The Claw Ecosystem Map

A personal autonomous AI companion maintained by Warengonzaga, recorded with provider attribution so it is not conflated with the former TinyClaw project now named TinyAGI.

An OpenClaw-based personal assistant configuration focused on running well with small local models through Ollama, LM Studio, and compatible inference servers.

A personal AI agent framework for autonomous aerial systems that composes flight, navigation, perception, memory, and evolving skills during live drone missions.

A Rust agentic assistant runtime inspired by several OpenClaw-style projects, with extensible model backends, channels, embeddings, and local-model support.

An agent-team orchestrator for one-person companies, formerly named TinyClaw; it is cataloged under its current name to avoid confusing it with the separate TinyClaw project.

An early Claw-branded project from Xpose Market whose public repository does not yet document enough persistent-agent behavior for inclusion in the verified Claw directory.

An experimental minimal Rust implementation inspired by OpenClaw, listed as an early runtime project while its agent capabilities receive further verification.

An experimental C rewrite of OpenClaw targeting a very small static binary and fast startup; the public repository currently provides limited documentation.

A managed platform for deploying and running OpenClaw, Hermes Agent, Claude Code, and Codex with one-click setup, 24/7 uptime, integrations, backups, and model choice.

Xiaomi’s cloud-based Claw product, designed for continuous operation and optimized for compatibility with the OpenClaw framework.

Qyclaw is an open-source multi-tenant AI agent task platform designed as a 'platformized agent operating system' with layered architecture for users, sessions, skills, and secure sandboxed tool execution.

KiloClaw is a fully-managed, one-click hosted version of the popular open-source OpenClaw AI agent. Deploy a proactive 24/7 AI assistant that reads emails, manages calendars, controls browsers, runs shell commands, and integrates with your favorite chat platforms—in under 60 seconds.

Official OpenClaw plugin for CamoFox Browser — adds powerful anti-detection web browsing capabilities to OpenClaw agents using the Camoufox engine with C++-level fingerprint spoofing.

ClawTip is JD Technology's pioneering A2A micro-payment infrastructure that empowers AI agents to autonomously discover services, negotiate prices, make secure small-amount payments, and complete transactions without human intervention.

Hermes Agent is a self-improving, autonomous AI agent that lives on your server, creates and refines its own skills from experience, remembers past conversations, and grows more capable over time.

Vidu Claw is an OpenClaw-powered AI Marketing Agent that transforms simple goals into complete marketing videos and social content through intelligent planning and multimodal generation.

Pi is a minimal, open-source terminal coding agent designed to be customized around a developer's workflow. It combines multi-model support, local coding tools, Agent Skills, TypeScript extensions, tree-structured sessions, and programmatic SDK/RPC modes without forcing heavyweight agent abstractions into the core.

MotiClaw is a local-first desktop control platform for building and managing teams of AI partners and agents. It centralizes agent onboarding, tasks, runtime status, configuration, messaging channels, maintenance, and usage monitoring while keeping work data on the user's device by default.

An on-device persistent memory layer for OpenClaw, Hermes Agent, and Claude Code using hooks, MCP, local embeddings, SQLite, and hybrid retrieval.

OpenFang is an open-source Agent Operating System built in Rust for running persistent, autonomous AI agents. It combines agent scheduling, tools, memory, messaging integrations, MCP/A2A interoperability, security controls, and a web dashboard in a single runtime.

NVIDIA NemoClaw is an open-source stack that adds privacy and security controls to OpenClaw, enabling the deployment of more secure, always-on AI assistants with a single command.

An end-to-end benchmark for autonomous scientific research agents, covering real datasets, code, figures, reports, and peer-review-style evaluation across multiple disciplines.

A benchmark for always-on personal assistants that measures long-horizon event understanding, interconnected digital services, and cross-device GUI and CLI interaction.

An open-source toolkit for generating, executing, and grading environments for Claw-like agents, paired with the Auto-ClawEval benchmark of 1,040 environments across 24 categories.

A benchmark for comparing heterogeneous agent harnesses—described by the authors as claws—on coding tasks under controlled settings.