AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Memory & Context/
memtrace-public
memtrace-public logo

memtrace-public

Active·★ 504·NOASSERTION·Updated 2026-10-22
★ Trending

Memtrace is a persistent memory layer for coding agents. It builds a bi-temporal, episodic, structural knowledge graph from your codebase's AST, enabling agents to remember and reason about code structure, evolution, and dependencies. It runs entirely locally, indexing code in seconds and providing sub-millisecond query latency.

memtrace-public sits in the Memory & Context category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward AST-based structural knowledge graph. A representative use case is Codebase exploration and understanding. The listed license is NOASSERTION. GitHub stars are currently 504. Relevant tags include ai-agents, code-intelligence.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#ai-agents#code-intelligence#code-search#coding-agents#developer-tools#knowledge-graph#local-first#mcp
$ Install
$ npm install -g memtrace && memtrace start
↗ Visit site★ GitHub
01

Features

01AST-based structural knowledge graph
02Bi-temporal version history with 6 scoring modes
03Cross-service HTTP API topology
04Hybrid search (BM25 + vector embeddings + RRF)
0525+ MCP tools and 12 agent skills
02

Why choose it

+AST-based structural knowledge graph
+Bi-temporal version history with 6 scoring modes
+Codebase exploration and understanding
+Supports 8 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Claude Code
Claude Code
Verified via docs
Claude Desktop
Claude Desktop
Verified via docs
Cursor
Cursor
Verified via docs
Windsurf
Windsurf
Verified via docs
VS Code (Copilot)
VS Code (Copilot)
Verified via docs
Cline / Roo Code
Cline / Roo Code
Verified via docs
05

Quick start

1
$ npm install -g memtrace
2
$ memtrace start
06

Use cases

↳Codebase exploration and understanding
↳Change impact and refactoring analysis
↳Incident investigation and root cause analysis
07

Alternatives

⚡Top VS:
VSsverklo★82→VSneurostack★47→VSopen-ontologies★1.2k→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases
VS
trace-mcp
★193
→
sverklo logo
sverklo★ 82
The local-first MCP server for code intelligence — symbol graph, blast-radius, git-pinned memory. Open-source alternative to Greptile/Sourcegraph for Claude Code & Cursor.
VSCompare→
neurostack logo
neurostack★ 47
Your second brain, starting today. CLI + MCP server that helps you build, maintain, and search a knowledge vault that gets better every day. Works with any AI provider. Local-first, zero-prereq install.
VSCompare→
open-ontologies logo
open-ontologies★ 1.2k
AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL tableaux reasoner, SHACL validation, SPARQL, versioning. Single binary, no JVM.
VSCompare→
trace-mcp logo
trace-mcp★ 193
Framework-aware code intelligence MCP server — 81 languages, 58 framework integrations, 138 tools, up to 99% token reduction
VSCompare→
Ori-Mnemos logo
Ori-Mnemos★ 333
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
VSCompare→
AgentRecall-MCP logo
AgentRecall-MCP★ 371
Persistent, correction-driven memory for AI agents. Cross-session, cross-platform (Claude Code, Codex, Gemini — any MCP client). Learns from mistakes, compresses context to save tokens, consolidates knowledge overnight. npm: agent-recall-mcp
VSCompare→
AgentRecall logo
AgentRecall★ 371
AI Session Memory with Think-Execute-Reflect Quality Loops — give your agent a brain that survives every session. Built on the Intelligent Distance principle.
VSCompare→
YourMemory logo
YourMemory★ 270
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
VSCompare→
See all alternatives →
07
Alternatives
syncable-dev /
memtrace-public
↗

The missing memory layer for coding agents

504
Last commit1d ago
StatusActive
CategoryMemory & Context
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit