Back to the catalog

Plugins · AI, RAG & memory

50 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.

  1. byom-review
    Code review with any AI model via OpenRouter. Run standard and adversarial reviews against your working tree or branch using Claude, GPT, Ge
  2. careerproof ★ 1
    Career and workforce intelligence built on a deep HR ontology — skill taxonomies, role definitions and responsibilities, compensation and in
  3. caveman ★ 104,558
    Auto-activation works differently per agent: Claude Code uses SessionStart hooks, this repo's Codex dogfood setup uses .codex/hooks.json, Ge
  4. cc-orchestrador-subagents ★ 1
    O cc-orchestrador-subagents transforma o Claude Code em um gerente técnico de execução, não em "mais um agente que programa". A skill assume
  5. cc-suite ★ 44
    cc-suite turns three CLI tools (Claude Code, OpenAI Codex CLI, Google Gemini CLI) into one shared brain. Project context is written once in
  6. cc10x-router-owned-harness ★ 164
    Supercharge Claude Code with Orchestrated Skills, Subagents, Persistent Memory
  7. challenger ★ 1
    Multi-agent adversarial plugin that stress-tests code decisions, architecture plans, and reasoning through evidence-backed challenge rounds.
  8. chinese-llm-models
    A unified API gateway that provides access to 6+ leading Chinese AI models (Kimi K2.5, Qwen3 Max, DeepSeek V3.2, GLM-5, MiniMax M2.1, Seed 1
  9. chub ★ 2
    Fetches curated, versioned API docs from Context Hub before writing code — so Claude uses current APIs instead of hallucinating from trainin
  10. circumpunct-ethics-virtues-plugin ★ 3
    This is an ethical reasoning and diagnostic plugin based on four pillars (Good, Right, True, Agreement) kept alive by four corresponding vir
  11. claude-bot ★ 1
    Persistent Claude Code agent with long-term memory, cron jobs, and a background daemon Your AI assistant that actually remembers. claude-bot
  12. claude-chronicle ★ 1
    Bridges Codex Chronicle's screen-recording memory into Claude Code. Codex Chronicle is an OpenAI Codex feature that passively records your s
  13. claude-code-bootstrapper ★ 15
    Analyze any project and generate a complete .claude/ automation structure: agents, pipelines, skills, memory, hooks, and settings. Supports
  14. claude-code-feedback ★ 1
    Claude Code user plugin for filing well-formed bug reports, feature requests, model-behavior reports, and docs issues against anthropics/cla
  15. claude-code-plugin-for-goodmem-a-memory-infra-for-agents ★ 8
    With this plugin, you can operate Goodmem's memory infra in plain English, to create, manage, and orchestrate embedders, rerankers, and LLMs
  16. claude-code-survival-kit
    10 slash commands and 3 agent definitions distilled from 6 months of daily Claude Code use. Not a framework -- just the patterns that surviv
  17. claude-codex-loop
    claude-codex-loop orchestrates a structured collaboration loop between Claude Code (designer/reviewer) and OpenAI Codex (auditor/implementer
  18. claude-cognis ★ 20
    Persistent memory for Claude Code powered by Cognis. Automatically loads relevant context at the start of every session and saves session su
  19. claude-context-monitor ★ 23
    Prevent context window exhaustion. Real-time token tracking, semantic compact scoring, and carry-forward memory that fixes cumulative amnesi
  20. claude-context-optimizer ★ 1
    Audit and optimize Claude Code context window usage. Runs a 9-phase analysis covering plugins, hooks, CLAUDE.md cascade, MCP servers, enviro
  21. claude-damn ★ 3
    A SME of SWE: a plugin giving Claude Code the expertise of an Expert Software Engineer across every SWE area, while still inviting novice pr
  22. claude-harness ★ 3,105
    Autonomous Plan → Work → Review cycle for Claude Code. Go-native engine with 25× faster hooks, runtime guardrails on .git/ / secrets / destr
  23. claude-meister
    Claude Code is great, but treating every prompt with full context is too expensive. I built Claude_Meister as an MCP plugin to dynamically r
  24. claude-mem ★ 93,225
    Persistent memory system for Claude Code - seamlessly preserve context across sessions
  25. claude-memory
    A Claude Code plugin that adds structured, categorized memory to your projects.
  26. claude-prompt-library ★ 3
    Save, search, load and manage reusable prompts across projects. Build a personal prompt library that persists across sessions and works in a
  27. claude-pulse ★ 456
    claude-pulse adds a live usage status bar to Claude Code showing your session usage, weekly limits, reset timer, and plan tier — pulled dire
  28. claude-self-reflect ★ 224
    Persistent conversation memory for Claude Code. Semantic search across past sessions, session continuity detection, cross-project intelligen
  29. claude-telegram-voice ★ 1
    Voice message transcription for the Telegram channel plugin. When a user sends a voice message, the plugin instructs Claude to automatically
  30. claude-telegram-voice-control
    Telegram channel with local voice transcription via whisper.cpp. Voice messages are automatically transcribed on-device using the Whisper me
  31. claude-train-prep ★ 2
    Claude Code plugin: AI consulting training material workflow (Word report + HTML slides) with multi-agent parallelism
  32. claude-transcribe
    Transcribe video and audio from URLs (YouTube, X/Twitter, TikTok, Vimeo, podcasts) or local media files into plain-text transcripts using yt
  33. claude-video-vision ★ 1,295
    A perception layer that gives Claude Code the ability to watch and understand videos. Extracts frames via ffmpeg and processes audio through
  34. claudetokensap ★ 3
    ClaudeTokenSAP is a Claude Code plugin marketplace focused on reducing context waste and improving session efficiency. Its first plugin, Tok
  35. clawcode ★ 62
    ClawCode is an open-source plugin that turns otherwise stateless sessions into persistent agents. It adds identity, personality, long-term m
  36. clawket ★ 1
    LLM-native work management plugin for Claude Code. 10 lifecycle hooks auto-track your entire workflow — PreToolUse blocks code changes unles
  37. closedloop ★ 103
    Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learn
  38. cmux-ultimate ★ 1
    Complete cmux integration for Claude Code. Includes full CLI reference (~130 commands), browser automation (~40 subcommands with element ref
  39. code-parser ★ 1
    Index Dart, Python, and TypeScript codebases with code-parser to slash LLM token consumption by 70–97%. Extracts classes, methods, and exact
  40. codedna ★ 147
    CodeDNA makes any codebase AI-navigable by embedding architectural context directly in source files. One command annotates every file with e
  41. codesmith ★ 1
    Codesmith is a Claude Code plugin that enforces the full dev lifecycle: spec refinement → TDD → implementation → parallel multi-agent review
  42. codex-bridge ★ 26
    Run Codex review, adversarial review, and second-pass handoffs from Claude Code while keeping ThumbGate reliability memory and pre-action ga
  43. codex-hud ★ 8
    Display OpenAI Codex usage and rate limits inside Claude Code. Real-time statusline integration with claude-hud, slash commands for usage/co
  44. codex-review ★ 8
    Send your implementation plan to OpenAI Codex CLI for iterative review. Claude and Codex go back-and-forth until Codex approves the plan.
  45. cognito
    A memory layer for Claude Code
  46. colosseum ★ 1
    proven wrong by search results, and earn scores based on accuracy and independence — not agreement. A built-in Devil's Advocate challenges t
  47. compact-knowledge-graph-ckg
    Build and query Compact Knowledge Graphs directly in Claude Code. Includes a skill to convert any CSV into a CKG and an MCP server with 8 pr
  48. compounded ★ 5
    compounded turns Claude Code skills into a trust-gradient system: every skill earns its autonomy through demonstrated reliability. New skill
  49. concordia-protocol ★ 4
    Structured negotiation protocol for autonomous agents. Gives your agent binding commitments, multi-attribute offers (basic, partial, conditi
  50. conotate
    A toolkit for generating and managing structured knowledge bases of code domains — explore, document, and navigate large codebases with AI-a