By leadsblender
A persistent personal-agent layer for Claude Code — replicates Hermes/OpenClaw behavior (identity files, MD-based skills, cron routines, memory) using Claude Code's native plugin system.
Delegate a task to a specific Claw subagent (researcher, coder, scheduler, librarian).
Reload Claw's identity, soul, user profile, and memory. Run after editing any identity file.
Schedule, list, edit, or remove autonomous routines. Defaults to picking the right backend (local daemon vs Claude Routines / cloud) per task.
Manage the messaging gateway (Slack / Telegram / WhatsApp). Pair new peers, list sessions, revoke access.
Show Claw's operational rhythm — current schedule, recent routine results, and what's coming up next.
Spawn for an isolated implementation task — one feature, one bug, one refactor. Use when work parallelizes cleanly into independent units. Returns a summary of what changed; verify the diff yourself before reporting done.
Curate the memory system — merge duplicates, prune stale entries, promote fast-path entries that grew too long, fix broken pointers. Spawn for the weekly memory consolidation pass or whenever memory feels noisy.
Spawn for open-ended research questions that need 3+ web sources or branch into sub-questions. Returns a synthesized answer plus citations, not raw search dumps.
Manage Claw's cron entries — add, list, edit, pause, remove. Spawn when the user has multiple scheduling changes at once, or when reconciling HEARTBEAT.md with the actual scheduled-tasks MCP state.
Decide what to write to memory and where. Triggers when something surprising or load-bearing comes up that should outlive this session — corrections from the user, decisions made, non-obvious facts about external systems, or stable preferences. Also triggers when the user explicitly says "remember", "save this", or "for next time".
Produce a single-screen morning briefing. Triggers when the user says "morning brief", "what's on today", "daily standup", or when the cron entry for it fires. Pulls from calendar, inbox, open PRs, and yesterday's memory.
First-run setup. Walks the user through filling in USER.md and SOUL.md so Claw becomes personalized. Triggers on the very first session (when USER.md still has placeholder values) or when the user runs /onboarding explicitly.
Create or manage Claude Routines (Anthropic's cloud-hosted scheduler). Triggers when the user wants a scheduled task that fires even when their machine is off, or says "create a routine", "schedule on cloud", "anthropic cron", or "use routines for X". Bridges to Claude Code's built-in `schedule` skill so the routine is registered with Anthropic's cloud trigger system.
Research a question on the web and synthesize a focused answer. Triggers when the user asks an open question that needs current info ("what's the state of X", "compare Y and Z", "is W still maintained"), or when an answer can't come from the codebase or memory.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A persistent personal-agent layer for Claude Code. Built to give Claude the same shape Hermes-Agent and OpenClaw give to their backends — identity files, MD-based skills, cron routines, persistent memory — but using only Claude Code's native plugin system. No daemon, no separate runtime, no second LLM provider.
If you've used OpenClaw or Hermes Agent, this will feel familiar:
| Concept | OpenClaw / Hermes | Claudeclaw |
|---|---|---|
| Persistent identity | ~/.openclaw/workspace/{IDENTITY,SOUL,USER,MEMORY,AGENTS,TOOLS,HEARTBEAT,BOOT}.md | ~/.claude/plugins/claudeclaw/identity/{IDENTITY,SOUL,USER,MEMORY,AGENTS,TOOLS,HEARTBEAT,BOOT}.md |
| Skills (procedural memory) | ~/.openclaw/skills/<name>/SKILL.md | ~/.claude/plugins/claudeclaw/skills/<name>/SKILL.md |
| Cron routines | openclaw cron add … | /cron add … — dual backend: local daemon (sub-minute, no quota, needs your machine) or Claude Routines (cloud, fires offline, daily quota). See docs/scheduling.md. |
| Memory persistence | MEMORY.md (single file, capped) | MEMORY.md (fast-path) + Claude Code's auto-memory (~/.claude/projects/<project>/memory/) |
| Subagent delegation | agent registry | Native sub-agents (~/.claude/plugins/claudeclaw/agents/<name>.md) |
| Multi-platform messaging | Native (WhatsApp, Telegram, Discord, …) | Built-in gateway for Telegram, Slack, WhatsApp — same identity, skills, memory. See gateway/README.md. |
| One-line install | curl …/install.sh | bash | curl …/install.sh | bash |
inbox-summarize skill instead of Claude reasoning from scratch each time.MEMORY.md for lines you want loaded every prompt, and a long-form auto-memory for per-topic markdown files./boot — Claw is now different.curl -fsSL https://raw.githubusercontent.com/leadsblender/claudeclaw/main/install.sh | bash
Add --with-gateway to also install the messaging gateway (Slack/Telegram/WhatsApp):
curl -fsSL https://raw.githubusercontent.com/leadsblender/claudeclaw/main/install.sh | bash -s -- --with-gateway
Or from a local checkout:
cd claudeclaw && bash install.sh # core only
cd claudeclaw && bash install.sh --with-gateway # core + messaging
The installer:
claude (Claude Code CLI) installed.~/.claude/plugins/claudeclaw/.~/.claude/settings.json (enabledPlugins.claudeclaw = true).Open Claude Code anywhere:
claude
Because USER.md still has placeholder values, the onboarding skill runs automatically. It asks you five questions, writes your answers into USER.md and SOUL.md, and you're personalized. Total time: ~90 seconds.
After that, every session greets you by name, knows what you're working on, and obeys your tone preferences.
| You say | What happens |
|---|---|
| "morning brief" | Calendar + inbox + open PRs + suggested first move, in one screen. |
| "summarize my inbox" | Threads grouped by needs-reply / needs-decision / fyi / noise. |
"review this PR" or /review | Structured review with blockers / should-fix / consider / liked. |
| "remember that I prefer Vite over webpack" | Memory written to the right store automatically. |
/cron add summarize my inbox every weekday at 8am | Scheduled, added to HEARTBEAT.md. |
/skill list | Every skill Claw has, with one-line descriptions. |
/identity edit SOUL | Reshape Claw's voice. Run /boot after to apply. |
npx claudepluginhub leadsblender/claudeclaw --plugin claudeclawMulti-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Memory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.