Search awesome repositories

Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.

Python Classes Without Boilerplate

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Democratizing Reinforcement Learning for LLMs

Chronos: Pretrained Models for Time Series Forecasting

Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

PyTorch native post-training library

🐢 Open-Source Evaluation & Testing library for LLM Agents

A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

A visual playground for agentic workflows: Iterate over your agents 10x faster

Python module that makes working with XML feel like you are working with JSON

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

Create and modify Word documents with Python

It's not just a linter that annoys you!

OpenClaw-RL: Train any agent simply by talking

A PyTorch native platform for training generative AI models

Context Graph for AI Native SDLC

Gemma open-weight LLM library, from Google DeepMind

JSON Web Token implementation in Python

A programmable Mixture-of-Models router for heterogeneous LLM inference

A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.

Model interpretability and understanding for PyTorch

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Familiar asyncio ORM for python, built with relations in mind

An open, sub-millisecond, single-executable Firebase alternative with type-safe APIs, built-in WebAssembly runtime, realtime subscriptions, auth, MCP and admin UI built on Rust, SQLite (PG) & Wasmtime.

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.