Hlido › Alternatives

LuKresXD/claw-skeleton alternatives

Looking for an alternative to LuKresXD/claw-skeleton? Here are the top Coding agents Hlido has independently tested β€” scored on the same framework, ranked by evidence.

Independently tested by Hlido. 8 alternatives ranked. Updated 2026-07-19.

You're
comparing

LuKresXD/claw-skeleton

82/100 STEADY Coding

LuKresXD/claw-skeleton β€” πŸͺΌ A personal AI assistant that lives in Telegram β€” every topic is its own isolated Claude Code agent with layered persistent memory and proactive cron heartbeats. Open skeleton of a real, running system.. Repo-surface review: measured from the public repository (63 stars, MIT, last push 2026-06-30); not hands-on tested.

Read the full LuKresXD/claw-skeleton review ›

Top alternatives to LuKresXD/claw-skeleton

#1

lucasrosati/claude-code-memory-setup

82/100 STEADY Coding

lucasrosati/claude-code-memory-setup β€” Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. πŸ‡§πŸ‡· PT-BR included.. Repo-surface review: measured from the public repository (852 stars, MIT, last push 2026-06-01); not hands-on tested.

#2

withkynam/vibecode-pro-max-kit

82/100 STEADY Coding

withkynam/vibecode-pro-max-kit β€” Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders β€” self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack. Repo-surface review: measured from the public repository (1042 stars, MIT, last push 2026-06-21); not hands-on tested.

#3

graykode/abtop

82/100 STEADY Coding

graykode/abtop β€” Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.. Repo-surface review: measured from the public repository (3351 stars, MIT, last push 2026-07-07); not hands-on tested.

#4

ClaudioDrews/memory-os

73/100 STEADY Coding

ClaudioDrews/memory-os β€” A 7-layer memory operating system for Hermes Agent β€” persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.. Repo-surface review: measured from the public repository (1272 stars, MIT, last push 2026-06-10); not hands-on tested.

#5

fazxes/Claude-code

60/100 FADING Coding

fazxes/Claude-code β€” Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster through natural language commands. Rebuilt from leaked source.. Repo-surface review: measured from the public repository (225 stars, no license, last push 2026-04-03); not hands-on tested.

#6

NeoTheCapt/RedteamAgent

73/100 STEADY Coding

NeoTheCapt/RedteamAgent β€” An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Codex into a structured recon β†’ test β†’ exploit β†’ report workflow, with containerized tools and resumable state.. Repo-surface review: measured from the public repository (92 stars, no license, last push 2026-05-14); not hands-on tested.

#7

itsinseong/value-for-fable

67/100 FADING Coding

itsinseong/value-for-fable β€” Opus에 κ·Όμ ‘ν•œ ν’ˆμ§ˆμ„ Sonnet 단가에 β€” κ°€μ„±λΉ„ AI 운영 λͺ¨λΈμ„ 직접 κ΅¬μΆ•ν•œ Claude Code ν”„λ‘œμ νŠΈ. Repo-surface review: measured from the public repository (235 stars, AGPL-3.0, last push 2026-06-21); not hands-on tested.

#8

iAmCorey/kooky

82/100 STEADY Coding

iAmCorey/kooky β€” A minimal modern terminal for AI coding experience β€” Sidebar workspaces; horizontal / vertical split panes; one-click agent launch; per-agent activity readout; live workspace state with one-click Node and branch switching.. Repo-surface review: measured from the public repository (544 stars, MIT, last push 2026-07-10); not hands-on tested.

How Hlido compares them

Every score is derived from a fixed 5-dimension framework with C2PA-signed evidence captured during testing. We don't accept payment for placement, so a higher-ranked alternative earned it on the evidence β€” not on a sponsorship.

Read our methodology · All reviews · All alternatives