#agentic-workflow

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done claims, patch sprawl, and tool loops in your Claude Code session.

An autonomous orchestrator for the Copilot Go SDK in Neovim, delivering a native, agentic coding experience.

BLXCode is an open-source desktop workbench for running AI coding agents beside real terminals, project memory, tasks, and an embedded browser. It is built with Tauri 2, Rust, Leptos, and Trunk.

A session-based working method for coding agents: plan in thin complete slices, build one at a time, verify by observing real behaviour, hand off cleanly. Skills + agents + 2 hooks for Claude Code.

Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. 87 subagents + skills, TDD defense-in-depth gates, Kaizen retros, a four-body adversarial council, and an empirically benchmarked QA harness. Does it hang true?

The orchestration repository for the Burnout 5 / Burnout Paradise decompilation. Includes tools, IDA databases, and reference files to assist agentic reconstruction of the game's C++ source code.

A shared knowledge vault + full software-engineering workflow for AI coding agents — run Claude Code and Codex in parallel with one memory, one plan.

Stateful agentic engineering workflow for local coding agents

Customizable agentic writing kit for writing, editing, polishing, and reviewing prose without AI smell.

API workspace in plain markdown. Design specs, send requests, validate contracts from CLI, browser, and coding agents.

Multi-agent Claude Code pipeline: spec → plan → parallel impl in worktrees → integration tests → two-tier review → smoke → PR. 13 sub-agents, 7 slash commands, calibrated on 222 completed tasks.

Agentic BI: Semantic and Ontology-driven Data Agent for natural language data Q&A，analysis，insights，and action recommendations.

A Claude Code plugin for Java & Spring Boot backend engineers that turns one task into a gate-enforced 7-phase agentic workflow — Discover → Brainstorm → Spec → Plan → Implement → Review → Learn. Native hooks, 11 subagents, path-scoped rules, project memory & strict test-first TDD.

Agentic workflow kit for any AI coding harness. One command wires OpenCode, Claude Code, Codex and Cursor with a coordinated swarm, persistent memory that survives restarts, a 24-agent squad and a 5-gate delivery workflow. Zero runtime dependencies.

Bedside: manners for AI agents that operate tools for smart, high-judgment non-experts. Ship and test, not only write.

AI workflow installer: 5-layer docs structure + GitHub Issues triage loop for Claude Code projects

Architectural taste for TypeScript coding agents. Minimize conceptual surface area, create boundaries deliberately, and generate code humans can navigate, review, and evolve.

Battle-tested multi-agent dev team for Claude Code — 9 specialized sub-agent templates + a 6-stage pipeline with agent memory, verdict protocols, commit checkpoints & standing review prompts. CLAUDE.md constitution, bug-pattern library, full Laravel + React example. Bilingual EN/AR. Extracted from a production app with 200+ releases.

Nightshift is an overnight AI agent harness that fixes bugs, manages TODOs, and implements features across your projects while you sleep, with a morning digest waiting when you wake up.

A disciplined 10-stage autonomous agent pipeline (Reflexion, Tree Search, ReAct) for Claude Code and AI coding agents. Lifts local LLMs to senior engineering quality.

Universal Agent Skill: builds anything with infinite disk memory and a two-brain team — typed consent gates, reproducible claims. Works with Claude Code, Codex, Antigravity.

Spec-driven development workflow for Claude Code — built around an approved design doc, where each stage waits for your approval.

An agent control plane for governed, replayable execution.

Persistent self-improving AI teammates with memory, skills, and schedules.

A vendor-agnostic runtime for orchestrating multiple AI agents across tools, models, and environments.

Agentic service that translates CI/CD pipeline definitions between Jenkins, GitLab CI, and GitHub Actions using a pluggable LLM (Gemini, OpenAI, Azure OpenAI, GitHub Models, Anthropic, or Ollama), LangGraph memory, and an MCP (Model Context Protocol) tool surface.

Local-first product analysis agent that researches supporting and opposing evidence and produces auditable reports｜本地优先、可核验的产品潜力分析 Agent

Startup Agent Skills Hub

SegAgent-AI: A Dockerized AI Platform for Industrial Defect Segmentation, Severity Analysis, and Cloud Deployment

Cookiecutter template for standardized agent deployment and setup.

SPEC-First AI DevKit for Agentic Code 2026 — 24 Agents, 52 Skills, TDD/DDD Gates

Template-driven HTML wiki and persistent knowledge harness for AI agents. Runs standalone or as an OpenProgram program.

Semi-autonomous issue-to-PR pipeline with cost-ordered routing across local and cloud LLMs.

An evidence-gated maker-checker-auditor workflow for agentic development, with mechanical enforcement for Claude Code.

Keep your Claude Code agents lean and in control — bounded agent loops, per-agent model routing, and real per-model token measurement.

Terminal-first multi-agent runtime for building, testing and releasing games and apps with Claude Code, Codex and GigaChat.

A set of specialist AI agents for building software solo. Installs into Claude Code with one command.

An open, project-agnostic operating model for running projects as a small company of AI agents — one manager, specialized departments, and a method that carries to your next project. Built for Claude Code.

JobPilot is a full stack AI-powered job hunting assistant. The user sets up their profile once, uploads their resume, and the agent automatically discovers relevant jobs from Adzuna