fastpaca What happens when LLMs hit production?
I write about memory systems, context management, how to scale agents, and more.
Research · Open Source · Fractional & Advisory
Writing
All posts →Ultimate Guide to LLM Memory
How do you add memory to your agent or LLM? What works and what does not? How do you use multiple memory systems at once to cover each others weaknesses?
Design Your LLM Memory Around How It Fails
Not all context is sacred. Design your agent's memory around what happens when critical information gets dropped.
Universal LLM Memory Does Not Exist
I benchmarked Mem0 and Zep on MemBench to understand why production agents were failing. Memory systems cost 14-77x more and were 31-33% less accurate than naive long-context.
LLM Memory Systems Explained
An introductory guide to how LLMs handle 'memory', from context windows to retrieval systems and everything in between.
Open Source
GitHub →cria
New models, providers, and memory systems drop. Your prompts break.
Prompt architecture for fast-moving teams—same logic, swap the building blocks underneath when you need to upgrade.
pacabench
Benchmarking agents shouldn't mean wrestling with brittle scripts and lost progress.
Local-first, reproducible benchmarks with isolated execution and persistent state. No SDK lock-in.