The Aigentic logo
Subscribe

Agents

A map of the agent landscape: self-hosted personal frameworks, hosted teammate products, coding CLIs, and libraries for building your own. Links go to the official repo or product page we could verify.

Checked as of Sep 21, 2026. Star counts, maintainers, and even repo locations move fast — especially in the OpenClaw family — so confirm the URL before you install anything that asks for system access.

Entries marked Invite only are waitlist-gated, invite-only, or otherwise not open for general self-serve signup as of our check date. Paid products anyone can buy are unmarked; we omit the badge when access status is unclear.

1. Open-source personal agent frameworks

Self-hosted daily-driver assistants — gateway runtimes, skills, and persistent memory you run yourself.

  • OpenClaw

    The original gateway platform; TypeScript, with a large skill ecosystem.

  • Hermes Agent

    Nous Research — self-improving agent that creates its own skills, with persistent memory.

  • nanobot

    HKUDS — Python rewrite, positioned as auditable in an afternoon.

  • NanoClaw

    Lightweight TypeScript alternative (~hundreds of lines of core); each agent runs in its own locked container.

    Canonical repo is nanocoai/nanoclaw (qwibitai/nanoclaw redirects here).

  • ZeroClaw

    Rust runtime aimed at tiny hardware footprints (very low RAM).

  • PicoClaw

    Sipeed — Go, single static binary, targets cheap boards.

Also in this family, without a single verified product URL in our check: TrustClaw, Goclaw, IronClaw, NullClaw, OpenAGI. Names circulate; treat installs as untrusted until you confirm the official source.

2. Hosted AI teammate products

Productized assistants — mostly cloud / subscription, sometimes with a local or open-source option.

  • Grok Bot

    xAI — named bots on a persistent cloud computer with browser, filesystem, terminal, connectors, and durable state.

  • Claude Cowork

    Anthropic — agentic knowledge-work mode across desktop, web, and mobile; multi-step tasks on files and tools you choose.

  • ChatGPT Agent

    OpenAI — agent mode in ChatGPT that plans and acts across apps, files, and the browser (successor to Operator).

    Product surface continues to evolve (e.g. Work mode in ChatGPT); this row tracks OpenAI’s ChatGPT agent capability, not plain chat.

  • Manus

    Cloud agent for long-horizon autonomous tasks.

  • Perplexity Computer

    Cloud agent orchestrator that coordinates multiple models to run multi-step workflows in the background.

  • Vellum

    Personal assistant as a native Mac app or Vellum Cloud, with iOS, web, voice, email, Telegram, and Slack surfaces sharing one memory.

    Open-source core (MIT) with managed cloud and self-host options — not a closed-only product.

3. Agentic coding CLIs

Agents scoped to a codebase — terminal-native plan / edit / test loops.

  • Claude Code

    Anthropic — terminal coding agent.

  • Codex CLI

    OpenAI — open-source coding agent CLI.

  • Grok Build

    xAI — terminal-native coding agent with parallel subagents and MCP support.

  • Gemini CLI

    Google — open-source Gemini coding agent in the terminal.

  • Muse Code

    Meta — terminal coding agent powered by Muse Spark; subscriptions and Meta Model API pay-as-you-go.

  • Cursor

    AI-native code editor with agent mode for multi-file edits, terminal commands, and background agent runs.

  • Devin

    Cognition — managed autonomous software engineer that plans, codes, and returns work for review.

  • GitHub Copilot

    GitHub — coding agent mode for issue-to-PR and multi-step repo work alongside editor autocomplete.

  • OpenHands

    Open-source autonomous coding platform (CLI, local GUI, cloud) with Docker sandboxes and an SDK.

    Also https://github.com/OpenHands/OpenHands for the primary repo.

4. Developer frameworks

Libraries and automation platforms for building your own agents.

  • LangGraph

    Stateful, graph-based agent workflows (LangChain ecosystem).

  • CrewAI

    Role-based multi-agent crews.

  • AutoGen

    Microsoft — multi-agent conversation framework.

  • Mastra

    TypeScript agent framework.

  • n8n

    Workflow automation with agent nodes.

  • Claude Agent SDK

    Anthropic — the harness behind Claude Code, exposed as a Python / TypeScript library.

How to read this

Category 1 projects launched in a tight cluster and still churn. Category 2 mixes closed cloud products with hybrids like Vellum (open-source core). Coding CLIs and frameworks are adjacent but not the same job as a daily-driver personal agent — we keep them separate so the map stays useful.

When we publish a Hands On guide for an agent here, it shows under that tile. Browse all guides on Hands On.

the aigentic

Know what matters in AI.

The stories shaping AI, the tools worth trying, and what they mean for your work.

Morning Brief + Closing Time. Two emails every weekday.

Free. Unsubscribe anytime.