DEVOURED
Give Your Coding Agents a Memory You Own
The funes project provides a durable, cross-platform memory layer, allowing coding agents like Claude Code and Codex to retain context between sessions.
What: funes enables local indexing and embedding of session histories, creating a portable memory store that functions independently of specific agent architectures.
Why it matters: As coding agents shift from ephemeral chatbots to long-running automation tools, standardized local state management is becoming a critical requirement for maintaining continuity.
Original article
funes introduces a durable memory layer for coding agents that allows them to retain and recall session histories across different machines and agents like Claude Code, Codex, pi, and Hermes. It enables contextual memory storage and retrieval without external dependencies, using local indexing and embedding.
Explore all 57 articles in today's digest
Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi