[PR #804] [CLOSED] Add local Graph-RAG with visualized ontology, security, self-evolution #10270

New Issue

GiteaMirror · 2026-06-12T10:51:44-05:00

GiteaMirror commented

2026-06-12 10:51:44 -05:00

📋 Pull Request Information

Original PR: https://github.com/Shubhamsaboo/awesome-llm-apps/pull/804
Author: @Hashevolution
Created: 5/12/2026
Status: ❌ Closed

Base: main ← Head: patch-1

📝 Commits (1)

ed5b845 Add local Graph-RAG with visualized ontology, security, self-evolution

📊 Changes

1 file changed (+1 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)

📄 Description

Summary

Adds PROJECT JAMES to the 📀 RAG section as an external standalone project.

PROJECT JAMES (https://github.com/Hashevolution/James-RAG-Evol) is a security-focused, locally-runnable Graph-RAG knowledge engine in Python, MIT-licensed.

What it offers

Graph-RAG with 12-type ontology — relations carry semantic meaning beyond embeddings
3-stage security: RBAC + ABAC + instruction isolation (vector → graph → output filter)
Self-evolution scaffold: feedback signals → patch proposals → 4-Gate validation → auto-rollback on bench regression
100% local via Ollama (no cloud LLM dependency)
Explicit reasoning paths surfaced in every response

Project status

Current version: v0.2.0 (Foundation Hardening, 5/6 axes engineering-complete, 2026-05-08)
License: MIT
External validation: OpenSSF Best Practices passing badge (Tiered 111%, 2026-05-11)
7 published GitHub Releases through v0.2.0

Format

Follows the existing external-entry convention used by Openwork:

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/Shubhamsaboo/awesome-llm-apps/pull/804 **Author:** [@Hashevolution](https://github.com/Hashevolution) **Created:** 5/12/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `patch-1` --- ### 📝 Commits (1) - [`ed5b845`](https://github.com/Shubhamsaboo/awesome-llm-apps/commit/ed5b84556f62f6e77b5f2e27627eaa1706cc4dff) Add local Graph-RAG with visualized ontology, security, self-evolution ### 📊 Changes **1 file changed** (+1 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) </details> ### 📄 Description ## Summary Adds PROJECT JAMES to the 📀 RAG section as an external standalone project. **PROJECT JAMES** (https://github.com/Hashevolution/James-RAG-Evol) is a security-focused, locally-runnable Graph-RAG knowledge engine in Python, MIT-licensed. ## What it offers - **Graph-RAG with 12-type ontology** — relations carry semantic meaning beyond embeddings - **3-stage security**: RBAC + ABAC + instruction isolation (vector → graph → output filter) - **Self-evolution scaffold**: feedback signals → patch proposals → 4-Gate validation → auto-rollback on bench regression - **100% local** via Ollama (no cloud LLM dependency) - **Explicit reasoning paths** surfaced in every response ## Project status - Current version: v0.2.0 (Foundation Hardening, 5/6 axes engineering-complete, 2026-05-08) - License: MIT - External validation: [OpenSSF Best Practices **passing** badge](https://www.bestpractices.dev/projects/12806) (Tiered 111%, 2026-05-11) - 7 published GitHub Releases through v0.2.0 ## Format Follows the existing external-entry convention used by `Openwork`: --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

GiteaMirror added the pull-request label 2026-06-12 10:51:44 -05:00

GiteaMirror closed this issue

2026-06-12 10:51:45 -05:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/awesome-llm-apps#10270