workflowstacks
ai-agent

cortexdb: AI Knowledge Graph

Get a single-file AI memory library for Go. For founders building AI-powered startups.

From the repo · “A pure-Go, single-file AI memory and knowledge graph library and plugin.”

467 stars+36★ this week26 forksGoGuide quality 8/10 · reviewed Jul 30Updated 10/23/2026100% free · open source
What it does

Cortexdb is a lightweight, single-file Go library that enables creating and managing AI memory and knowledge graphs for building intelligent applications.

When to use it
  • •When building a chatbot or virtual assistant that requires a knowledge base
  • •When creating a recommender system that relies on graph-based relationships
  • •When developing an AI-powered application that needs to store and query complex data relationships
Ready-to-paste prompt
Create a knowledge graph with entities and relations: `db.InsertEntity(cortexdb.Entity{ID: "1", Type: "Person", Properties: map[string]string{"name": "John"}})`
Heads up: Cortexdb requires Go version 1.17 or later to work correctly, so ensure your Go environment is up-to-date before using the library
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/cortexdb && curl -fsSL https://workflowstacks.com/api/skills/cortexdb/claude-skill -o ~/.claude/skills/cortexdb/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How cortexdb: AI Knowledge Graph works
Codeflow
Free to inspect

Cortexdb: AI Knowledge Graph is a very large Go project (~270k lines across 1136 code files, plus 15 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~270k lines · 1136 code files · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 5 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Go
Go 95%JavaScript 2%Rust 1%Python 1%TypeScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    SKILL.md
    The instructions the AI actually follows
  3. 3
    cmd/cortexdb-grpc/main.go
    Where the program starts running
  4. 4
    pkg/agentmem/agentmem_test.go
    Inside pkg/ — the main logic begins here
  5. 5
    examples/01_core/main.go
    A worked example — copy this to get going
What's in each folder
pkg/Core code — the actual logic1313 files
internal/Core code — the actual logic6 files
skills/Prompts, skills & agent definitions6 files
cmd/Command-line entry points76 files
plugins/Sub-packages / plugins75 files
docs/Documentation52 files
examples/Examples you can copy39 files
clients/SDKs / client libraries66 files
READMEHas testsDocumentedCI checksExamples includedMIT licenseUpdated this month
Quick Actions
Details
Creator
liliang-cn
Language
Go
Category
ai-agent
Published
8/7/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/cortexdb.svg)](https://workflowstacks.com/skills/cortexdb?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 303,974
superpowers
An agentic skills framework & software development methodology that works.
ai-agent★ 277,160
Track GitHub Stars with 996.ICU
Get a popular GitHub star counter for your startup, backed by 276k+ GitHub stars, ideal for founders.
ai-agent★ 253,255
Linux – 251k+ GitHub stars for building custom kernel solutions
Get the complete Linux kernel source in C, perfect for founders needing deep system control or tailored OS components.
ai-agent★ 1,268
Gym
Evaluate and improve models and agents using environments
ai-agent★ 91,633
OpenHands: Accelerate AI‑Powered Development for Founder Teams
Leverage OpenHands to build, test, and iterate AI agents with a single CLI, letting tech founders prototype smarter tools faster. 90k+ GitHub stars.
ai-agent★ 8,115
lmdeploy: Accelerate LLM Compression and Deployment
Scale your AI stack fast—lmdeploy lets founders compress, deploy, and serve large language models in Python with 8.1k+ GitHub stars. Ideal for teams building AI agents.