agent-runtime

The Semantic Intelligence Layer

Search, understand, reproduce, and improve an idea with ease

AuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery.

Secure and persistent computer for AI agents -- build your own Grokbot, and Muse.

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

Self-hosted AI Agents Platform supporting Claude Code, Codex, Gemini agents. Apache 2.0.

Reconcile stuck AI-agent tasks after restarts and timeouts. Preview SQLite changes, close stale delivery states, and never guess success.

Deterministic safety solutions for probabilistic AI agents

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

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.

Run your own organization of agents

Parallel ai-agent sessions in one panel, with permission-aware tools, preflight conflict checks.

Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evolution.

OpenClaw + 大模型驱动的完整电商客服自动化系统：覆盖淘宝、拼多多、抖音、快手、小红书、视频号，包含浏览器/手机 Worker、订单物流与售后工具、记忆、回执、恢复和 Eval。

A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it.

A minimal, readable agent-framework kernel — understand how LangGraph/ADK work under the hood. 1800行代码的 agent 框架内核，理解 LangGraph/ADK 底层的工作原理

OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable system — designed for building real, production-grade AI applications.

Minimal agent runtime built with DSPy modules and a thin Python loop. Includes CLI, FastAPI server, and eval harness with OpenAI/Ollama support.

Memory, working state, heartbeat, and bounded autonomy for long-running AI agents.