Dreamer is a framework inspired by Claude's dream mode, but extends it to any Coding CLI and multiple users at the same time.
In short, agents submit short memories through an MCP server when they hit something the current context didn't cover. Then, a scheduled "dream" consolidates each batch into long-term memory and updates the AGENTS.md and skills from it. The produced skills can be pushed to git and fed back to the agents, essentially enabling the autonomous self-evolution loop
Main features:
- Works with any coding agent that supports MCP and skills.
- Works across the team: submissions pool across everyone's sessions and aggregated into a team-level context.
- Output is plain AGENTS.md plus skills, so it is easy to version, review, edit.
- Extensible by design. Every component (short term memory, long term memory, dreamer model, hooks, etc) is a Python Protocol and is wired from a runtime config, so virtually anything can be swapped/extended.
Dreamer is a framework inspired by Claude's dream mode, but extends it to any Coding CLI and multiple users at the same time.
In short, agents submit short memories through an MCP server when they hit something the current context didn't cover. Then, a scheduled "dream" consolidates each batch into long-term memory and updates the AGENTS.md and skills from it. The produced skills can be pushed to git and fed back to the agents, essentially enabling the autonomous self-evolution loop
Looking for your feedback!Github repo: https://github.com/luml-ai/dreamer
Blogpost: https://luml.ai/blog/2026/dreamer-self-evolving-agents
Looks like something anyone working with AI agents will eventually need
Thanks for the feedback!