19 plugins · data as of 2026-09-30
Plugin catalog
Ranked by GitHub stars, each integer read from the fetchable page recorded in that entry's source field, as of the asOf date. Star counts move daily, so every entry carries its own source and date.
openclaw5
- Brave Search (OpenClaw)390,823OpenClaw's official external plugin (@openclaw/brave-plugin): wires the Brave Search API in as the provider behind OpenClaw agents' web_search tool, supporting web and llm-context modes, with a baseUrl setting to route requests through a proxy.2026-03-16
- Browser (OpenClaw)390,823Core built-in OpenClaw plugin (@openclaw/browser-plugin): gives the agent a dedicated managed browser — a separate openclaw profile (orange accent by default) of Chrome/Brave/Edge/Chromium, driven through a loopback-only control service inside the Gateway, with deterministic tab control (list/open/focus/close), actions (click/type/drag/select), snapshots, screenshots, PDFs and managed downloads; a bundled browser-automation skill teaches agents to use it. The built-in user profile mode instead attaches to your real signed-in Chrome (via Chrome DevTools MCP).2026-03-26
- CUA Computer (OpenClaw)390,823OpenClaw's official external plugin (@openclaw/cua-computer, marked experimental): provides computer control on Windows (x64/ARM64) and glibc Linux (x64/ARM64) hosts — the agent observes the desktop via screenshots (screen.snapshot) and performs real mouse/keyboard actions (computer.act) through one uniform computer tool, calling the package's pinned CUA Driver SDK directly and requiring a vision-capable model. macOS does not use this plugin (built-in Peekaboo/CUA fulfillers instead).2026-07-21
- Discord (OpenClaw)390,823OpenClaw's official external plugin (@openclaw/discord): connects OpenClaw agents to Discord as a bot — guild channels and DMs, native slash commands, app events, reaction/presence wakes, plus advanced surfaces like realtime voice conversations, continuous voice transcripts and automatic meeting notes. DMs default to pairing mode; channel access is governed by allowlists and mention gating.2026-01-18
- File Transfer (OpenClaw)390,823Core built-in OpenClaw plugin (@openclaw/file-transfer): fetch, list and write files on paired nodes via dedicated node commands — base64 over node.invoke bypasses bash stdout truncation for binaries up to 16 MB; dir_fetch pulls a whole directory tree, dotfiles and hidden directories included.2026-04-30
claude-code7
- Code Review148,649Official Anthropic plugin for Claude Code: /code-review automates pull-request review — it first checks whether review is needed (skipping closed, draft, trivial or already-reviewed PRs), gathers the repo's CLAUDE.md guidelines, summarizes the changes, then launches 4 parallel agents (two audit CLAUDE.md compliance, one scans for obvious bugs, one analyzes git blame/history for context issues), scores every finding 0-100 for confidence, filters out anything below 80, and outputs to the terminal or posts as a PR comment with --comment.2025-10-23
- Commit Commands148,649Official Anthropic plugin for Claude Code: three slash commands streamlining git workflow — /commit analyzes staged and unstaged changes, matches the repo's commit style and creates the commit; /commit-push-pr commits, pushes and opens a Pull Request in one step; /clean_gone removes local branches marked [gone] (deleted on the remote) along with their worktrees.2025-10-08
- Feature Dev148,649Official Anthropic plugin for Claude Code: /feature-dev runs a structured 7-phase feature-development workflow — understand the codebase, clarify requirements, design architecture, then implement and review — bundled with three specialized agents: code-explorer, code-architect and code-reviewer.2025-10-09
- Hookify148,649Official Anthropic plugin for Claude Code: create custom hooks in natural language — /hookify analyzes your description (or uses the conversation-analyzer agent to mine unwanted behavior patterns from the conversation) and generates Markdown + YAML-frontmatter rule files (e.g. .claude/hookify.warn-rm.local.md) that regex-match tool usage and show warnings on hit; effective on the very next tool call with no restart, plus list/configure/help subcommands for rule management.2025-11-17
- PR Review Toolkit148,649Official Anthropic plugin for Claude Code: six review agents each specializing in one aspect — comment-analyzer, pr-test-analyzer, silent-failure-hunter (swallowed errors), type-design-analyzer, code-reviewer and code-simplifier — usable individually or combined via /pr-review-toolkit:review-pr with selected aspects.2025-10-08
- Ralph Wiggum148,649Official Anthropic plugin for Claude Code: implements the Ralph technique — a Stop hook intercepts Claude's exit attempts and feeds the same prompt back, creating an in-session while-true self-referential loop until the task completes (declared via --completion-promise, e.g. DONE). /ralph-loop starts it, /cancel-ralph stops it. No external bash loop needed.2025-11-16
- Security Guidance148,649Official Anthropic plugin for Claude Code (v2.0.0) with three review layers: (1) instant regex warnings on Edit/Write for ~25 known-dangerous patterns (yaml.load, pickle, raw innerHTML, hardcoded secrets...); (2) at turn end the diff goes to a fast LLM call (Opus 4.7 by default), with high-severity findings fed back so Claude fixes them before you see the response; (3) on git commit an SDK-driven agentic reviewer uses Read/Grep/Glob to trace cross-file data flow, catching IDOR, auth bypass and cross-file SSRF that pattern matching misses.2025-10-09
hermes-agent7
- Hindsight43,265Hermes Agent long-term memory provider maintained by Vectorize (listed in Hermes' official plugin catalog, human-reviewed and commit-pinned): knowledge graph, entity resolution and multi-strategy retrieval via recall/reflect/retain tools, plus automatic per-turn capture. Cloud, local-external and local-embedded modes are available.date not on record
- Honcho7,403Hermes Agent memory provider maintained by Plastic Labs (official catalog entry, review-pinned commit): cross-session user modeling — dialectic Q&A, semantic search and persistent conclusions remember who the user is and what they prefer, with an on_session_end hook processing data when sessions close.date not on record
- Mnemosyne3,301Community-maintained local-first memory layer listed in Hermes' official catalog (human-reviewed, commit-pinned): SQLite with vector + FTS5 hybrid recall, episodic consolidation and a temporal knowledge graph — officially described as Zero cloud. The catalog declares 32 tools (mnemosyne_recall/remember/forget/graph_query/scratchpad_*/shared_*, etc.).date not on record
- Cognee95Knowledge-graph memory plugin by topoteretes, listed in Hermes' official catalog: five tools (cognee_recall/remember/forget/switch_dataset/code_search) and two hooks (on_session_end, on_memory_write), backed by either a local cognee server or Cognee Cloud.date not on record
- Claude Subscription (Direct SDK)64Official NousResearch Hermes plugin (experimental model provider): runs Hermes turns on your Claude Pro/Max subscription via the official Claude Code CLI's Agent SDK path — no separate API key, no per-token bill. It checks for an installed and logged-in claude CLI at load, in the hermes model pickers and before every request, refusing cleanly with an install hint when missing.2026-09-20
- Blender (Hermes)7Official NousResearch Hermes plugin: wires the Blender Lab MCP server into Hermes over stdio (pinned to upstream v1.0.3) and bundles a Blender workflow skill so the agent can drive Blender for 3D work. Requires Blender 5.1+ (with its separately installed MCP add-on), Git and uv; first startup downloads Python dependencies.2026-09-22
- Apify6Apify's official catalog plugin for Hermes Agent (listed in the official catalog at a review-pinned commit): three tools — apify_discover, apify_start and apify_collect — let the agent discover, run and collect results from thousands of ready-made Actors (scrapers, automation tools) on the Apify platform.date not on record