Letta releases open-source Trajectory package to standardize coding-agent data
The new format cuts token usage by up to fivefold and lets agents learn across Claude Code, Codex and Letta Code sessions.
By Ryan Merket · Published
Primary source: Letta
Why it matters
A common data format lets coding agents aggregate experience across Claude Code, Codex and Letta Code, cutting token costs and unlocking cross‑harness memory learning.
On July 24th 2026, Letta announced the open‑source trajectory package, a standard format for recording coding‑agent sessions across multiple harnesses such as Claude Code, Codex and Letta Code. The blog post on the Letta research site frames the launch as a response to the fragmented experience data that limits today’s agents from learning across tools.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.