costing full price.
Building voice assistants on LiteLLM? Add a semantic cache so latency-sensitive, repetitive spoken queries stop costing full price.
Building sales enablement tools on Haystack? Add a semantic cache so reps asking the same product questions stop costing full price.
Cache poisoning is the whole problem with semantic caches. A practical, Crowkis-grounded take, no hype, just what actually moves cost, latency, and safety.
Bring your own embedder / reranker, swaps in any sentence-transformers MiniLM or GTE export via ONNX, so you're never locked to the default model. Here's how Crowkis does it and why it matters for cost and safety.
The most secure dependency is the one that isn't there. Crowkis ships as a single stripped binary with the model baked in, no Python, no package manager, nothing to poison at runtime.
Building customer support bots on Rig (Rust)? Add a semantic cache so repeat questions from every customer, all day stop costing full price.
Building ecommerce assistants on the Mistral SDK? Add a semantic cache so the same product and policy questions across shoppers stop costing full price.
Building email drafting tools on LiteLLM? Add a semantic cache so similar drafts requested over and over stop costing full price.
Building knowledge base assistants on Haystack? Add a semantic cache so the same lookups across a team all day stop costing full price.
How to warm an LLM cache during a model migration. A practical, Crowkis-grounded take, no hype, just what actually moves cost, latency, and safety.
Multi-turn session memory (CSESSION), keeps a bounded conversation buffer with both recent-window reads and semantic search across the whole chat. Here's how Crowkis does it and why it matters for cost and safety.
We gave agents tools, planning, and the ability to act. We forgot to give them a place to remember. That gap is why your agents feel brilliant and amnesiac at the same time.
Building coding assistants on Rig (Rust)? 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 the Mistral SDK? Add a semantic cache so recurring policy and triage questions stop costing full price.
Building code review bots on LiteLLM? Add a semantic cache so the same review patterns across pull requests stop costing full price.
Building research assistants on Haystack? Add a semantic cache so overlapping literature and summary questions stop costing full price.