#1 AI CodingUnknown
agentty — alternative #1 to Agent Island
⭐ 608 — Native C++26 terminal coding agent and drop-in claude-code alternative; single ~13.6 MB static binary with sub-millisecond cold star...
GitHub source617MIT
Recorded alternatives
Alternatives to Agent Island
Every candidate below sits in AI Coding. What ends up on this page is decided entirely by a recorded score — not by bidding, not by editor taste. Review both records, check current vendor terms, then decide.
#2 AI CodingUnknown
AionUi — alternative #2 to Agent Island
⭐ 32.1k — Free desktop Cowork app that runs OpenClaw, Hermes, Claude Code, Codex, OpenCode, and 20+ other CLI agents around the clock; custo...
GitHub source33.8kApache-2.0
#3 AI CodingUnknown
m1nd — alternative #3 to Agent Island
⭐ 22 — Local-first MCP server that gives a CLI coding agent a neuro-symbolic code graph over the repo: impact/why/change-reasoning across a...
GitHub source
#4 AI CodingFree
Podiom — alternative #4 to Agent Island
⭐ 4 — Self-hosted control plane for local Claude Code and Codex CLI agents: durable named agents whose chat sessions replay onto a fresh bac...
GitHub source
#5 AI CodingUnknown
showagent — alternative #5 to Agent Island
⭐ 44 — Bubble Tea TUI that unifies the local session stores of Claude Code, Codex, Gemini CLI, and OpenCode: fuzzy search grouped by workspa...
GitHub source
#6 AI CodingUnknown
ax — alternative #6 to Agent Island
⭐ 95 — Local-first agent telemetry and observability for Claude Code and Codex sessions.
GitHub source122AGPL-3.0
#7 AI CodingUnknown
Cate — alternative #7 to Agent Island
⭐ 2.1k — Desktop app that runs terminals, Claude Code agent panels, editors, and browsers on an infinite zoomable canvas; multiple agent ses...
GitHub source2.2kMIT
#8 AI CodingUnknown
token-meter — alternative #8 to Agent Island
📇 🏠 🍎 🪟 🐧 - Local-first dashboard + MCP server for Claude Code and Codex token usage. Cost, per-MCP/per-tool breakdown, hourly distribution,...
GitHub source
Questions about this page
How were these alternatives selected?
Each candidate is a live catalogue record in the same primary category, picked by a deterministic score that Oryxen records in its catalogue: how many meaningful words the two listings share, whether their pricing classes oppose (a paid product against a free one), whether both are open source, and whether either record is featured. The same catalogue state always produces the same list — no randomness, no manual ranking.
Are these alternatives ranked by payment?
No. Rows are ordered only by the recorded score, highest first, with alphabetical ties — payment never influences the order, nothing here is paid placement, and Oryxen charges no listing or placement fee.
Always verify current terms with Agent Island directly — Oryxen records pricing classes, not live quotes.