Remembering why

“Every one of the 50 writes returned success: true, and the DB stays integrity_check: ok. One process's entire batch was obliterated.”

“The cost of leaving duplicated logic is that agents will find it as prior art and replicate it further.”

“This is a data-durability bug in the AgentDB persistence layer: a long-running store should not be one interrupted/concurrent flush away from total loss.”

“the agents need to understand where everything lives and what depends on what. So, we built a company world modeled based on the entirety of our 25,000 repo code base”

“Persisted state after the background flush shows runCount=432. This creates the misleading impression that the CLI trigger did not execute, when in fact it did.”

“I think we found that the state-of-the-art in December was you could probably run this for about two weeks. By the end of those two weeks, you’d find that, hey, you want to like change a color of a button. Well, turns out this button is implemented in like 10 different places”

“The result is that state is written to whichever subdirectory the session drifted into, and then never read again. Nothing errors.”

“The core challenge of long-running agents is that they must work in discrete sessions, and each new session begins with no memory of what came before. Imagine a software project staffed by engineers working in shifts, where each new engineer arrives with no memory of what happened on the previous shift.”

“Agents are creating duplicate .claude-flow and .swarm folders in subdirectories instead of using the main workspace root folders.”

“There's a JSON file, one line per issue, and it has merge conflicts all the time, and it gets xlerped into the database, and there's a daemon, and it gets stale.”

“It's so wild because like 8 out of 10 get done, and 2 out of 10 get lost.”

“The inherent fragility of the v0.x Beads architecture, with its bidirectional sync, 3-way merge, two sources of truth, race conditions, and tombstone hell — that's all gone now.”

“Our team used to spend every Friday (20% of the week) cleaning up “AI slop.” Unsurprisingly, that didn’t scale.”

“A durable work record is not the same thing as a durable procedure.”

“When two ruflo MCP servers share one memory store, memory_retrieve on one server keeps returning a value after the other server has updated or deleted it.”

“Each change can be reasonable in isolation but since it’s frictionless, none of us necessarily has to talk to the others or familiarize ourselves with the code we are changing.”

“Some bugs get fixed 2 or 3 times, and someone has to pick the winner. Other fixes get lost. Designs go missing and need to be redone.”

“the maintainer's fix prevents cross-process corruption, but does not prevent two saveState() calls within the same process from racing on the shared <file>.tmp name.”