Engineering at Lindy

How we build Lindy.

Inside the team building an AI employee that does real work.

Latest · Agents / Memory

How we built the memory system at the core of Lindy Teammate

We tore out Lindy's RAG stack and replaced it with a plain file system that a memory agent rewrites every 12 hours from Slack, Gmail, meetings and tasks. Here's how it works.

Flo Crivello · August 16, 2026

2026-08-16How we built the memory system at the core of Lindy TeammateWe tore out Lindy's RAG stack and replaced it with a plain file system that a memory agent rewrites every 12 hours from Slack, Gmail, meetings and tasks. Here's how it works.Flo Crivello4 min
2026-06-24Migrating from Claude to DeepSeekWe moved most of Lindy's model traffic from Claude and Gemini to DeepSeek v4 Flash and cut inference costs on those routes by about 90%. Here's the eval and rollout process that made it safe.Bruno Škvorc5 min
2026-04-28AI agent guardrails: how we built a validator to stop rogue actionsA separate LLM call reviews every side-effectual action before it runs. The agent has to justify it, and the validator checks that against what the user actually asked for.Marvin Aziz8 min
2026-03-16iMessage API: three rewrites, one Apple ban, and what actually worksWe built iMessage support three times in six weeks. A Swift daemon, a BlueBubbles rewrite, then an API migration after Apple banned our account for sending 10K messages in 12 hours.Marvin Aziz9 min