Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.

SimpleMem: Efficient Lifelong Memory for LLM Agents

Build Real-Time Knowledge Graphs for AI Agents

Knowledge Engine for AI Agent Memory in 6 lines of code

Agentic orchestrator for parallel coding agents — plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.

Browser-native personal AI assistant. Zero infrastructure, the browser is the server.

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

Universal memory layer for AI Agents

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

sharing current agents in use

Public repository for Agent Skills

data load tool (dlt) is an open source Python library that makes data loading easy 🛠️

A massively parallel, high-level programming language

AIConfig is a config-based framework to build generative AI applications.

The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

Grok open release

Pyodide is a Python distribution for the browser and Node.js based on WebAssembly

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

AI code-writing assistant that understands data content

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

Build AI Agents, Visually

A new model-based algorithm for offline inverse reinforcement learning

A Pure Python, React-style Framework for Scaling Your Jupyter and Web Apps

A library for efficient similarity search and clustering of dense vectors.

Training platform for End-to-End compression models, losses and metrics defined in Compressai

A PyTorch library and evaluation platform for end-to-end compression research

Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.