knowns

Stores project tasks as markdown files in .knowns/tasks/ directory with Git-friendly format, enabling AI agents to maintain persistent memory across sessions. Tasks include acceptance criteria, implementation plans, and @doc/path/@task-N references that create a context graph. When an AI agent is assigned a task, it parses all embedded references, recursively follows links to documentation, and builds a complete context graph before implementation — solving the stateless AI problem where context must be re-explained each session.

Implements a Model Context Protocol (MCP) server that exposes the task and documentation system to AI agents via standardized protocol bindings. When an AI agent connects via MCP, it can query tasks, resolve references, and retrieve full context graphs without parsing markdown directly. The MCP server translates internal FileStore operations into MCP resource and tool endpoints, enabling seamless integration with Claude, GPT, and other MCP-compatible agents.

Implements knowns as a TypeScript codebase that compiles to JavaScript and runs on Node.js, Deno, and browser runtimes. The build system uses Vite for bundling and supports multiple entry points (CLI, server, web UI). Core logic is runtime-agnostic, with platform-specific adapters for file I/O, HTTP, and other system operations. This enables the same codebase to run as a CLI tool, HTTP server, web application, and embedded library.

Provides a React-based web interface that renders the same task and documentation data as the CLI. The web UI includes a Kanban board for visual task management, a documentation browser for exploring linked docs, and a task detail view with full context. The UI communicates with the knowns server via HTTP API and WebSocket for real-time updates. All UI state is derived from the FileStore, ensuring consistency with CLI and other interfaces.

Parses @doc/path and @task-N reference syntax embedded in task descriptions and documentation, then recursively resolves all linked documents to build a complete context graph. When an AI agent requests a task, the system traverses the reference tree, fetches all linked documentation, and returns a flattened context structure. This enables AI agents to understand not just the immediate task but all architectural decisions, patterns, and related work that inform implementation.

Provides a command-line interface (knowns/kn commands) for creating, updating, and organizing tasks and documentation with built-in Kanban board state management. Tasks move through predefined states (backlog, in-progress, review, done) tracked in markdown frontmatter. The CLI supports batch operations, filtering, and status transitions. A companion web UI (React-based) renders the same data as a visual Kanban board, with both interfaces operating on the shared .knowns/ file store.

Maintains a version history of all task and documentation changes using a VersionStore layer that tracks file mutations over time. Each change is recorded with timestamp and metadata, enabling rollback to previous states. The versioning system operates transparently on top of the FileStore, capturing all mutations whether they come from CLI, web UI, or API calls. This enables audit trails and recovery from accidental deletions or edits.

Stores project documentation as markdown files in .knowns/docs/ with YAML frontmatter for metadata (title, tags, created, updated). Documentation supports standard markdown syntax plus knowns-specific reference syntax (@doc/path, @task-N) for linking to other docs and tasks. The system treats documentation as first-class entities that can be queried, linked, and versioned alongside tasks. A documentation browser in the web UI enables visual navigation of the doc structure.

Exports task and documentation context as plain text (via --plain flag) in a format optimized for AI agent consumption. The export includes task details, acceptance criteria, implementation plans, and all recursively resolved linked documentation in a single text block. This enables AI agents without MCP support to access full context by reading a single text file or stdout. The export format is designed to be token-efficient while preserving all relevant information.

Tracks time spent on tasks and estimates effort through YAML frontmatter metadata (estimated hours, actual hours, time logs). Tasks maintain a time log of work sessions with timestamps and duration. The system enables reporting on effort vs. estimate, identifying tasks that exceed estimates, and tracking team velocity. Time data is stored in markdown frontmatter, making it Git-trackable and queryable.

Provides search and filtering across tasks and documentation using tag-based queries and basic full-text matching. Tags are stored in YAML frontmatter and indexed for fast lookup. The CLI supports filtering by tag, status, and other metadata. Search results can be piped to other commands for batch operations. The system maintains a simple in-memory index of tags and metadata for fast filtering without external search infrastructure.

Exposes task and documentation data through a REST-like HTTP API and WebSocket protocol for real-time updates. The API supports CRUD operations on tasks and docs, query operations for filtering and search, and WebSocket subscriptions for live updates when data changes. The server layer (Node.js HTTP server) translates API requests to FileStore operations, enabling programmatic access without CLI. WebSocket connections enable real-time synchronization between multiple clients (CLI, web UI, external tools).