Search awesome repositories

Production-grade Rust-native trading engine with deterministic event-driven architecture

Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

No description.

Open-source data movement for ELT pipelines and AI agents — from APIs, databases & files to warehouses, lakes, and AI applications. Both self-hosted and Cloud.

🕵️‍♂️ Offensive Google framework.

The best free and open-source automated time tracker. Cross-platform, extensible, privacy-focused.

Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

GIT utilities -- repo summary, repl, changelog population, author commit percentages and more

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

The LLM Evaluation Framework

FinRL®: Financial Reinforcement Learning. 🔥

Simple, unified interface to multiple Generative AI providers

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

Alternative Twitter front-end

OCR & Document Extraction using vision models

the first library to let you embed a developer agent in your own app!

Synapse: Matrix homeserver written in Python/Twisted.

The open-source AIOps and alert management platform

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

An elegant PyTorch deep reinforcement learning library.

Official inference library for Mistral models

Open source annotation tool for machine learning practitioners.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

High-speed Large Language Model Serving for Local Deployment

highlight.io: The open source, full-stack monitoring platform. Error monitoring, session replay, logging, distributed tracing, and more.

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

🧙 Build, run, and manage data pipelines for integrating and transforming data.