Give Claude Code persistent semantic memory for retrieving past decisions and judgments.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "claude-memory" yet — see the docs or source repo.
Find our previous decision about the authentication approach from memory, and summarize the final choice, reasons, and rejected alternatives.
A summary of past authentication decisions, including rationale and context.
Search memory for past cases related to “slow builds” and list the troubleshooting steps and conclusions.
Relevant historical cases semantically similar to the current issue and how they were handled.
Using historical judgment records in memory, assess the delay risk of this refactor and explain which past cases support the assessment.
A risk assessment calibrated by past judgments, with supporting precedents.
Developers can use it to recover prior architecture or implementation decisions from persistent memory in long-running projects. This reduces repeated debate and preserves context over time.
When a team faces a new coding issue or task, it can use semantic retrieval to find similar past cases, handling steps, and outcomes. This helps reuse prior experience quickly.
For risk, timeline, or approach assessments, it can surface prior judgment records through a judgment ledger to ground current predictions. This fits workflows that benefit from learning from past decision quality.
It is a persistent semantic memory system for Claude Code. It combines vector search with a judgment ledger to surface prior decisions and help calibrate predictions.
It mainly stores and retrieves past decisions, related context, and judgment records. This lets Claude Code refer to historical information instead of relying only on the current session.
The provided material does not include installation steps, runtime details, or key requirements. See the source repository for specifics.
Give Claude Code persistent cross-session memory with semantic search and project isolation.
Give Claude Code cross-session long-term memory with SQLite full-text search.
Give Claude Code persistent cross-device memory with semantic recall and self-maintenance.
Capture coding feedback and sync learned preferences into project memory files.
Add persistent database-backed memory to Claude Code.
Search past Claude Code chats to recover facts, decisions, and context.