iryna_kondr

2 bulan yang laludiscuss

Thanks for the feedback!

2 bulan yang laludiscuss

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.

Looking for your feedback!

Github repo: https://github.com/luml-ai/dreamer

Blogpost: https://luml.ai/blog/2026/dreamer-self-evolving-agents

iryna_kondr

5 bulan yang laludiscuss

I’ve definitely been feeling that shift too. What have you guys found that helps with this? Any habits you use to avoid the constant context switching and decision fatigue?

iryna_kondr

5 bulan yang laludiscuss

Hi Emilie, nice project, thanks for sharing. I’m curious whether there were any decisions that you added mainly for educational value even though you wouldn’t make the same call in a production system?

iryna_kondr

6 bulan yang laludiscuss

My experience is similar. AI's context is limited to the codebase. It has limited or no understanding of the broader architecture or business constraints, which adds to the noise and makes it harder to surface the issues that actually matter.

iryna_kondr

6 bulan yang laludiscuss

Great visualization! What part of this project was the hardest to get “right” (math, overall aesthetic balance, etc.)?

iryna_kondr

Submissions

Show HN: The platform layer for agentic ML engineering

Ask HN: What are your strategies for reviewing AI generated code?

Show HN: Self-improving skills for any coding agent

Dreamer: Make any coding agent self-evolving, across the whole team

Show HN: AGENTS.lock – a package manager for Agents/Skills/MCPs

comments