Project dashboard
A command center for progress, status, task flow, and project activity.
Open source project memory for teams and AI
Every task, decision, and pattern stays connected.
Knowns keeps tasks, docs, and decisions linked, searchable, and ready for every coding agent.

Tasks
Linked to the same project state.
Docs
Linked to the same project state.
Memory
Linked to the same project state.
Knowns keeps the working state readable for people and coding agents.
Bring tasks, docs, decisions, and context into one place.
Connect related work, patterns, and dependencies.
Validate with your team, agents, and automated checks.
Institutional memory that stays accurate and useful.
Actual Web UI
Knowns is not just a CLI surface. The browser UI gives teams and agents the same project graph with board views, task detail, documentation, and relationship maps.
Included surfaces
A command center for progress, status, task flow, and project activity.
Move work through status columns while keeping every task tied to project context.
Open a task with acceptance criteria, references, notes, and progress in one focused view.
See how tasks, docs, memories, and decisions connect before changing the system.
Browse project documentation next to the same graph and task relationships.
Knowns turns scattered project traces into a working memory layer your team and agents can read.
A simple cycle that keeps knowledge connected.
Write down what needs to happen and what 'done' means.
Connect tasks to docs, specs, templates, and past decisions.
Your AI reads the full context and follows the plan.
Check acceptance criteria before marking complete.
Extract patterns and decisions for next time.
Real-world examples of using Claude Code with Knowns skills.
Use /kn-research, /kn-plan, /kn-implement, and /kn-extract to implement dark mode in a Flutter project.
All skills use the /kn-* namespace. View full workflow guide →
Six capabilities that work together. One connected system.
Plan work with acceptance criteria, linked specs, and progress tracking.
Keep project knowledge searchable, versioned, and close to work.
Reuse proven workflows instead of starting from scratch.
Explicit links between tasks, docs, and decisions. Nothing orphaned.
Find anything by meaning, not just keywords. Semantic search built in.
Give AI assistants structured project memory via MCP integration.
Knowns helps people and AI agents start from the same context.
You build projects across multiple sessions. Knowns remembers your architecture decisions, tracks what's done, and gives your AI the full picture every time you start working.
Multiple people and AI agents working on the same codebase. Knowns ensures everyone — human or AI — works from the same structured context. No conflicting assumptions.
Specs, tasks, and acceptance criteria live in one connected system. When engineering picks up a task, the full context is already there — linked docs, related decisions, and clear definition of done.
Most tools cover one slice. Knowns connects them all.
| Knowns | BMAD Method | Spec Kit | Backlog.md | mem0 | Claude Memory | Cursor / Windsurf rules | Repomix | |
|---|---|---|---|---|---|---|---|---|
| Structured tasks with ACs | Story-like | Spec tasks | ||||||
| Linked specs & docs | Partial | Specs only | ||||||
| Semantic search | Partial | |||||||
| Project memory across sessions | Process only | Static rules | ||||||
| Templates & code generation | Rule templates | |||||||
| AI agent context (MCP) | Via integrations | Third-party | Hooks | |||||
| Validation & coverage checks | Process QA | Partial | ||||||
| Web UI (kanban, docs, chat) | API only |
Install, initialize, and your AI assistant is connected.
Multiple install paths are available including Homebrew, shell script, PowerShell, npm, and `npx`. npm-based installs still need Node.js 20+. Download Node.js
After a new release, update your installation then run:
This keeps your skills and agents always up to date.
Need help? Read the documentation or open an issue
Start with one project. See the difference in your next AI session.
Open source · Local-first · MIT License · No vendor lock-in