No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by 0xK3vin · MCP Server · ★ 709
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is MegaMemory safe to install? View the security audit →
MegaMemory Persistent project knowledge graph for coding agents. An MCP server that lets your coding agent build and query a graph of concepts, architecture, and decisions — so it remembers across sessions. The LLM is the indexer. No AST parsing. No static analysis. Your agent reads code, writes concepts in its own words, and queries them before future tasks. The graph stores concepts — features, modules, patterns, decisions — not code symbols. The Loop understand → work → upda
| Stars | 709 |
| Forks | 75 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 70.0423197380954/100 |
| Open Issues | 4 |
| Last Updated | 2026-05-03 |
| Created | 2026-02-06 |
| Platforms | browser, claude-code, mcp, node |
| Est. Tokens | ~43k |
These tools work well together with MegaMemory for enhanced workflows:
Looking for a MegaMemory alternative? If you're comparing MegaMemory with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o
Persistent memory for AI coding agents
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured
Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr
Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Disco
Explore other popular mcp server tools:
MegaMemory is Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.. It is categorized as a MCP Server with 709 GitHub stars.
MegaMemory is primarily written in TypeScript. It covers topics such as agentic-coding, ai, ai-agents.
You can find installation instructions and usage details in the MegaMemory GitHub repository at github.com/0xK3vin/MegaMemory. The project has 709 stars and 75 forks, indicating an active community.
MegaMemory is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to MegaMemory on Agent Skills Hub include Ori-Mnemos, octocode, omega-memory. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: