AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

Abhay-J-Kashyap/Agentic-RAG-System

An open-source, fully local Agentic RAG system for Indian Law. Features LangGraph multi-agent orchestration, sequential tool-calling, and a DeBERTa NLI guardrail to eliminate LLM hallucinations on consumer-grade GPUs.

⚡ AI-using Python ⑂ 1 forks MIT GitHub ↗
★ 0
stars
75
AI relevance
50
solo dev
0
tool sigs

SUMMARY AI summary by gpt-5-mini

Local, multi-agent Retrieval-Augmented Generation (RAG) pipeline for Indian statutes (IPC, CrPC, MVA, CPC, IDA). Built to run offline on consumer GPUs, it targets two core problems in legal AI: LLM hallucinations and VRAM limits. Intended for legal practitioners, researchers, and developers needing accurate, explainable statutory retrieval and reasoning. Key features: - LangGraph multi-agent orchestration for iterative research and answer aggregation - DeBERTa Cross-Encoder NLI guardrail that scores contradictions to flag hallucinations - Sequential tool calling to avoid Vulkan/GPU OOMs - Parent-child chunking to preserve provisos and exceptions in retrieval - Qdrant vector DB, all-mpnet-base-v2 embeddings, Qwen 2.5 (7B) LLM, and a Gradio "glass-box" UI streaming agent actions.

DETECTED Detected AI stack

AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.

🧩 AI frameworks (1)
LangGraph
🤖 LLM models (1)
Qwen
🌐 Web frameworks (1)
Gradio

Language breakdown (by bytes)

Python
70%
Dockerfile
0.8%
Jupyter Notebook
29.2%

Owner

Account
Abhay-J-Kashyap
Type
User
Followers
0

Dates

Created on GitHub 2026-05-04
Last push 2026-05-09
First seen here 2026-05-09
Last fetched 2026-05-09 15:42

Similar repos (same language)

bgzhang1/sw2api

Reverse proxy for your ai quota from the SW platform.

Python 19 AI 45
dea6cat/2b-agent

This llm Agent was created based on necessity for one that could simply use local models without making them hallucinate and keep them focus

Python 1 AI 75
Zuboy/Carbon-Cost-Optimizer-Agentic-AI

An AI agent that decides where and when to run ML training jobs to minimize cost and carbon emissions, then launches them autonomously — exposed entirely through MCP tools.

Python 1 AI 75
FuchaZ/lm-studio-vision-bridge

给纯文本 AI agent 装上眼睛——通过 LM Studio 本地视觉模型提供 MCP 图片识别服务

Python 1 AI 45
Shrutirowlo/AI-Video-Agent

AI-powered video generation agent that automates script analysis, scene planning, and video creation.

Python 1 AI 75
Shivang0/social-vision

Paste an Instagram/TikTok/YouTube/X link and Claude watches it for you — transcribes audio, reads on-screen text & visuals, explains what it's about. Local, cross-platform Claude Code plugin.

Python 1 AI 70
markusbegerow/claude-fuer-oeffentliche-verwaltung

⚠️ Experimentelle Skill-Sammlung für Digitalisierung, Fachverfahren und Organisation der deutschen öffentlichen Verwaltung (OZG, FIM, FIT-Connect, KI-Einsatz, eIDAS, BSI-IT-Grundschutz, DSGVO) – bitte testen, Issues/PRs willkommen! Keine Rechts-/Datenschutzberatung, keine verbindliche Behördenentscheidung. Keine Bürger-/Mitarbeiterdaten im Repo.

Python 1 AI 75
knowledgegut/course-distiller

把有權使用的工作坊/課程回放消化成套品牌色的步驟式學習 PDF;最後的重組交還人腦。A Claude Code skill by 知識包小腸.

Python 1 AI 45