cortexdb — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 liliang-cn · MCP Server · ★ 263

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is cortexdb safe to install? View the security audit →

About cortexdb

CortexDB AI memory and a knowledge graph in one SQLite file. Pure Go, no service to run, works without an embedding model. Install Use go db, := cortexdb.Open(cortexdb.DefaultConfig("brain.db")) defer db.Close() brain := db.KnowledgeMemory() , = brain.Remember(ctx, cortexdb.KnowledgeMemoryRememberRequest{Content: "Alice prefers tabs.", Scope: "user"}) rec, := brain.Recall(ctx, cortexdb.Knowledg

agent-memoryai-memoryclaude-codecodexembeddingsfull-text-searchgogolanggraphraghindsight

Quick Facts

Stars263
Forks6
LanguageGo
CategoryMCP Server
LicenseMIT
Quality Score66.088936507317/100
Last Updated2026-10-04
Created2025-08-07
Platformsclaude-code, codex, go, mcp
Est. Tokens~16k

Compatible Skills

These tools work well together with cortexdb for enhanced workflows:

  • mnemon — semantic(0.31)+complementary+same_lang+similar_pop+shared_platform (61%)
  • rekal-cli — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (60%)
  • skills — semantic(0.27)+complementary+shared_fw(openai)+similar_pop+shared_platform (57%)
  • memX — semantic(0.26)+complementary+shared_fw(openai)+similar_pop+shared_platform (57%)
  • lucid-memory — semantic(0.40)+complementary+shared_fw(openai)+similar_pop (57%)

cortexdb alternative? Top 6 similar tools

Looking for a cortexdb alternative? If you're comparing cortexdb 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.

  • Ori-Mnemos by aayoawoyemi · ⭐ 328

    Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

  • shodh-memory by varun29ankuS · ⭐ 295

    Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns

  • hermes-memory-installer by mage0535 · ⭐ 195

    🧠 Production-grade memory sidecar for AI agents — gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-

  • octocode by Muvon · ⭐ 477

    Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o

  • antigravity-workspace-template by study8677 · ⭐ 1.3k

    Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A wi

  • docsagent by docsagent · ⭐ 623

    ⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, A

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Go Agent Tools

Frequently Asked Questions

What is cortexdb?

cortexdb is AI memory and a knowledge graph in one SQLite file. Pure Go: vectors, RAG, agent memory, RDF/SPARQL, Cypher, 80+ MCP tools. Works without an embedding model.. It is categorized as a MCP Server with 263 GitHub stars.

What programming language is cortexdb written in?

cortexdb is primarily written in Go. It covers topics such as agent-memory, ai-memory, claude-code.

How do I install or use cortexdb?

You can find installation instructions and usage details in the cortexdb GitHub repository at github.com/liliang-cn/cortexdb. The project has 263 stars and 6 forks, indicating an active community.

What license does cortexdb use?

cortexdb is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to cortexdb?

The top alternatives to cortexdb on Agent Skills Hub include Ori-Mnemos, shodh-memory, hermes-memory-installer. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools