Proposal: durable project and user memory for Goose sessions
- Dominant language
- Rust
- Stars
- 54.2k
- Forks
- 6.2k
- Avg merge
- 3d 4h
- Merged PRs (30d)
- 240
Description
Hi, I’m Vivek Gupta, Founder & CEO at [MemCode](https://memcode.in). Goose is designed for extensible, tool-using agent workflows, and its users build up useful project context, preferences, and decisions over many sessions.
Would Goose consider an optional MemCode memory integration? MemCode provides durable, scoped memory that can preserve project conventions, user preferences, tool decisions, and learned context across sessions and model changes, while leaving the existing local and self-hosted paths intact.
I’d be glad to prepare a small example or PR around the appropriate extension point. The integration can be opt-in, with explicit scopes, retrieval controls, and forget/delete behavior. Is there a preferred design discussion or contribution path for this?
Contributor guide
Research direction
Look for extension points in the Goose codebase related to session state, memory, or tool integration. The issue mentions preserving project context and user preferences across sessions. Start by understanding how Goose currently manages session data and where an optional external memory service like MemCode could be hooked in. A small example or PR is proposed, so check existing integrations or plugin systems to see the pattern.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- ai-infra-agents
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100