Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
Open-source Agent Operating System
deep, reliable and confidential coding-context
A Go agent harness and service framework
Build resilient agents.
Claude Code's compaction engine, as a drop-in DeepAgents middleware
JavaScript in-page GUI agent. Control web interfaces with natural language.
Build effective agents using Model Context Protocol and simple workflow patterns
Markdown that runs — one file, any agent.
Mastra is the modern TypeScript framework for AI-powered applications and agents.
Astrid is a portable, capability-secure operating system for composable software.
AtlasClaw is an enterprise agent framework supporting mutliple users and multi system integration.
A Python framework for modular, self-contained skill management for machines.
LLM agents as your hyperparameter optimizer.
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
Unofficial Ruby SDK for Claude Agent
A Lisp with first-class LLM primitives, implemented in Rust
Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.
The agentic server framework.
A TypeScript SDK for implementing Model Context Protocol (MCP) over MQTT, supporting both browser and Node.js environments.
Go SDK for Anthropic Claude Code CLI – unofficial Claude Code Go agent SDK
Composable agent runtime with enforced isolation boundaries
The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
Local first, desktop companion platform with animated pets, plugin SDK and coding-agent integrations.