Composable agent runtime with enforced isolation boundaries

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.

Agentic personal OS to automate high-leverage workflows with Codex, Claude Code, Pi, OpenClaw and other coding agents/ runtime platforms.

YouTube Transcript API skills for AI agents. Get transcripts, search videos, browse channels. Works with OpenClaw, Hermes Agent, and other agent runtimes.

lnwjud — local AI-agent runtime & MCP gateway

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

A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Coding Agent, Tmux alternative

Agent skills for coding CLIs, multi-agent runtimes, context engines, MCP extensions, and terminal tooling. Instead of using claude code's source code, give your agent skills to create your own!

See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.

Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistral/Koyeb — works with any LLM.

Markdown that runs — one file, any agent.

Deterministic safety solutions for probabilistic AI agents

Remote approvals, policy checks, and execution evidence for unattended AI agents.

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

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.