store_memoryLABSCO SUMMARY
Relationships are the point; a flat memory store would not answer these questions.
Because a solution is linked to the problem it solved and the technology it applies to, "has this failed before" and "what replaced this" become traversals rather than keyword searches. The project marks core memory operations as current work and the intelligence layer as still ahead, so treat the analytics tools as newer ground than storage.
What it is
A Python server backed by Neo4j that stores development memories — tasks, code patterns, problems, solutions, projects and technologies — along with the relationships between them.
What you get
- Memories stored, fetched, searched, updated and removed — store_memory, get_memory, search_memories, update_memory, delete_memory
- Memories linked to each other and traversed — create_relationship, get_related_memories, analyze_relationships
- Seven categories of relationship, from causal (CAUSES, TRIGGERS, LEADS_TO) through to quality (EFFECTIVE_FOR, PREFERRED_OVER, DEPRECATED_BY)
- A project scanned into a contextual memory graph — analyze_codebase
- Workflow recorded, analogous past solutions surfaced, and success estimated — track_task_execution, suggest_similar_solutions, predict_solution_effectiveness
- The knowledge network read back: get_memory_graph, find_memory_paths, memory_effectiveness
Requirements
Python 3.10 or higher and a Neo4j database, local or hosted. NEO4J_URI (default bolt://localhost:7687), NEO4J_USER (default neo4j) and NEO4J_PASSWORD; MEMORY_LOG_LEVEL is optional. Clone the repository, install it with pip install -e ., and copy .env.example to .env for the Neo4j settings.
Setup effort
Build from source — git clone https://github.com/ViralV00d00/claude-code-memory.git
USE CASES
01
Not solving the same problem twice
Search past memories for the situation you are in, then pull the solutions linked to it and how well each one worked.
02
Seeding the graph from a repository
Scan the project once to build a contextual graph of its conventions and dependencies, so later questions have something to traverse.
03
Recording why a decision was made
Store the decision as a memory and link it — SOLVES, REPLACES, DEPRECATED_BY — so the reasoning survives the conversation it happened in.
04
Tracing how two ideas connect
Find the chain of relationships between two memories, rather than reading each one and inferring the link yourself.
15 tools
Listed in project docs. Your client may show a different list.
get_memorysearch_memoriesupdate_memorydelete_memorycreate_relationshipget_related_memoriesanalyze_relationshipsanalyze_codebasetrack_task_executionsuggest_similar_solutionspredict_solution_effectivenessget_memory_graphfind_memory_pathsmemory_effectivenessBEFORE YOU INSTALL
What to know first
Tools you get
15 tools named in the project's documentation.
Requires
- Python 3.10 or later
- NEO4J_PASSWORD in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
This one is built from source rather than installed with a single command.
Server setup
TERMINAL
git clone https://github.com/ViralV00d00/claude-code-memory.git
cd claude-code-memory
pip install -e .
cp .env.example .envEdit .env with your Neo4j credentials
MCP Clients
Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"claude-memory": {
"command": "python",
"args": [
"-m",
"claude_memory.server"
],
"env": {
"NEO4J_URI": "bolt://localhost:7687",
"NEO4J_USER": "neo4j",
"NEO4J_PASSWORD": "<YOUR_NEO4J_PASSWORD>"
}
}
}
}
