Trellis and task-trellis-mcp
These are **complements**: Trellis provides the foundational AI framework and toolkit, while Task Trellis MCP extends its capabilities by adding specialized project decomposition and task tracking features through the Model Context Protocol interface.
About Trellis
mindfold-ai/Trellis
All-in-one AI framework & toolkit
Provides structured AI coding through auto-injected project specs, task-centered workflows with git worktrees for parallel execution, and shared team standards stored in `.trellis/` that sync across 10+ AI coding platforms (Claude, Cursor, Codex, Gemini CLI, and others). Context is preserved across sessions via workspace journals, eliminating the need to re-explain project conventions to each new agent.
About task-trellis-mcp
langadventurellc/task-trellis-mcp
Greatly improve how AI coding agents handle complex projects. Task Trellis helps track requirements for projects, breaks them down into smaller manageable parts until you have trackable and assignable tasks with built-in workflow management, dependency handling, and progress tracking. Basically, it's like Jira for coding agents.
Implements as an MCP (Model Context Protocol) server with local Markdown-based storage, exposing structured tools for hierarchical issue management (Project → Epic → Feature → Task) and automated workflow operations like dependency validation and file-change tracking. Designed for integration with Claude and other MCP-compatible AI agents, it enables multi-session continuity by persisting project state locally rather than relying on agent memory alone.
Scores updated daily from GitHub, PyPI, and npm data. How scores work