llm

Memory architectures that evolve with your agent

CLI, MCP server, and TypeScript library that extracts text, layout, and page images from PDFs for AI agents — when extraction goes wrong, it says so per page and says what to do next.

EgoNormia | Benchmarking Physical Social Norm Understanding in VLMs

A Multimodal Discord bot with machine learning functions, including LLM chat, Image generation, and Speech Generation capabilities

Context Runtime — a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused substrate, and learns from the outcome.

A curated list of papers, benchmarks, project pages, and code for proactive agents.

Create a supercut montage video with Gemini LLM

AI-powered fashion visual search and personalized styling assistant using CLIP, FAISS, and Gemma-3B in Streamlit. Search visually similar fashion items, simulate user history, and generate outfit suggestions using LLMs.

Enterprise multi-source RAG platform with multimodal embedding, hybrid vector/BM25 retrieval, MCP & RBAC support

Batch LLM Inference with Ray Data LLM: From Simple to Advanced

LLM inference engine built from scratch in C++. No PyTorch, no frameworks.

vLLM tool parser for Qwen2.5-Coder models using <tools> tag format.

Benchmark OpenAI-compatible AI endpoints and AI Accelerators in a reproducible structured way

Collection of ChatGPT alternatives & LLM tuning methods

Fine-tune GPT2 to generate fake job experiences

AgriMind: The smart LLM application that every farmer truly needs

This is the unofficial re-implementation of "Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack" (ICML2025)

[ICML 2025] Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

🧪 SynthForge — toolkit for generating high-quality synthetic datasets for LLM fine-tuning. Multi-backend, filterable, GPU-accelerated. Early-stage experimental project.

Fine tuning Mistral-7b with PEFT(Parameter Efficient Fine-Tuning) and LoRA(Low-Rank Adaptation) on Puffin Dataset(multi-turn conversations between GPT-4 and real humans)