Harness Books alternatives for AI agents.

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

Ground truth layer for humans and AI agents working together. Version control for knowledge.

Agent Package Manager

The agent that grows with you

OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.

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

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

Surface AI blindspots before you ship. Put up to 8 AI models on every research, design or coding task.

Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.

agent multiplexer that lives in your terminal.

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

Semantica 🧠 — AI-native knowledge graph intelligence framework for semantic retrieval, ontology reasoning, context graphs, and explainable AI systems.

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi, Pi, and Hermes in a local trace viewer.

Minimal AI coding agent (~1,400 LoC Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.