Three windows into one cache: dashboard, Prometheus, logs
The built-in dashboard for humans, /metrics for your Grafana, one JSON line per event for your pipeline, same truth, three consumers, zero adapters.
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.
The built-in dashboard for humans, /metrics for your Grafana, one JSON line per event for your pipeline, same truth, three consumers, zero adapters.
A cache exists to make costs predictable. Metering the cache would be self-defeating. So Community is free and Enterprise is flat per cluster, priced on a call, not a meter.
CBUDGET reports token and dollar consumption per tenant in real time, and surfaces the tenants approaching or crossing their thresholds.
One config block turns Crowkis into a tool an AI assistant can hold, check the cache, store the answer, over MCP, with the same trust pipeline as every other write.
347 integration tests, a smoke suite that kills the process on purpose, and a Docker image hardened before anyone asked. The receipts behind 'production-ready.'
Building chatbots on LangChain.js? Add a semantic cache so high-volume conversational traffic that repeats constantly stop costing full price.
Building multi-agent systems on Ollama? Add a semantic cache so a swarm of agents asking overlapping questions stop costing full price.
Building IT helpdesk bots on Semantic Kernel? Add a semantic cache so the same tickets and fixes, endlessly stop costing full price.
Building meeting-notes summarizers on LangChain? Add a semantic cache so similar summaries requested repeatedly stop costing full price.
MCP server for AI apps, doubles as an MCP server over stdio, so Claude and any MCP-capable agent can check the cache and store what they compute. Here's how Crowkis does it and why it matters for cost and safety.
Sometimes you need to clear 'everything about the old pricing', a fuzzy, semantic set. CINVALIDATE takes a natural-language instruction, previews what it would purge, and only acts on COMMIT.
Most semantic caches call out to a vector database. Crowkis embeds the HNSW graph in-process, and that placement decision is worth more than any algorithm tweak.
Python gateways treat caching as one feature among forty. Crowkis treats it as the product, and ships it without a Python supply chain attached.
CDEDUP finds entries that mean the same thing and collapses them, reporting clusters and memory reclaimed, best run as off-peak maintenance.
Building AI search on LangChain.js? Add a semantic cache so popular queries hit again and again stop costing full price.
Building voice assistants on Ollama? Add a semantic cache so latency-sensitive, repetitive spoken queries stop costing full price.
Building sales enablement tools on Semantic Kernel? Add a semantic cache so reps asking the same product questions stop costing full price.
Building SQL generation tools on LangChain? Add a semantic cache so the same schema questions and query shapes stop costing full price.
Add a semantic cache to LangChain so repeated and reworded questions are served for free, no rewrite, self-hosted.
A WHERE clause is a promise; a namespace is a wall. How Crowkis makes cross-tenant leakage structurally impossible rather than procedurally unlikely.