Astrid is a portable, capability-secure operating system for composable software.
-
Updated
Jul 18, 2026 - Rust
Astrid is a portable, capability-secure operating system for composable software.
Multi-Agent Framework
The agent that remembers and learns.
Search, understand, reproduce, and improve an idea with ease
Enterprise audit agent workspace with Agentic RAG, governed tool use, evaluation harness, memory, and human-review delivery workflows.
The foundation layer for agentic intelligence.
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
Agents daemon that hides nothing
Open-source AI sandbox infrastructure with unified API for VMMs -- Firecracker, QEMU and libkrun.
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.
ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers
Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.
Deterministic safety solutions for probabilistic AI agents
Self-hosted Personal AI + agent runtime in .NET (NativeAOT-friendly)
Every project gets its own persistent AI agent runtime. Open source, self-hosted, and shared across Desktop, CLI, bots, and apps.
The agent-native OS for companies.
Clouds Coder is a local-first coding agent platform centered on separating the CLI execution plane from the Web user plane, with Web UI, Skills Studio, resilient streaming, and long-task recovery controls.
AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.
Model-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible / Anthropic-compatible model API. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills,and local code search.
Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.
Add a description, image, and links to the agent-runtime topic page so that developers can more easily learn about it.
To associate your repository with the agent-runtime topic, visit your repo's landing page and select "manage topics."