Composable agent runtime with enforced isolation boundaries

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

A runtime-free MCP server that converts source code into AST🌲, regardless of language.

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

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

Collective intelligence runtime for AI agents. Knowledge graph + persistent memory.

the runtime your coding agents live on

ClawGod is a runtime patch applied to the official Claude Code. It continues to be supported with each version update.

Universal skill installer and package manager for AI coding agents. One command, 12+ runtimes. npx ai-agent-skills

Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.

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

Universal memory runtime for AI agents

An MCP server that allows users to dynamically add custom tools/functions at runtime

lnwjud — local AI-agent runtime & MCP gateway

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

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.

Governance runtime for Claude Code. Enforces workflow gates at tool time, delivers the engineering rules relevant to the work, and preserves decision provenance across sessions.

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP

AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perception of web & desktop applications.

Orchestrate AI coding agents (Claude Code, Codex) as parallel subagents over tmux — a loop-engineering runtime with auto-continue, execute-then-review, and cross-session memory.

50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.

Deterministic safety solutions for probabilistic AI agents

Deno skills for AI coding assistants. Covers using Deno as a package manager and runtime, migrating from npm/yarn/pnpm/bun, Fresh, and Deno Deploy.

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.