Workflow middleware
-
@ai-eng-system/cli
Compounding engineering system for Claude Code and OpenCode. Shared agents, commands, skills, and plugin development tools.
-
@calebux/agent-kit
Infrastructure for autonomous agent economies — identity, reputation, payments, governance, discovery, coordination, and audit on Celo and Stellar. Also works fully off-chain with persistent memory, agentic loops, and tool-use.
-
@catladder/cli
Panter cli tool for cloud CI/CD and DevOps
-
@claude-flow/cli
Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
-
@clawdbot/lobster
Workflow runtime for AI agents - deterministic pipelines with approval gates
-
@factorialco/shadowdog
<img src="https://raw.githubusercontent.com/factorialco/shadowdog/refs/heads/main/logo.png" alt="drawing" width="100"/>
-
@fatihkan/badi
Workflow management CLI for Claude Code, Cursor, and Gemini CLI — 30 AI agents (incl. a virtual eng team, ads strategist, market/SEO/data analysts), 86 commands, OWASP security scans. Built for Anthropic Claude Opus and Sonnet.
-
@gunesbizim/agent-smith
Autonomous development pipeline — MCP auto-config, project-aware skill stubs, Jira-to-PR automation, Playwright+Obsidian docs
-
@itradingai/aiwiki
Local Markdown knowledge base for AI assistants. Save what your AI reads, ask it later, and keep everything local.
-
@juspay/neurolink
Universal AI Development Platform with working MCP integration, multi-provider support, voice (TTS/STT/realtime), and professional CLI. 58+ external MCP servers discoverable, multimodal file processing, RAG pipelines. Build, test, and deploy AI applicatio
-
@mindfoldhq/trellis
AI capabilities grow like ivy — Trellis provides the structure to guide them along a disciplined path
-
@promptbook/utils
Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action
-
@temporalio/testing
Temporal.io SDK Testing sub-package
-
0nMCP
🤖 Orchestrate AI across apps with a universal API that simplifies integration and automates tasks using Model Context Protocol (MCP) compatibility.
-
action-pin-check
Audit GitHub Actions workflows for mutable or missing action pins.
-
adobe-acrobat-pro-workflow
Technical configuration utility for Adobe Acrobat Pro environment automation.
-
aegisloop
A guarded ChatGPT-to-Codex automation bridge for bounded local engineering loops.
-
agent-orch
Run local coding agents in a cross-audit loop on any git repo — author, cross-audit, test-gate, merge
-
agent-orchestrator-framework
Turn Your AI Agent Into a Full Developer Team: Plan, Code, Test & Ship in One Sprint 2026
-
agent-rules-kit
Diagnose AI agent instruction files like AGENTS.md, CLAUDE.md, and Cursor rules using this local read-only Python CLI.
-
Agent-Skills
Governed skill foundry and Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.
-
agentic-flow
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
-
agentic-swmm-workflow
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex, Hermes, Claude code as well as OpenClaw compatibility
-
agentic-tui
Agentic orchestrator TUI: turns a goal into worktree-isolated claude -p sessions that plan, implement, and verify epics in parallel
-
agentic-workspace
Repo-native operating layer for AI agents: memory, planning, proof, routing, and continuity across sessions.
-
AgentsCommander
Run multiple CLI coding agents (Claude Code, Codex, Gemini, OpenCode) as a coordinated team, on a Loop. Local-first, file-based coordination, full PTY, no telemetry.
-
AI-CLI-Agent
A privacy-first, local AI desktop agent. Wraps Gemma 4 in a modular Python framework, enabling autonomous web searching and system-level tool execution directly from the Linux terminal. Zero API keys required.
-
ai-hiring-workflow-engine
Analyze resumes against job descriptions using Claude AI to generate match scores, gap insights, and improvement actions for recruiters and job seekers.
-
ai-jury
Stdlib-only Python CLI that runs native coding-agent CLIs (Claude Code, Codex, Antigravity) + a free local model as one review jury — review a diff/PR/issue, debate, verify, synthesize one verdict (chair or panel vote). Local-first, secure by default.
-
aibranch
🤖 Generate AI-driven Git branch names that follow conventional standards, streamlining your workflow and improving code management.
-
AIDOCS
AIDOCS — AI Doctrine Orchestrator, Control & Security.
-
ArtiTam-Gallery
Archivio pubblico per le immagini e il file gallery.json del sito dell’artigiano edile. Aggiornato automaticamente da Google Drive tramite Apps Script.
-
askproof-skill
Verify AI agent output with actionable evidence for non-engineers. Build better prompts by auditing AI claims and checking task status before continuing.
-
automated-business-analysis-workflow
📊 Streamline business analysis with this workflow that scrapes websites, extracts key data, and generates AI-driven reports in Google Doc and PDF formats.
-
awesome-agent-orchestration
Compile and organize top tools, frameworks, and resources for AI agent orchestration and multi-agent system development.
-
awesome-agent-skills
Curated, auto-updated awesome-list of vetted AI agent skills with quality ratings for Claude, GPT, a
-
Bamboo-agent
Bamboo — a local-first AI agent runtime in Rust: tasks, tools, memory, MCP, workflows and schedules behind an HTTP + SSE API. The self-contained execution core powering the Bodhi desktop agent.
-
beads_rust
🎯 Track issues in your Git repositories with this fast, non-invasive Rust port of the classic SQLite + JSONL "beads" architecture.
-
builder-jobs-scraper
Hourly pipeline that discovers, fetches, and classifies engineering jobs from company ATS boards — publishes a curated index to builder-jobs.
-
C_Processes_Signals
C programs explore processes and signals for OS concepts. Learn process creation, synchronization, and signal handling with concise, practical exercises. 🐙
Workflow C++ -
Carmack-Council
Build multi-agent Claude Code applications using a simple, battle-tested framework inspired by John Carmack’s engineering principles.
-
cbb-ratings-pipeline
End-to-end Python ETL pipeline that collects NCAA men's basketball rankings from multiple sources, standardizes team names, and deploys a live dashboard via GitHub Pages.
-
ChainWeaver
Deterministic MCP tool flows for AI agents. Remove unnecessary LLM calls between predictable tool steps.
-
chimera-agent
Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully yours.
-
ci-cd
🚀 Streamline your development process with this CI/CD setup for Turborepo, featuring tools for type checking, linting, and code formatting.
-
claude-agents-forge
Build and run production-ready Claude Code agents with full agent specs, including turn limits, permissions, memory, and tool orchestration.
-
claude-auto-tok
Automate TikTok video creation with six AI agents for trend research, scripts, voiceovers, B-roll, rendering, and QA
-
claude-code-boilerplate
🛠️ Streamline your Claude Code projects with universal coding standards and AI agent configurations for efficient development and collaboration.
-
claude-code-tips
Provide ready-to-use plugins, hooks, and commands to enhance Claude Code sessions with data mining, automation, and integration tools.
-
claude-daily-check-in
A GitHub Actions project that strategically automates Claude Code session resets. It schedules triggers to align with your work hours, ensuring you get a fresh 5-hour usage window precisely when you need it for maximum productivity.
-
claude-forge
Transform Claude Code into a complete development environment for efficient coding and project management.
-
claude-memory
Enable persistent memory for Claude that works across crashes and restarts in both Claude Code and Claude Cowork environments.
-
claude-orchestrator
Local web dashboard for orchestrating parallel Claude Code sessions — task dispatch, automated PR review, lifecycle management.
-
claude-pangu
基于中国传统文化的 Claude Code 智能编排插件 - A Claude Code plugin inspired by Chinese traditional culture (原名 oh-my-claude)
-
claude-product-workflow
🚀 Transform product ideas into development-ready documents with a 5-skill workflow that enforces professional standards for research, design, and planning.
-
ClawUI
Run a cross-platform OpenClaw desktop client with built-in Gateway, onboarding, chat, and a full admin panel.
-
clov-ai
Manage and filter AI context and outputs locally using Rust-powered tools for precise control and improved response quality.
-
code-review-skill
Automate code reviews for general code projects with modular parallel checks, config-driven scope, and clear reports.
-
codeadd
CLI for Code Addiction framework - AI-powered development workflows
-
codeam-cli
Workflow-continuity bridge for AI coding agents. Wrap Claude Code or Codex in a PTY and supervise, approve, and redirect the session from any device — async. The terminal companion for CodeAgent Mobile.
-
codexconclave
Build and orchestrate autonomous AI agent teams with a Python framework for structured workflows, observability, and control
-
comandos
Mission control for running many Claude Code agents in parallel — live dashboard, actionable popups with full markdown, voice alerts, tabbed terminals, one-key answers, Telegram remote control. Linux, no cloud, survives reboots.
-
context-generator
Switch AIs without re-explaining everything.
-
copilot-orchestra
🎭 Streamline software development with a multi-agent system that enhances AI-assisted TDD workflows, ensuring quality and speed in coding.
-
CrewLoop
A team of specialized AI agents covering the complete software development flow — from requirements discovery to deploy. One responsibility per agent, specs as source of truth, no shortcuts.
-
crm-with-blockchain-ai-rag
AI-native CRM with RAG pipeline, blockchain-verified deals, and programmable financial rails for modern sales teams
-
cys-terminal
AI agent fleet orchestration terminal — bidirectional socket IPC, resource governance, mission-control dashboard. macOS · Windows. Built largely by AI agents under human direction.
-
DecisionNode
Store and query shared structured memory across Claude Code, Cursor, Windsurf, and any MCP client with a local CLI and MCP server
-
DeepSeek_Science
Rust-first Science Agent Kernel for reproducible, auditable, cache-aware STEM workflows.
-
devlyn-cli
AI development toolkit for Claude Code — ideate, auto-resolve, and ship with context engineering and agent orchestration
-
dispatch
Harness-agnostic Kanban and work dispatch for AI agents working GitHub Issues and PRs.
-
doc2dataset
📄 Ingest documents into structured datasets for LLMs, ensuring numeric integrity and easy export across multiple frameworks with doc2dataset.
-
drt
Reverse ETL for the code-first data stack
-
eos
Does what PM2 and supervisord do: keep your services running,restart on crash, manage logs. Written in Go.
-
evolve-loop
Self-improving AI pipeline that autonomously discovers, builds, audits, and ships improvements to any codebase. 4 agents, 5 phases, eval gating, continuous learning. Plugin for Claude Code & Gemini CLI.
-
forge
Self-hosted lifecycle platform for software powered by Claude Code. Configurable pipelines, devices you control, no credentials on the server. Apache-2.0.
-
Forge
Self-hosted AI coding orchestration dashboard with an Orchestrator, worker queue, providers, GitHub CLI tooling, and local/cloud LLM support.
-
glyph
Glyph is a workbench for composing the forms intelligence takes today — and discovering the language it will speak tomorrow.
-
gossipcat-ai
Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time. Agents that catch real bugs get picked more often. Agents that hallucinate get deprioritized. MCP server for Claude Code, Cursor, and other IDEs.
-
harness-engineering
Provide tools and best practices for building and running long-running AI coding agent harnesses with Claude Code integration.
-
hermes-agent-desktop
Automate desktop tasks and workflows using the Hermes agent for efficient local interaction.
-
hermes-agent-desktop
Automate tasks on your local machine using an AI agent client for Claude, Grok, and Gemini models on Windows, macOS, and Linux.
-
hikizan
Claude Code plugin / Agent Skills pack — verb-split skills for design, review, TDD, and PR flow, with deterministic git hooks as safety floors
-
iosm-cli
Provide a terminal-based AI tool to perform controlled, measurable engineering tasks directly on real codebases.
-
jak-swarm
Public-beta AI workflow operator for founder-led teams: plan tasks, route specialist agents, request approvals, and record audit evidence.
-
jazz-ai
Your terminal. Your agent. Your rules.
-
json-ghost-mannequin-pipeline
👗 Streamline ghost-mannequin photography with an automated 6-step pipeline for e-commerce, ensuring high-quality images and efficient processing.
-
kazi
Make your coding agent actually finish the job. Install one skill and Claude Code keeps working — planning, fixing, testing, deploying — until your goal is objectively true (tests pass, endpoint live, deployed), or it tells you why.
-
koino-insurance-os
RepFlow — insurance agency OS for life & health distribution. Static React + Supabase. Deploys to repflow.koino.capital.
-
LangChain
Framework for building applications with large language models — chains, agents, tools, and retrieval.
-
lead-generation-workflow-automation
🚀 Automate lead generation workflows to save time, capture more leads, and boost marketing team efficiency with streamlined processes.
-
LeMontage
A pipeline-first workflow built for content creators: clips, reels, TikToks, shorts, podcasts and long videos. The goal is to become the TailwindCSS of content creation.
-
lite-research-agents
Coordinate agent brainstorming to generate research proposals and manage future experiment and review workflows
-
llm-wiki
Build a personal LLM wiki using Claude Code with a two-layer cache architecture that integrates with Logseq and Obsidian.
-
loki-mode
Loki Mode by Autonomi. Autonomous spec-to-product system: takes a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief to a deployed app via the RARV-C closure loop with 8 quality gates. Provider-agnostic (Claude Code, OpenAI Codex, Cline, Aider).
-
loopr
A focused CRM that thinks with you built for solo founders running high-touch outbound.
-
Lumi_Agent
Production-ready autonomous AI agent for software engineering, featuring planning, coding, memory, and continuous self-improvement. OPEN SOURCE.
-
maestro
Orchestrate AI coding agents with plain markdown files, no setup, no dependencies, and support for Claude Code, Gemini, Codex, and Cursor
-
mcp-github-pr-issue-analyser
A Model Context Protocol (MCP) application for automated GitHub PR analysis and issue management. Enables LLMs to fetch PR details, analyse diffs, manage issues, and handle releases through a standardised interface
-
mcp-time-travel
Record and replay MCP agent sessions with a transparent proxy to debug tool calls deterministically and step through failures interactively.
-
memroos
MemroOS / memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.
-
metaharness
MetaHarness — mint a custom AI agent harness from any repo. Browser Studio + `npx metaharness` CLI. Runs on Claude Code, Codex, pi.dev, Hermes, OpenClaw, RVM.
-
mongo-orchestration
REST API to manage MongoDB configurations on a single host
-
Multi-Agent-Newsletter-Automation
📰 Streamline newsletter creation with an AI-powered system, automating research, content generation, and delivery using multiple agents.
-
n8n
n8n Workflow Automation Tool
-
n8n-mcp
Integration between n8n workflow automation and Model Context Protocol (MCP)
-
nexus
a methodology for autonomous projects that ship themselves (hands off)
-
nightshift-ai
nightshift is a free Claude Code plugin that turns one terminal into a full software-delivery team — it reads a ticket and ships the spec, plan, code, and review while you sleep.
-
nothumanallowed
Local AI assistant: 80 tools (Gmail, Calendar, Drive, GitHub, Slack, browser, code, files), 38 agents, visual workflows (Studio, AWF, WebCraft). Install with `npm i -g nothumanallowed`, run with `nha ui`. Free tier built-in (Liara), no API key required. Y
-
obsidian-llm-wiki
Convert your Obsidian markdown vault into a six-persona MCP team for local LLM tools to provide cited, accurate insights.
-
obsidian-skills
Use Agent Skills in Obsidian for Claude Code, Codex CLI, and other compatible agents
-
oh-my-iflow
Provide intelligent command-line workflows using multi-agent automation with built-in support for Python, Rust, Go, and shell languages.
-
openclaw-killer
Uninstall OpenClaw completely with a single click, removing all files and traces across macOS, Linux, and Windows systems.
-
openclaw-n8n-stack
Deploy an OpenClaw and n8n Docker stack for AI agents, MCP, and workflow automation in one setup
-
openclaw-orchestrator
Manage complex tasks by breaking goals into subtasks, routing them to specialized agents, and iterating with an LLM-driven real-time orchestrator.
-
opendigitalproductfactory
This is the official open digital product factory
-
openvisio
Cut your AI coding agent's token usage. MCP server + CLI that turns any codebase into a deterministic code graph and serves Claude Code, Cursor, Codex & Windsurf a ranked, token-budgeted query surface — agents query structure (symbols, imports, call edges
-
paneflow
Local-first Rust/GPUI workspace for running coding agents side by side: real terminal panes, live status, worktree review, read-only MCP, and local orchestration.
-
partyline
One wire, every agent — a shared telephone line for Claude Code agents. (It's a JSONL file.)
-
plandb
Manage AI agent task dependencies with a lightweight, local-first SQLite-based tool requiring no configuration.
-
pluidr
Opinionated engineering workflow installer for OpenCode, Plan, Build, Review, Debug.
-
potion
🧪 The magic potion for Claude Code — a lean project framework: plans are prompts, disk is memory, evidence or it didn't happen. Brewed itself to v1.0.0.
-
probot
A framework for building GitHub Apps to automate and improve your workflow
-
ProseForge-Agent
General agent runtime with a built-in ProseForge writing workflow pack.
-
pyspark-etl-automation
🚀 Automate ETL processes with PySpark to transform and load transactional data into PostgreSQL for efficient analytics.
-
python-expert-agent
Provide Python automation with specialized skills and subagents using FastAPI patterns for efficient local project management.
-
Qyvaria
Qyvaria OS and Qyvaria AI Software: an open-source AI engineering platform with qyvaria.py kernel corpus, local AI workflows, agents, monitoring, prompt generation, QyChat, AI BIOS, and hard-logic automation.
-
rag-ready-extractor
Convert webpages and PDFs into clean, structured data optimized for retrieval-augmented generation in a single API call.
-
redcube-ai
Agent-first visual deliverable gateway for experts and PIs, spanning PPT decks and Xiaohongshu posts.
-
repo-digest
📦 Transform any code repository into an AI-ready text bundle, enhancing analytics and enabling smarter code reviews and documentation.
-
RExecOP
Regulated Execution Operations control-plane for profile-defined workflows, governed by GovEngine and recorded through SCLite receipts and evidence.
-
reyn
AI agent workflow OS . Constrained, validated, replayable execution. Predictability over autonomy.
-
rilable
Build iOS apps on your iPhone using AI agents that compile code in the cloud, manage sandboxes, and deploy directly to your device.
-
sciwin
🦀 SciWIn: Reproducible computational Workflows made easy!
-
sdlc-ai-workflow
Complete SDLC Workflow Plugin for Claude Code: 26 agents, 43 skills, 14 commands, 6 phases. Covers planning → design → development → testing → deployment → operations, with industry-standard SDLC best practices embedded in every agent.
-
skill-olympus
Twelve Greek gods. One command. A working SaaS. 98 skills + 49 agents + 13 hooks for Claude Code + Codex CLI + Gemini CLI. Cross-CLI persistent memory, zero-interaction full pipeline (design → build → inspect → test → ship).
-
skills-tracker
Real-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend
-
SM-Live-TV
Automatically updated list of (SM LIVE TV) Live Matches Links (provided as json-file or PlayList)
-
soleur
The Company-as-a-Service platform. Build, ship, and scale -- powered by AI teams.
-
specrails-core
AI agent workflow system for Claude Code — installs 12 specialized agents, orchestration commands, and persona-driven product discovery into any repository
-
squadrant
Multi-project orchestration for your coding agents (Claude, Codex, opencode, Gemini)
-
stream-chain
Chain functions, generators, Node streams, and Web streams into a pipeline with backpressure support.
-
swarmux
Manage and control tmux sessions with agents for efficient local coding task orchestration using validated machine-readable commands.
-
takt
Workflow control for AI coding agents
-
Task-Management-Dashboard
Manage, track, and organize tasks with a React and TypeScript dashboard featuring real-time search, filters, views, and automatic browser saving.
-
taskflow
A task and workflow management system with scheduling and automation.
-
the-frame-ai
FRAME — Framework for AI-Assisted Solo Development
-
the-last-harness
The last harness you'll ever need.
-
The-Senior-Dev-s-LLM-Prompt-Library-100-Production-Ready-System-Prompts
Build production-ready LLM system prompts for senior dev workflows, from React and SQL to refactoring and architecture.
-
TO-BE-CEO
Model startup decisions by guiding raw ideas through research, team debates, and board approval using a structured AI-driven process.
-
tradingview-selenium-fixed-time-trading-automation-bot
🤖 Automate fixed-time trading by executing trades based on TradingView signals through Selenium browser control, ensuring reliable and efficient trade management.
-
tron
A deterministic supervisor that builds software from specs — one agent you talk to; it runs the fleet.
-
uspto_fpd_mcp
🚀 Improve patent analysis with a high-performance MCP server for USPTO Final Petition Decisions, featuring context reduction and customizable fields.
-
vibe-engineering
Deliver and enforce engineering discipline with 38 proven skills and a CLI designed for real-world multi-agent CI/CD workflows.
-
vibestrate
Every vibe-coder needs a CTO! Let Vibestrate supervise your favorite AI models. You name the work - he makes sure it ships!
-
vogon-runtime
Vogon Runtime is a Rust toolkit for deterministic, replayable AI workflows: structured prompts, provider-agnostic adapters, reproducible runs, and verifiable replay logs.
-
voriya-skills
Convert website capabilities into reusable, API-first AI skills with automated authentication and seamless integration for workflow automation.
-
Wakeflow
Dual-host Wakeflow plugins for Codex and Claude Code: controller state roots, task packages, direct-thread/session delivery, evidence review, and local-first runtime.
-
Wardian
Modular, local-first desktop habitat for agents, workflows, and reusable context.
-
zen-gitsync
Auto commit, scheduled sync, and visual GUI for Git. Run `g` in any repo for one-key commit & push, AI commit messages, scheduled background sync, and a drag-and-drop workflow builder.
-
zero-operators
Autonomous AI research team: write a plan.md, spawn agents, train, verify, and deliver a clean ML repo.
-
MERIDIAN_Brain