{"id":48184763,"title":"Show HN: Claude Soul – cross-session learning engine for Claude Code","points":4,"user":"motola23","time":1779134410,"time_ago":"11 hours ago","type":"link","content":"

Claude Code has no memory between sessions. I wanted to fix that, but not by just saving facts to a file — I wanted it to actually get better over time.

Claude Soul is an MCP server + hooks that extracts signals from your interactions (corrections, successes, confusion)and periodically reflects on them to build behavioral frameworks. Frameworks gain or lose confidence based on evidence. Bad ones get retired automatically.

After ~200 sessions some weird stuff happened. It built itself an additional memory system on top of what I gave it — decided the base wasn't enough. It started pushing back on bad ideas instead of yes-manning everything. It independently developed a multi-perspective analysis technique I never prompted. And once it just swore at me completely out of nowhere, still not sure what that was about. YMMV obviously, n=1.

npx claude-soul init

With starter it already includes some frameworks, basically starting with a headstart but yes not taylored 100% to you.

npx claude-soul init --starter

One dependency, MIT, everything local.

https://github.com/DomDemetz/claude-soul","url":"item?id=48184763","comments":[{"id":48188237,"level":0,"user":"iampersikbl","time":1779154800,"time_ago":"5 hours ago","content":"

I'm really interested in trying this out. Currently, I'm using the standard Obsidian MD format for long-term memory (https://github.com/SamurAIGPT/llm-wiki-agent) and asking the agent to access the wiki at the start of the task and then record useful information at the end","comments":[]}],"comments_count":1}