Pixelize the real world on-chain

Open-source Agent Operating System
A chatbot implementation compatible with MCP (terminal / streamlit supported)
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Compound Engineering Framework for Alpha Feature Research in Quant Finance
Qt C++ library for working with AI/LLM Providers and MCP
Build effective agents using Model Context Protocol and simple workflow patterns
AI agent microservice
AI said it finished. Flyto2 shows the proof.
A framework for discovering, compiling, and validating reusable skills for scientific agents.
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.
A Python library for building AI agents that leverage the full power of Google Antigravity.
The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.
Open source version of Claude Managed Agents. Fastest way to build and deploy reliable AI agents, MCP tools and agent-to-agent.
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.

Universal memory runtime for AI agents
Poirot is a deep research agent kernel built for those who care about how agents are architected.
Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Umbrella package for SciTeX — reproducible science from raw data to manuscript
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
🔬 A Researcher&Agent-Friendly Framework for Time Series Analysis. Train Any Model on Any Dataset!