- engineering 21
- agents 14
- claude-code 12
- rag 10
- memory 7
- architecture 6
- operations 5
- migration 4
- security 4
- hooks 3
- vault 3
- durability 2
- honest-tradeoffs 2
- multi-agent 2
- query-planner 2
- queues 2
- self-hosting 2
- skills 2
- storage 2
- transactions 2
- afk 1
- chunking 1
- compliance 1
- concurrency 1
- context-engineering 1
- cost 1
- cost-tracking 1
- data 1
- decision-frameworks 1
- disaster-recovery 1
- evals 1
- firebase 1
- hardware 1
- incident 1
- intro 1
- isolation 1
- kubernetes 1
- learning 1
- manifesto 1
- mcp 1
- mongodb 1
- observability 1
- ops 1
- performance 1
- persistence 1
- pgvector 1
- postgres 1
- regression-testing 1
- sagas 1
- sdk 1
- search 1
- slash-commands 1
- stride 1
- threat-model 1
- tutorial 1
- vector 1
- wal 1
- MAY 2026
Agent observability — traces, tokens, and costs in RedDB
Most Claude Code setups can't answer "what did the agent cost me last sprint?" or "which tools dominate p99 latency?". A PostToolUse hook that writes every tool call, token count, and cost into RedDB turns those questions into one-line SQL.
-
Hooks that mutate state — making Claude Code hooks transactional with RedDB
A PostToolUse audit-log hook looks trivial until the agent crashes mid-turn, the network blips, or Slack 503s. Wrap the side effects in a RedDB transaction with idempotency keys and a saga for the external call, and the hook stays honest.
-
RedDB as Claude Code's memory backend — beyond CLAUDE.md
Swap the static MEMORY.md file for a queryable, embeddable memory layer. A SessionStart hook reads top-K memories into context, a /remember slash command writes them, and RedDB stores rows, vectors, and audit log in one transaction.