Alternatives

Products that do what agentty does

Blazing-fast coding agent in your terminal.

1. 1
   Claude Code and Claude 3.7 Sonnet ▲874

   Our most intelligent model to date

   2025 · anthropic.com

2. 2
   Agentmemory▲322

   Persistent memory for Claude Code, Codex & coding agents

   May 2026 · agent-memory.dev

3. 3
   opencode▲395

   Your terminal's AI agent, with any model you want

   2025

4. 4
   Claude Opus 4.6▲764

   Claude’s most advanced model for agentic tasks

   Feb 2026 · anthropic.com

5. 5
   Xcode 26.3▲326

   Leverage coding agents to tackle complex tasks autonomously

   Feb 2026

6. 6
   Claude Code Desktop App Redesigned▲565

   Run parallel coding agents from one desktop workspace

   Apr 2026 · claude.com

7. 7
   Claude Code Review▲549

   Multi-agent review catching bugs early in AI-generated code

   Mar 2026

8. 8
   Replicas▲239

   Run Claude Code and Codex in the cloud

   Jun 2026 · replicas.dev

9. 9
   agentcad▲110

   A CAD design tool for coding agents (free + open source)

   Jun 2026 · agentcad.dev

10. 10
    spacecake▲79

    Run Claude Code agents in terminal with a visual editor

    Feb 2026

11. 11
    Remote OpenClaw▲81

    13,000+ MCP servers, skills & plugins for AI coding agents

    Jul 2026 · codexmarketplaces.com

12. 12
    agentbrowse▲89

    Give your AI coding agent the web as a command line

    Jun 2026 · npmjs.com

13. 13
    VEXI▲94

    Open-source AI coding agent for your terminal

    Jun 2026 · vexi.pro

14. 14OS
    Open-source CLI coding framework using Claude▲84

    2024 · github.com

15. 15
    /dev for Claude Code▲84

    Claude Code as a Tech Lead with parallel Worker Agents

    Apr 2026

16. 16AS
    AgentBox – SDK to Run Claude Code, Codex, or OpenCode in Any Sandbox▲8

    Hi HN, AgentBox is an SDK for running coding agents (Claude Code, Codex, OpenCode) inside sandboxes (Docker, E2B, Modal, Daytona, Vercel). One API. Swap the agent or the sandbox and your code doesn't change. Think of it as what the AI SDK did for LLMs, but for agent + runtime. Most wrappers call agents in non interactive mode (claude --print, codex exec). AgentBox instead boots each agent's native server inside the sandbox (Codex app-server over JSON-RPC, OpenCode serve over HTTP/SSE, Claude Code's SDK WebSocket transport) and drives it from the host, behaving like an interactive…

    Apr 2026 · github.com

17. 172C
    20+ Claude Code agents coordinating on real work (open source)▲53

    Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…

    Feb 2026 · github.com

18. 18
    AgentGrid▲77

    Your AI agents team, terminals, notes: one infinite canvas

    Jul 2026 · agentgrid.sh

19. 19
    Navox Agents▲75

    Specialist AI engineering team for Claude Code

    Apr 2026 · github.com

20. 20
    Agentinel▲18

    Stop AI agents from installing malicious packages.

    Jul 2026 · agentinel.habitwala.in

21. 21
    Agent terminal▲22

    One terminal. Every agent. Total clarity.

    May 2026 · github.com

22. 22IB
    I built a service to run Claude Code in the Cloud▲13

    2025 · agentwrap.dev

23. 23
    Friday AI▲28

    The full-stack AI Agent — Claude Code meets Lovable

    Jun 2026 · tryfriday.ai

24. 24LM
    Long Mem code agent cut 95% costs for Claude with small model reading▲29

    Feb 2026 · marketplace.visualstudio.com

Ranked by how close each launch is in meaning, then by votes. Refine with a description →