Memory for you and your coding agents
A shared memory for the whole project. Connect goals, architecture, decisions, and implementation—so every agent can find its context and leave knowledge for the next session.
Keep the context. Continue the work.
General context on the left. Specific knowledge on the right. Select a node to look inside.
Project overview
Shared contextAtlas gives a team one place to organize its working knowledge. Keep project goals, constraints, terminology, and conventions here so each branch starts from the same context.
Architecture
Project knowledgeKeep the system overview and component responsibilities together. Link each architectural decision to the feature and implementation work it affects.
Feature context
Work in progressStart with sign-in requirements and acceptance criteria. Branch into session behavior, callback implementation, and verification without losing the feature’s goal.
Research & sources
Findings recordedRecord sources, findings, and unanswered questions. Connect a useful finding to the decision it informs, so later agents can inspect the reasoning.
Architecture decision
Accepted decisionWe chose server-side sessions so access can be revoked centrally. The decision links to authentication work and records the alternative we considered: long-lived client tokens.
Implementation & review
Review recordedLink the session callback’s Git branch, pull request, and reviewed revision. Record review findings beside the implementation and keep fixes connected to those findings.
Verification details
Verification recordedRecord the tested revision and results for revoked, expired, and valid sessions. Connect each result to its requirement and preserve any remaining limitations.
One connected project. Many paths into the knowledge you need.
Let the structure carry the context
Goals, constraints, and conventions give the project a common starting point. Connect specific work back to the larger reason for doing it.
An agent working on authentication can move from project context to architecture, requirements, and the details of its task.
Record decisions, findings, code references, and verification where they belong. Later sessions can build on what the project already knows.
Across sessions, agents, and tools
Your workflow saves the useful context in Knowen. A connected agent can find it, follow the relevant decisions, and add what it learns back to the project.
See how agents share a Kanban task →One idea can belong in more than one place
A decision can connect to architecture and a feature. A finding can inform several tasks. Keep the knowledge together while giving each agent a path to the detail it needs.
Make memory part of the workflow
Start with purpose, terminology, conventions, and architecture. Add decisions with reasons, research sources, task plans, review findings, and verification as work develops.
Through MCP, compatible agents can search and read accessible project knowledge, then write useful results back. Your workflow determines what to record and when to consult it.
Open the MCP setup guide →Yes. Knowen supports multiple paths to the same knowledge node, so a decision can belong to the architecture and the feature that uses it.
Use content history and comments to inspect how knowledge evolves. Grant collaborators access to your project, and publish knowledge when you choose to share it more broadly.
A place to pick up where you left off
Create a project, give it context, and connect the coding agents you already use.
Account creation is by invitation during beta. You can explore public knowledge as a guest.
01Create a project
02Add goals, decisions, and context
03Connect through MCP