Agent Workflows & Frameworks for OpenCode
Methodologies and orchestration layers on top of your coding agent: spec-driven development, task planning and parallel agents. Every listing below works with OpenCode. Free GitHub projects and paid options are ranked together.
Updated October 2026 Β· 19 listings Β· stars refreshed daily from GitHub
How to add agent workflows & frameworks to OpenCode
Subagents are usually Markdown files with a name, description, tool list and system prompt. Copy the ones you need into your app's agents folder rather than installing a whole pack at once.
Spec Kit π€ AgentFree
GitHub's toolkit for spec-driven development with AI coding agents
Task Master π€ AgentFree
AI task management that turns a PRD into tasks your coding agent works through
Fast Agent π€ AgentOpen source
Python framework for building, orchestrating and evaluating MCP-native AI agents
OpenSpec π€ AgentFree
Lightweight spec-driven development: agree on changes before the agent codes
CC Safety Net π€ AgentOpen source
Pre-execution guard that blocks destructive commands and secret access for coding agents
cc-sdd π€ AgentOpen source
Spec-driven development harness with Agent Skills and long-running autonomous implementation
MemSearch π€ AgentOpen source
Persistent cross-platform memory for coding agents, backed by Markdown and Milvus
Oh My OpenAgent (OmO) π€ AgentFree
Multi-model agent orchestration for OpenCode and Codex: type ultrawork, agents run to done
Claude Octopus π€ AgentOpen source
Run multiple AI models against one task and surface disagreements before you ship
Claude Codex Bridge (CCB) π€ AgentFreemium
Multi-agent terminal UI that coordinates Claude, Codex, Gemini and other CLI agents in one workspace
Babysitter π€ AgentOpen source
Code-defined agent workflows with quality gates, approval breakpoints and resumable journals
evo π€ AgentOpen source
Autoresearch loop that has coding agents run gated optimisation experiments on your codebase
Agent Swarm π€ AgentOpen source
Self-hosted operating system for delegating work across a lead agent and Docker worker agents
nWave π€ AgentOpen source
Seven-wave, human-gated workflow from idea to TDD-delivered code inside Claude Code
Autoprompt π€ AgentOpen source
Installs a plan, build and independent-review loop into your coding agent
Codeman π€ AgentOpen source
Self-hosted mission control to run and monitor terminal AI coding agents from any browser
Subtask π€ AgentOpen source
Claude Code skill and CLI to run tasks as subagents in parallel Git worktrees
AI-Driven Development π€ AgentOpen source
Cross-agent skills for disciplined AI development, plus a Bash safety hook for Claude Code
pstack for Claude Code π€ AgentOpen source
Port of Cursor's pstack playbooks for verified bug fixes and features
More for OpenCode
π§© Skills for OpenCode (53) π MCP Servers for OpenCode (73) OpenCode review