Post

Context repositories are our biggest innovation since sleeptime compute. Letta Code memory is now git-backed. Any number of agents can swarm over things to learn, remember, and store them in a cohesive format. Massively parallel memory management with standard conflict resolution.

Our original sleeptime compute was a dual-agent system. A primary agent works, a background agent reflects on the conversation and updates memory. Powerful, but single-threaded. One agent learning at a time.

Context repositories change that. Each subagent gets an isolated worktree, processes a slice of experience, and merges back. Memory formation can now fan out across as many agents as you want.

For example, Letta Code's /init can now dispatch subagents to comb through Claude Code and Codex histories to rapidly learn your entire project from the start. No more lock in. We hate lock in.

Our general approach to memory is "keep it simple, stupid." What's simpler than a file? Every agent already knows how to work with files and terminals. They also know git. Easy conflict resolution. We just made formalized it an built it directly into our open source agent harness.

Letta Code supports context repositories now. Enable it with /memfs enable. Read more: www.letta.com/blog/contex...