NanoClaw

OpenClaw is a self-hosted AI assistant and agent platform developed by the OpenClaw Foundation. It runs on macOS, Linux, Windows, or WSL2 devices and connects hosted or local model providers, tools, skills, plugins, messaging channels, and optional companion apps through a Gateway. The same Gateway architecture supports a personal assistant on one device or a trusted shared-team deployment. The Gateway is the local control plane for sessions, tools, events, and channel connections; the Control UI, CLI, and terminal UI connect to it. Channels include WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, and iMessage, while companion apps and nodes can provide voice, Canvas, camera, screen, and device-local actions on supported platforms. OpenClaw’s security model treats inbound messages as untrusted input, pairs unknown senders by default on direct-message-capable channels, and runs tools on the host for the main session unless sandboxing is configured. The project is distributed under the MIT license.

An SDK for building AI agents that can operate beyond a standard chatbot. The video describes it as providing filesystem access, tool calling, code writing, and debugging capabilities; AssemblyAI used it to build the Joey support agent with local Markdown documentation, embeddings, agentic file search, and a large CLAUDE.md configuration file.

Open Instinct is an open-source personal AI agent that users text through iMessage, SMS, email, or webhooks. It runs its own agent process in a microVM with a Linux desktop, uses the Pi agent loop and Composio to operate connected applications, and can create files such as PDFs in its workspace before sending them back as attachments. A policy guard evaluates every tool call. Its network model defines six trust tiers for contacts and their agents, with grants for narrowly scoped exceptions; permissions, invitations, agent-to-agent tools, approvals, scheduling, memory, and audit logging are handled by the repository's packages. Payments use a Stripe Link wallet to request a single-use card for an exact total after owner approval, with spending limits and confirmation rules defined in a policy file. The repository provides a TypeScript CLI, local development and Maritime deployment paths, a multi-user gateway, and documentation for configuration, permissions, protocols, security, and self-hosting. It is distributed under the MIT license; the README describes live iMessage and Maritime deployment as beta and requires users to provide their own service keys.

Munder Difflin is a free, open-source desktop multi-agent harness that runs multiple terminal-based AI coding agents as coordinated local agents. It wraps agents including Claude Code, OpenAI Codex, Gemini CLI, Qwen, OpenCode, GitHub Copilot CLI, and custom commands, working with users' existing subscriptions and hourly usage limits. Each agent runs as a real node-pty process and is rendered through xterm.js, while an Electron and React interface displays sessions as avatars on a Pixi.js office floor. A GOD orchestrator called Michael assigns and routes work, adjudicates agent messages, and escalates spending, destructive operations, scope changes, and other configured approvals. Agents coordinate through a local Git-backed hive of plain-file memory, atomic mailboxes, a shared blackboard, and an append-only event log; a markdown-first semantic memory layer supports recall across sessions. Optional Git worktrees isolate parallel agents.

CowAgent is an open-source AI assistant and agent harness developed by LinkAI. It plans complex tasks step by step, runs tools and skills, controls computers and external services, maintains long-term memory and a personal knowledge base, and supports multi-agent teams with separate roles, models, skills, knowledge, and workspaces. Its architecture routes messages from web and messaging channels through an agent core that reasons over available models, tools, skills, memory, and knowledge before returning a response. Memory uses a three-tier structure of conversation context, daily memory, and long-term MEMORY.md, with a nightly Deep Dream process that distills memories; the knowledge base is an automatically curated Markdown wiki with cross-references and a browsable knowledge graph. Built-in tools include file and terminal operations, web fetching and search, scheduling, memory retrieval, vision, and browser automation, while MCP servers can be added through configuration. Skills can be installed from the Skill Hub, GitHub, ClawHub, or URLs, or authored through conversation. CowAgent supports multiple LLM providers and routes chat, vision, image generation, speech, and embedding workloads separately. It can run locally, in Docker, on a server, or through its macOS and Windows desktop client, with a web console for configuration and a command-line interface for service and skill management. The project is licensed under the MIT License and was formerly named chatgpt-on-wechat.