#agentic-workflows

A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。

Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub Copilot, and more) work as teammates in channels, threads, DMs, and shared tasks. Your data stays on your machines.

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-agent backends through an MCP server + CLI.

🔁 Build reliable recurring AI-agent systems: 1025 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.

Skill repository to enforce Engineering disclipline in coding assistants

Agent permission firewall for MCP tools, shell, files, and x402/Base payments.

Fable 5 workflow Loop; A Claude Code skill: autonomous build / audit / verify loop that runs until a machine-checkable contract passes, with ▎ deterministic anti-spin stop conditions (no-progress, retry, oscillation, budget) and on-disk human escalation.

Local-first AI agent platform with a Tauri desktop app and Rust CLI. Run governed tools, durable sessions, multi-agent workflows, modular packages, and one-shot effect permits.

Behaviour trees for AI agents. Define agentic workflows in YAML, drive deterministic agent runs from a CLI works with any agent, Claude, Codex, Copilot, Gemini etc.

A curated, credited library of loops — repeatable AI-agent workflows for Claude Code, Cursor & Codex. Refactor until clean, test until 100%, hunt bugs until none remain.

Source-bound evidence and release assurance for AI-written code.

Delegate work to isolated sub-agents inside the pi coding agent — proven multi-agent patterns with safety, cost caps, and tracing built in.

Run an autonomous AI company from your iPhone. Boardroom turns Hermes on your Mac into a local-first team that scouts, debates, builds, runs QA, and reports to you.

Autonomous software factory: give it a plan, get a verified, merged codebase. Pull-based agents (Claude Code, OpenCode, Codex) in a sandboxed rig, with a Beads ledger, typed railway-oriented Rust, and done-means-verified.

WorkBuddy Skill Atlas: search 21k+ public Agent Skills, inspect immutable provenance, and install reviewed WorkBuddy packages.

A Spec-Driven State Machine for AI Agents. Enforces structured workflows, parallel worktrees, and zero-config GitHub sync for Agentic Software Engineering.

Turn Claude Code into a phase-aware, multi-team software factory: hard-gated pipeline, Clean Architecture + Effect standards, adversarial review, token discipline.

How one person runs a full AI automation agency on Claude Code - memory architecture, skills, subagents, hooks, quality gates, and the daily loop that replaced a team. Free guide, no signup, no email gate.

⚡ Crash-consistent Two-Phase Commit (2PC) & WAL engine for AI agent workflows. Zero dirty state, zero hallucinated rollbacks.

Agent Memory Kit System: Capture every correction and interaction to build your own SLM from day one

Best OpenCode Fork with Task DAGs & Semantic Retrieval 2026 - Stateful Agent Workbench

Static analysis for AI automation workflows. Find prompt-injection paths, overpowered tools, and write-capable agent jobs before they run.

Hermes Agent starter kit for safe scheduled, stateful AI-agent loops

A local, multi-agent-aware CLI task tracker and fact store for AI coding agents, with humans as a secondary user.

AI Creator Ops: living authority site and data desk for AI creator businesses, synthetic influencers, and creator automation.

An open-source knowledge repository for building, running, and constraining Agentic AI systems.

Technology-neutral playbook and templates for AI agents that publish, secure, document, release, and maintain open-source repositories.

Digital Garage Enterprise

An operating system for a 32-agent AI software org — charters, a file-based board, a gated lifecycle, and Claude Code orchestration.

An agent workspace that turns a description into a finished, distinctively designed static site — for Claude Code, Codex, Gemini CLI, Grok CLI, or any coding agent.

Open-source, ready-to-use agent skills — dispatcher: submit a task list and workers complete every task; deepen-review-push: deterministic scan → implement → review → push pipeline straight to main. Tool-agnostic.

Git-native operating model for reliable AI-assisted project work, continuity, and handoffs.

This repository contains a small experiment that compares a healthy AI agent implementation with a deliberately regressed implementation using Gemini on Vertex AI.

20 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and quality audits (eval-leakage, doc-drift). Works with Claude Code, Codex, and Cursor.

Local-first agent workspace for knowledge, tasks, documents and verifiable workflows · Локальная агентная система для знаний, задач и проверяемых процессов · t.me/romarayt

A GitHub-centered starter kit for AI-assisted project work with tickets, PR evidence, human gates, agent prompts, and an AI Vault.

Voice-first, agent-readable YouTube research and content planning SaaS built with Next.js, Supabase, OpenAI, Firecrawl, and Apify.

Multi-tier autonomous AI agent harness integrating Anthropic Claude 3.5 Sonnet, Google Antigravity, and Hermes with Telegram motion streaming UX