analyze_file
Returns forensic history, hidden dependencies, and risk assessment. USE THIS before modifying files.
LABSCO SUMMARY
extract_memories is the idea worth stealing: the warnings were already written, in comments, and nobody was reading them as memory.
Every codebase has a layer of HACK, WARNING and TODO comments left by people who knew something the code does not say. Treating those as a retrievable memory store, rather than as decoration a linter ignores, gets value out of work that has already been done — no adoption cost, no discipline required from the team. The rest of the surface is a familiar shape done thoughtfully: history search for intent, context before a write, lessons after one. Note that ask_history's own description tells you it needs short specific keywords, which is an admission that the search is keyword matching and not semantic — worth knowing before an agent asks it a sentence-shaped question and reads the empty result as an absence of history.
What it is
A code-memory server in two halves: forensics over the repository's own history, and a store of lessons an agent writes for its successors. Six tools covering file analysis, history search, context retrieval, lesson capture, comment extraction and search.
What you get
- analyze_file returns forensic history, hidden dependencies and a risk assessment, and its description places it before modifying a file rather than after.
- ask_history searches git history for why code was written, with the tool itself warning that short specific keywords work and long queries do not.
- get_context returns the memories and code-graph relationships relevant to a file before it is touched.
- save_lesson stores a decision or a discovery for future sessions — the write side of the same loop.
- extract_memories harvests what is already in the code: IMPORTANT, WARNING, HACK and TODO comments that were written as notes to a human and never read as data.
- search_memories retrieves them with BM25 keyword matching.
Requirements
Nothing to supply for the local path. Some behaviour changes when a cloud backend is configured, which extract_memories notes in its own description.
Setup effort
One command — npm install -g @byronwade/memoria
USE CASES
01
Working out why something is the way it is before you change it
Search history for the intent behind the code, and read the file's forensic history, dependencies and risk assessment first.
02
Getting at the warnings already in the codebase
Extract the IMPORTANT, WARNING, HACK and TODO comments as searchable memory, then query them when a related file comes up.
03
Leaving something behind for the next session
Save the decision or the dead end you just found, so the next agent starts from it instead of rediscovering it.
6 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
ask_history
Search git history for WHY code was written. IMPORTANT: Use SHORT, SPECIFIC KEYWORDS (e.g., 'serialization', 'race condition', 'timeout'). Do NOT use full sentences or long descriptions - they will return 0 results. Use when asking 'why does this exist?' or before removing code.
extract_memories
Extract memories from code comments (IMPORTANT, WARNING, HACK, TODO, etc.). When cloud is configured, automatically saves high-confidence (>=70%) memories. Use to find and capture implicit knowledge in code.
get_context
Get relevant memories and context before modifying a file. Returns memories, code graph relationships, and recent high-risk commits. Auto-saves critical discoveries when cloud is configured.
save_lesson
Save a lesson, context, or decision for future AI sessions. Use this when you discover important context that should be remembered.
search_memories
Search extracted memories using BM25 keyword matching. FREE feature. Find relevant context from code comments using natural language queries.
BEFORE YOU INSTALL
What to know first
Tools you get
6 tools when we connected. Only analyze_file and ask_history are documented; extract_memories, get_context, save_lesson and search_memories are available but undocumented.
Requires
- npx on PATH
- Node.js 18+
CONTEXT COST
Light Standing cost
Rated by the size of the 6 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install -g @byronwade/memoriaMCP Clients
Claude Desktop, Cursor, Cline, Windsurf
JSON
{
"mcpServers": {
"memoria": {
"command": "npx",
"args": [
"-y",
"@byronwade/memoria"
]
}
}
}VS Code
VS CODE · JSON
{
"servers": {
"memoria": {
"command": "npx",
"args": [
"-y",
"@byronwade/memoria"
]
}
}
}Claude Code
CLAUDE CODE · TERMINAL
claude mcp add memoria -- npx -y @byronwade/memoriaContinue
CONTINUE · JSON
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@byronwade/memoria"
]
}
}
]
}
}
