Skip to content
Back to the index

cortex-kg

PyPIInfrastructure

PulseGate's liveness check found it on 14 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 22 Jul 2026. How this is checked

Cortex provides a persistent, workspace-level Engineering Knowledge Graph designed for AI coding tools and local-first RAG applications. It captures and organizes engineering knowledge across projects, enabling better context for AI agents and coding assistants like Cursor. The package includes MCP server capabilities for seamless integration with development environments.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

4 features

Purpose: Maintaining persistent, workspace-level engineering knowledge for AI coding assistants and RAG systems.

Inferred · not functionally tested

Audience: developers

Inferred · not functionally tested

Functions: rag, agents

Inferred · not functionally tested

Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

cortex-kg is a RAG, search & retrieval project. Inferred · not functionally tested: It focuses on maintaining persistent, workspace-level engineering knowledge for AI coding assistants and RAG systems. Inferred · not functionally tested: cortex-kg is an open-source project aimed at developers. Basis unknown · not verified: cortex-kg is open source under the MIT license. Basis unknown · not verified: cortex-kg is available on the command line, and it can be self-hosted.

Roshan Gamage builds and maintains cortex-kg, and it first shipped in 2026. Inferred · not functionally tested: Key capabilities include Knowledge Graph, Local-first Storage, and RAG Integration. Basis unknown · not verified: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Knowledge Graph
  • Local-first Storage
  • RAG Integration
  • Engineering Context

Topics: Inferred · not functionally tested

Tags
engineering-knowledge-graphlocal-ragworkspace-contextmcp-server
AI capabilities
Structured
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

Connectors
MCP
Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed22 Jul · 17:37 UTC
    cortex-kg seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about cortex-kg

What is cortex-kg?
Inferred · not functionally tested: Cortex-kg focuses on maintaining persistent, workspace-level engineering knowledge for AI coding assistants and RAG systems. It is catalogued under RAG, search & retrieval on PulseGate.
Who is cortex-kg for?
Inferred · not functionally tested: cortex-kg is an open-source project built for developers.
Does cortex-kg have a free plan?
Basis unknown · not verified: Yes — cortex-kg is open source under the MIT license and free to use.
What platforms does cortex-kg run on?
Basis unknown · not verified: cortex-kg runs on the command line. It can also be self-hosted.
Is cortex-kg still active?
PulseGate's liveness check found it on 14 Sep 2026.
What are alternatives to cortex-kg?
Similar projects tracked by PulseGate include Kortex, cortexe, and cortexctl.Kortexcortexecortexctl
Who develops cortex-kg?
cortex-kg is developed by Roshan Gamage.
How long has cortex-kg been around?
cortex-kg first shipped in 2026.

Similar projects

Closest matches by what these projects do