Practical reads to help you spend less on AI.
Guides, benchmarks and deep dives on semantic caching, agent memory, LLM cost and LLM classification, from the team building Crowkis and Curva.
Subscribe with RSSOlder articles
Page 15 of 18-
How to cache n8n LLM calls with Crowkis
Add a semantic cache to n8n so repeated and reworded questions are served for free, no rewrite, self-hosted.
-
Summarization at scale: the same documents keep getting summarized
Reports, tickets, calls, and articles get summarized on every view, by every viewer, in every digest. The document didn't change between viewers. The bill did.
-
Give n8n agents long-term memory with Crowkis
Durable, per-user memory for n8n agents that survives restarts and consolidates contradictions, self-hosted, zero egress.
-
How to cache Flowise LLM calls with Crowkis
Add a semantic cache to Flowise so repeated and reworded questions are served for free, no rewrite, self-hosted.
-
Crowkis vs LangSmith: tracing the waste vs deleting it
LangSmith shows you every span of every chain, beautifully. The spans are still billed. There's a component whose job is making the spans not happen.
-
Give Flowise agents long-term memory with Crowkis
Durable, per-user memory for Flowise agents that survives restarts and consolidates contradictions, self-hosted, zero egress.
-
Classification and extraction: high-volume, low-variance, born to be cached
Routing tickets, tagging content, extracting fields, LLM classification runs millions of small calls over heavily repeating inputs. The cache hit rate is absurd, in your favor.
-
How to cache Dify LLM calls with Crowkis
Add a semantic cache to Dify so repeated and reworded questions are served for free, no rewrite, self-hosted.
-
Give Dify agents long-term memory with Crowkis
Durable, per-user memory for Dify agents that survives restarts and consolidates contradictions, self-hosted, zero egress.
-
Crowkis vs Cloudflare AI Gateway: the edge is the wrong place for trust decisions
Cloudflare's gateway adds caching at the CDN layer, exact-match, eventually-evicted, on someone else's network. Useful plumbing; not a reuse brain.
-
How to cache Rig (Rust) LLM calls with Crowkis
Add a semantic cache to Rig (Rust) so repeated and reworded questions are served for free, no rewrite, self-hosted.
-
Docs assistants: your documentation has a top-40 chart
Every docs site has the same hit parade, auth, rate limits, pagination, that one confusing endpoint. The assistant answering them should not bill like a consultant.
-
Give Rig (Rust) agents long-term memory with Crowkis
Durable, per-user memory for Rig (Rust) agents that survives restarts and consolidates contradictions, self-hosted, zero egress.
-
How to cache Continue LLM calls with Crowkis
Add a semantic cache to Continue so repeated and reworded questions are served for free, no rewrite, self-hosted.
-
Crowkis vs Kong AI Gateway: plugins are not engines
Kong added AI plugins to a great API gateway. A semantic-cache plugin in a proxy is a feature; a semantic cache engine is a product. The difference shows in production.
-
Give Continue agents long-term memory with Crowkis
Durable, per-user memory for Continue agents that survives restarts and consolidates contradictions, self-hosted, zero egress.
-
Answer-engine products: when the answer is the product, margin is the moat
If your product is answering questions, your COGS is the model bill and your UX is the latency. The cache moves both, which makes it strategy, not plumbing.
-
How to cache LangFlow LLM calls with Crowkis
Add a semantic cache to LangFlow so repeated and reworded questions are served for free, no rewrite, self-hosted.
-
Give LangFlow agents long-term memory with Crowkis
Durable, per-user memory for LangFlow agents that survives restarts and consolidates contradictions, self-hosted, zero egress.
-
Crowkis vs building it yourself: a love letter to the repo you'll abandon
Every team builds the in-house semantic cache once. The prototype takes a week. The production version takes the year you didn't budget. We know, we budgeted it.
-
How to cache the Cohere SDK LLM calls with Crowkis
Add a semantic cache to the Cohere SDK so repeated and reworded questions are served for free, no rewrite, self-hosted.
-
Give the Cohere SDK agents long-term memory with Crowkis
Durable, per-user memory for the Cohere SDK agents that survives restarts and consolidates contradictions, self-hosted, zero egress.
-
How to cache Zapier AI LLM calls with Crowkis
Add a semantic cache to Zapier AI so repeated and reworded questions are served for free, no rewrite, self-hosted.
-
Give Zapier AI agents long-term memory with Crowkis
Durable, per-user memory for Zapier AI agents that survives restarts and consolidates contradictions, self-hosted, zero egress.