Claude Code Best Practice alternatives for AI agents.

A dev agent multiplexer for git worktrees and coding agents.

The agent that grows with you

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code

omo; the one and only agent harness for complex codebases. the pickaxe for complex software engineering. For your Codex, for your OpenCode

Lightweight, open-source AI agent for your tools, chats, and workflows.

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

The agent-native LLM router for OpenClaw. 41+ models, <1ms routing, USDC payments on Base & Solana via x402.

An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Memory library for building stateful agents

Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

🛠️ Awesome tools & guides for harness engineering.