Agent Workflows & Frameworks for Claude Code
Methodologies and orchestration layers on top of your coding agent: spec-driven development, task planning and parallel agents. Every listing below works with Claude Code. Free GitHub projects and paid options are ranked together.
Updated October 2026 · 43 listings · stars refreshed daily from GitHub
How to add agent workflows & frameworks to Claude Code
Subagents are Markdown files with YAML front matter in ~/.claude/agents/ (personal) or .claude/agents/ (project). Run /agents inside Claude Code to create, edit and set their tool permissions.
Spec Kit 🤖 AgentFree
GitHub's toolkit for spec-driven development with AI coding agents
Task Master 🤖 AgentFree
AI task management that turns a PRD into tasks your coding agent works through
Fast Agent 🤖 AgentOpen source
Python framework for building, orchestrating and evaluating MCP-native AI agents
OpenSpec 🤖 AgentFree
Lightweight spec-driven development: agree on changes before the agent codes
CC Safety Net 🤖 AgentOpen source
Pre-execution guard that blocks destructive commands and secret access for coding agents
BMAD Method 🤖 AgentFree
Agile AI-driven development with analyst, PM, architect, developer and UX agents
Claude Squad 🤖 AgentFree
Manage multiple terminal agents in parallel in separate workspaces
cc-sdd 🤖 AgentOpen source
Spec-driven development harness with Agent Skills and long-running autonomous implementation
Ruflo (Claude Flow) 🤖 AgentFree
Agent orchestration platform for running swarms of Claude Code agents
MemSearch 🤖 AgentOpen source
Persistent cross-platform memory for coding agents, backed by Markdown and Milvus
Claude Code Workflows 🤖 AgentOpen source
Development recipes that keep Claude Code's exploration focused on the approved outcome
Agents CLI 🤖 AgentFree
Google's official CLI and skills for building AI agents on Google Cloud with any assistant
claude-devtools 🤖 AgentOpen source
Visual inspector for Claude Code sessions: tool calls, diffs, tokens, subagents and context
SuperClaude Framework 🤖 AgentFree
Configuration framework that adds commands, personas and modes to Claude Code
Claude Octopus 🤖 AgentOpen source
Run multiple AI models against one task and surface disagreements before you ship
Maestro 🤖 AgentOpen source
Multi-agent orchestration with 39 specialists, phased workflows and persistent sessions
Harness 🤖 AgentOpen source
A meta-skill that designs domain-specific agent teams and generates the skills they use
DeerFlow 🤖 AgentOpen source
ByteDance's self-hosted agent harness with subagents, sandbox, memory and skills
Oh My Claude Code 🤖 AgentOpen source
Multi-AI orchestration plugin coordinating Claude, Gemini and Codex workers inside Claude Code
Claude Codex Bridge (CCB) 🤖 AgentFreemium
Multi-agent terminal UI that coordinates Claude, Codex, Gemini and other CLI agents in one workspace
Babysitter 🤖 AgentOpen source
Code-defined agent workflows with quality gates, approval breakpoints and resumable journals
evo 🤖 AgentOpen source
Autoresearch loop that has coding agents run gated optimisation experiments on your codebase
Claude Code Agent Monitor 🤖 AgentOpen source
Self-hosted real-time dashboard for Claude Code and Codex sessions, agents, tools and cost
Citadel 🤖 AgentOpen source
Routing, repo-local memory, guarded workflows and handoffs around Claude Code and Codex
Agent Swarm 🤖 AgentOpen source
Self-hosted operating system for delegating work across a lead agent and Docker worker agents
nWave 🤖 AgentOpen source
Seven-wave, human-gated workflow from idea to TDD-delivered code inside Claude Code
Hivemind 🤖 AgentFreemium
Shared, searchable session memory that turns agent traces into team skills
Claude Forge 🤖 AgentOpen source
All-in-one Claude Code kit of agents, commands, skills, safety hooks and adversarial review
Oh My Subagents 🤖 AgentFree
Local orchestration for Claude and Codex subagent teams with durable, recoverable state
OpenEvolve 🤖 AgentOpen source
Open-source AlphaEvolve-style framework that evolves code using an LLM ensemble
Ouroboros 🤖 AgentOpen source
Spec-first workflow engine that runs an interview-evaluate-evolve loop over coding agents
Autoprompt 🤖 AgentOpen source
Installs a plan, build and independent-review loop into your coding agent
Codeman 🤖 AgentOpen source
Self-hosted mission control to run and monitor terminal AI coding agents from any browser
Claude Code Hooks 🤖 AgentOpen source
Audio and voice feedback on every Claude Code hook, with a fully documented hook reference
Obelisk 🤖 AgentOpen source
Index past coding-agent sessions into local SQLite, queryable by your agent and browsable by you
SWE-ATLAS 🤖 AgentOpen source
A senior-engineer layer for Claude Code: explore and clarify before the native build loop
Subtask 🤖 AgentOpen source
Claude Code skill and CLI to run tasks as subagents in parallel Git worktrees
Gemini-GPT Hybrid 🤖 AgentOpen source
Claude Code subagents that route work to Gemini or GPT by scope, then review before writing
AI-Driven Development 🤖 AgentOpen source
Cross-agent skills for disciplined AI development, plus a Bash safety hook for Claude Code
Yume 🤖 AgentFreemium
Native desktop UI for the official Claude Code CLI with orchestration and background agents
pstack for Claude Code 🤖 AgentOpen source
Port of Cursor's pstack playbooks for verified bug fixes and features
My Claude Devteam 🤖 AgentOpen source
An engineering team in a box for Claude Code: role-based agents plus safety and quality hooks
Fluent Korean 🤖 AgentOpen source
Claude Code output style that makes the agent write clear, natural Korean
More for Claude Code
🧩 Skills for Claude Code (68) 🔌 MCP Servers for Claude Code (74) Claude Code review
Popular searches
- Subagents for Claude Code
- Subagent collections for Claude Code
- AI code review agents for Claude Code
- Skills for Claude Code
- Development workflow skills for Claude Code
- Community skill collections for Claude Code
- MCP servers for Claude Code
- Docs & code context MCP servers for Claude Code
- Developer tool MCP servers for Claude Code
- Claude Code alternatives