Introducing Context Repositories: Git-based Memory for Coding Agents | Letta
We're introducing Context Repositories, a rebuild of how memory works in Letta Code based on programmatic context management and git-based versioning.
We're introducing Context Repositories , a rebuild of how memory works in Letta Code based on programmatic context management and git-based versioning. Letta Code stores a copy of the agent’s context in the local filesystem, meaning agents can leverage their full terminal and coding capabilities (including writing scripts and spawning subagents) to manage context, such as progressive disclosure and rewriting context for learning in token-space . In comparison, prior approaches to memory limited agents to MemGPT -style memory tools or virtual filesystem operations. Context Repositories are git-
saved by
related reading
- Sleep-time Compute | Lettaletta.com
- Continual Learning in Token Space | Lettaletta.com
- Effective context engineering for AI agents \ Anthropicanthropic.com
- Code Storage by the Pierre Computer Companycode.storage
- Memory Models: Towards Agents That Learnletta.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- The versioned filesystem for AI agents | Mesamesa.dev
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Memory in the wild: how we use Context Engine on our own code | Applied Computeappliedcompute.com
- Supermemory — Memory and continual learning for agentssupermemory.ai
- GitHub - mem0ai/mem0: The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.github.com
- The AI Agent Landscape in 2026 | Canteenthecanteenapp.com