alexsniffin

gpt_graph

A flexible pipeline library designed for fast prototyping, suitable for llm data processing

llama-agentic-system

Agentic components of the Llama Stack APIs

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

semantic-router

Superfast AI decision making and intelligent processing of multi-modal data.

open-parse

Improved file parsing for LLM’s

anole

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

fructose

phidata

Build AI Assistants with memory, knowledge and tools.

lyzr

Lyzr SDKs help you to build all your favorite GenAI SaaS products as enterprise applications in minutes.

julep

Open-source alternative to Assistant's API with a managed backend for memory, RAG, tools and tasks. ~Supabase for building AI agents.

composio

Composio equips agents with well-crafted tools empowering them to tackle complex tasks

langgraph

Build resilient language agents as graphs.

stable-diffusion.cpp

Stable Diffusion in pure C/C++

AutoRAG

RAG AutoML Tool - Find optimal RAG pipeline for your own data.

langgraph-example

llama2_chat_templater

Wrapper to easily generate the chat template for Llama2

burr

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

marker

Convert PDF to markdown quickly with high accuracy

surya

OCR, layout analysis, reading order, line detection in 90+ languages

cover-agent

CodiumAI Cover-Agent: An AI-Powered Tool for Automated Test Generation and Code Coverage Enhancement! 💻🤖🧪🐞

llama-cpp-python

Python bindings for llama.cpp

llama-3-quant-comparison

Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.

graph_maker

phoenix

AI Observability & Evaluation

transitions

A lightweight, object-oriented finite state machine implementation in Python with many extensions

hamilton

Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

pykka

🌀 Pykka makes it easier to build concurrent Python applications.

KRAGEN

Software to implement GoT with a weviate vectorized database

crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.