Astrid is a portable, capability-secure operating system for composable software.

Composable agent runtime with enforced isolation boundaries

Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents

Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

Markdown that runs — one file, any agent.

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

Open-source customer money path for usage-based SaaS — authorize customer spend before paid work runs.

55 framework-portable UI components for Astro, React, and Vue. Install accessible Tailwind CSS components as source you own, backed by a shared framework-neutral Runtime.

TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included.

Deterministic safety solutions for probabilistic AI agents

Universal memory runtime for AI agents

pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers into code that runs in secure sandboxes for token-efficient workflows.

Build and run agents you can see, understand and trust.

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

Apache Camel is an open source integration framework with 350+ connectors. Write routes in Java, YAML, or XML. Run on Spring Boot, Quarkus, or standalone. Apache License 2.0.

Deploy production-ready AI services in minutes. One YAML file for agents, RAG pipelines, and MCP servers — run anywhere. Inspired by docker-compose.

The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.

Build resilient agents.

AI agent microservice

A Lisp with first-class LLM primitives, implemented in Rust

🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source