What is hexstrike_augment?

clutch-61/hexstrike_augment — explained in plain English

Analysis updated 2026-05-18

★ 34PythonAudience · researcherComplexity · 4/5Setup · hard

Mindmap

mindmap
  root((hexstrike augment))
    What it does
      Local Ollama MCP client
      Security testing tools
      Knowledge base search
      Multi agent task planning
    Tech stack
      Python
      Ollama
      ChromaDB
      Qdrant
    Use cases
      Authorized pentest assistance
      Vulnerability knowledge search
      Automated task breakdown
    Audience
      Security researchers
      Authorized testers

mindmap root((hexstrike augment)) What it does Local Ollama MCP client Security testing tools Knowledge base search Multi agent task planning Tech stack Python Ollama ChromaDB Qdrant Use cases Authorized pentest assistance Vulnerability knowledge search Automated task breakdown Audience Security researchers Authorized testers

What do people build with it?

USE CASE 1

Ask a local Ollama model to help plan and carry out an authorized penetration test using built in security tools.

USE CASE 2

Search a vulnerability and security knowledge base using keyword, vector, or hybrid retrieval.

USE CASE 3

Let a multi-agent planner break a security research task into steps and pick the right tools automatically.

What is it built with?

PythonOllamaChromaDBQdrantMCP

How does it compare?

	clutch-61/hexstrike_augment	abhisumatk/epstein_files_rag	asdfo123/forgewm
Stars	34	34	34
Language	Python	Python	Python
Setup difficulty	hard	moderate	hard
Complexity	4/5	3/5	5/5
Audience	researcher	researcher	researcher

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1h+

Needs a local Ollama install with a tool-calling model, git submodules, and optionally a Qdrant database for the full RAG pipeline.

No project-specific license stated, terms follow the upstream ollmcp project and each included submodule or dependency.

So what is it?

HexStrike Augment builds on top of an existing open-source MCP client for Ollama, combining security testing automation, two retrieval-augmented search systems, and a multi-agent workflow layer. It is designed for authorized security research and penetration testing assistance, running entirely with local language models via Ollama rather than cloud APIs. The README is written in Chinese. The security testing components come from a submodule called hexstrike-ai, which provides a collection of tools for tasks such as vulnerability analysis. The retrieval-augmented search layer runs in two configurations: a lighter one using ChromaDB with Ollama-generated embeddings, and a more complete pipeline that adds BM25 keyword search, vector search, and result re-ranking, with optional Qdrant support for production use. A multi-agent mode, activated by typing "ma" in the chat interface, uses a three-layer design: a Strategy agent that breaks down a task, a Selector that chooses relevant tools, and an Executor that carries out the steps. The README states this approach reduces token usage by avoiding loading tools that are not relevant to the current task. Setup requires Python 3.10 or newer and a local Ollama installation with a model that supports tool calling, such as qwen3. Configuration is handled through JSON files copied from provided example templates, with the repository's absolute path filled in by the user. Qdrant and Redis are optional and only needed for the full retrieval pipeline. The project includes a prominent notice that it is intended for authorized security testing and security research only, and users should not direct its scanning capabilities at systems they do not have permission to test.

Copy-paste prompts

Prompt 1

Walk me through cloning hexstrike_augment with its submodules and setting up the example config files.

Prompt 2

Explain the difference between the Chroma RAG knowledge base and the hexstrike-rag pipeline in this project.

Prompt 3

How do the Strategy, Selector, and Executor agents divide up work in the multi-agent mode?

Prompt 4

What do I need installed locally, including Ollama models, to run this project's mock mode?

Frequently asked questions