Memtrace Public

data-ai MCP Server

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · Hermes · VS Code · Windsurf.

VerifiedInstall Ready
data-aidata-ai
4 views184 stars14 forksNOASSERTION

Why This Matters

Discovered via github-topic:mcp-server and last synced 3mo ago.

VerifiedInstall Ready
Source
github-topic:mcp-server
Stars
184
Last synced
3mo ago
Install
Instructions detected

Install

1. Install the package

npx memtrace-skills install --only cursor --local

2. Add to claude_desktop_config.json

{
  "mcpServers": {
    "memtrace-public": {
      "command": "npx",
      "args": [
        "memtrace-public"
      ]
    }
  }
}

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)

54
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (54)

overview

Quick module-level summary

Skill

You say…

Kiro

`~/.kiro/settings/mcp.json` or `.kiro/settings/mcp.json`

Minimum

Recommended

Operation

Memtrace

compound

General-purpose "what changed?" — weighted blend of impact, novelty, recency

Agent

Global skills / guidance

impact

"What broke?" — ranks by blast radius (`in_degree^0.7 × (1 + out_degree)^0.3`)

novel

"What's unexpected?" — anomaly detection via surprise scoring

0

Exact-symbol lookup (1,000 queries, mempalace)

1

Token economy (same 1,000)

Yes

No

memtrace-codebase-exploration

_"I'm new to this project"_, _"give me an overview"_

2

Intent retrieval (100 NL PR titles, Django)

memtrace-change-impact-analysis

_"what will break if I refactor this"_

Bench

Primary axis

RSS

Tokens

383

90

Requirement

Minimum

3

Graph queries (Django, pyright GT)

No

BM25 + optional embeddings

memtrace-incident-investigation

_"something broke"_, _"root cause analysis"_

Tool

Coverage

Language

**Rust (compiled binary)**

memtrace-refactoring-guide

_"help me refactor"_, _"clean up tech debt"_

Runner-up

Δ

217

- **Coverage** = the tool returned any result for the query (separates "did you index it?" from "did you rank it well?") - **Acc@K** = the correct file appeared in the top K ranked results - **Avg latency** = wall-clock per query, including all protocol overhead (MCP JSON-RPC for Memtrace, HTTP for GitNexus, in-process for ChromaDB, subprocess spawn for CGC) - **Tokens** = average response size in tokens (chars / 4) **What the numbers say, read fairly:** - **Memtrace** holds rank-1 on 96.6% of queries with **128× lower latency** (0.07 ms vs GitNexus 8.95 ms), **1.18× tighter RSS** (26 MB vs 31 MB), and **1.38× higher precision@10** (0.97 vs 0.70). It ranks results by structural relevance — the canonical implementation comes first in one round-trip with the full agent envelope. - **GitNexus** wins by a 4-query margin on acc@1 because it ships raw enumeration order; memtrace re-orders by `direct_callers_count` so `Model.delete` precedes `tests.fake_delete`. Right tradeoff for agents, small benchmark cost. See [`BENCHMARKS-v0.3.22.md`](BENCHMARKS-v0.3.22.md) for the full reasoning. - **ChromaDB** shows what semantic embeddings look like for this workload — 87.8% top-10 but rank-1 is probabilistic, and the response is ~5× larger because it returns 800-char chunks rather than symbol metadata. Per-process RSS is 41× heavier (1,060 MB). - **CodeGrapherContext**'s 100% coverage of mempalace shows its FalkorDB-Lite parser works at small scale; latency is dominated by per-query subprocess spawn (2 s/query). It DNFs on Django (24+ min wall, no progress). **Where each tool shines** — the table above measures exact-symbol lookup only (Bench #0). Different workloads produce different rankings: ChromaDB wins Bench #2 (natural-language / intent retrieval), GitNexus has strong execution-flow traces, Memtrace wins exact lookup, graph queries (Bench #3), incremental freshness (Bench #4), token economy (Bench #1), plus capabilities no competitor has (bi-temporal memory, cross-service HTTP topology, typo tolerance via Levenshtein). See [`benchmarks/README.md`](benchmarks/README.md) for the full consolidated table and per-bench repro. <details> <summary><strong>Memtrace vs. general memory systems (Mem0, Graphiti)</strong></summary> <br/> Mem0 and Graphiti are strong conversational memory engines designed for tracking entity knowledge (e.g. `User -> Likes -> Apples`). They excel at that. For code intelligence specifically, the tradeoff is that they rely on LLM inference to build their graphs — which adds cost and time when processing thousands of source files. **Graphiti** processes data through `add_episode()`, which triggers multiple LLM calls per episode — entity extraction, relationship resolution, deduplication. At ~50 episodes/minute ([source](https://github.com/getzep/graphiti)), ingesting 1,500 code files takes **1–2 hours**. **Mem0** processes data through `client.add()`, which queues async LLM extraction and conflict resolution per memory item ([source](https://mem0.ai)). Bulk ingestion with `infer=True` (default) means every file passes through an LLM pipeline. Throughput is bounded by your LLM provider's rate limits. **Both** accumulate $10–50+ in API costs for large codebases because every relationship is inferred rather than parsed. **Memtrace takes a different approach:** it indexes 1,500 files in 1.2–1.8 seconds for $0.00 — no LLM calls, no API costs, no rate limits. Native Tree-sitter AST parsers resolve deterministic symbol references (`CALLS`, `IMPLEMENTS`, `IMPORTS`) locally. The tradeoff is that Memtrace is purpose-built for code — it doesn't handle conversational entity memory the way Mem0 and Graphiti do. </details> <details> <summary><strong>Memtrace vs. code graphers (GitNexus, CodeGrapherContext)</strong></summary> <br/> GitNexus and CodeGrapherContext both build AST-based code graphs with structural relationships — solid tools in the same space. Memtrace shares that foundation and extends it with temporal memory, API topology, and a Rust runtime:

NotSupported

613.7 ms

4

Incremental freshness (50 edits)

Memtrace

GitNexus

Mode

Best for

memtrace-relationships

"who calls this", "show class hierarchy"

Languages

**16+** (Tree-sitter)

memtrace-search

"find this function", "where is X defined"

memtrace-evolution

"what changed this week", "how did this evolve"

memtrace-impact

"what breaks if I change this", "blast radius"

memtrace-graph

"show me the architecture", "find bottlenecks"

memtrace-api-topology

"list API endpoints", "service dependencies"

memtrace-index

"index this project", "parse this codebase"

memtrace-cochange

"what else changes with this", "hidden coupling"

recent

"What changed near the incident?" — exponential time decay

directional

"What was added vs removed?" — asymmetric scoring

Windsurf

`~/.codeium/windsurf/mcp_config.json`

OpenCode

`~/.config/opencode/opencode.json` or project `opencode.json`

Codex

`~/.codex/config.toml` or `.codex/config.toml`

Hermes

`~/.hermes/config.yaml`

Editor

Config file

Cline

Cline MCP settings in the extension panel

CPU

4 cores

Memory

8 GB RAM

GPU

Not required

Git

Required for temporal analysis

memtrace-quality

"find dead code", "complexity hotspots"

Disk

5 GB free