Wire Memory – Persistent cross-session memory for Claude Code
Finally remembers your architecture decisions between Claude Code sessions — CLAUDE.md couldn't do this.
Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory
Evidence-based cognitive frameworks evolve across sessions, not just static memory storage.
Developers using Claude Code who want persistent AI improvement
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.
Finally remembers your architecture decisions between Claude Code sessions — CLAUDE.md couldn't do this.
Fixes the core gap: AI agents can now actually use interactive CLIs, not just dump output.
MCP server lets Claude search its own conversation history instead of re-deriving paid context.
Local RAG + MCP for Claude with zero external dependencies—elegant constraint execution.
Cross-project memory for coding agents, but MCP ecosystem is nascent and fragmentation risk high.
Persistent memory for Claude Code with auto-compaction recovery—but relies entirely on external API.