Workit Claude Code plugin — session and per-turn task context, branch policy on git shell commands, workit method skills, and verifier/reviewer/implementer agents

Local dashboard auditing Claude Code's per-turn token context (skills, agents, commands, CLAUDE.md, MEMORY.md, hooks, MCP) with toggle-based disable and session analytics.

Open tax skills for AI: 2,250 skills across 266 jurisdictions, every figure cited to the law. Works in ChatGPT, Claude, Cursor and any MCP client.

Semantic skill router for Claude Code — load only the skills you need, save 20k+ tokens per session

27 FREE Professional and Comprehensive Business Strategy Skills for Claude Code; with intelligent context chaining, skill iteration, terminal charts and HTML visualization options.

Persistent memory system for Claude Code via Markdown. Setup with /init-project, resume with /catchup, wrap with /wrapup. Includes coding standards, MCP servers, and modular skills. Solves context loss after /clear.

A Claude Code and Codex CLI hook that denies an edit or a gated tool call until the session loads the skills and reads the reference files it needs, and blocks after a Bash command that changed a gated file without them

Open-source 3D architectural editor with a local CLI, MCP tools, and practical workflows for humans and AI agents.

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.

Unbrowse - Reverse engineer any website so that your agents can access its APIs directly

The self-improving context engine for coding agents.

Bounded-autonomy plugin harness for agents. Intent to implementation: ready, then go.

Linter for AI agent configurations. Validates SKILL.md, CLAUDE.md, hooks, MCP, and more.

AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude subscriptions and any harness with ACP support.

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

39 MCP servers (488 tools) that give AI agents the Iranian web: Digikala, Torob, Divar, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche, laws, tax, crypto, stocks, news and more. Prices in Toman.

36 MCP servers (469 tools) that give AI agents the Iranian web: Digikala, Torob, Divar, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche, qavanin.ir laws, tax, news and more. Prices in Toman.

MCP server for EPLAN Electric P8: ~200 tools to drive EPLAN from Claude Code, Codex, Cursor or any MCP client (actions, scripts, live DataModel, exports). Includes the eplan-tools plugin marketplace.

Lossless context compression plugin for Claude Code & OpenCode.

Local RAG MCP Server - Easy-to-setup document search with minimal configuration

Self-hosted mission control for AI coding agents: run Claude Code, OpenCode, Pi, Codex, and Antigravity & Gemini CLI 24/7, from any device, watch every subagent live

AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated