KnoWiki // 0%

HOW IT WORKS

01

RESEARCH & TEMPLATE

Select or construct a KB schema template appropriate to your project. Templates define what sections the KB will contain, what types of knowledge belong in each, and what atomic knowledge units look like.

Decision · Constraint · Architectural Pattern · Agent Skill · Coding Practice · Open Question · Component
02

CODEBASE INGESTION

Ingest your repositories into the platform — source code files, configurations, commit histories, and pull requests. The platform processes these according to your schema.

Automated · Supervised · Manual — you control the analysis scope
03

COMPILED KNOWLEDGEBASE

The output is a structured, version-controlled knowledge system. Queryable. Every good answer gets filed back as a new page. Exploration compounds in the knowledge base just like ingested sources.

Index · Log · Cross-references · Citations · Content hashes
04

AGENT INTERFACE

The platform generates an agent-readable context file from the current KB state. Active constraints, coding practices, architectural patterns, agent skills, open questions — assembled into a structured handoff.

Every developer gets the same behavioral contract. No individual customization. No drift.
05

AGENT CONTRIBUTION

Agents log findings back to the KB. Structural discoveries, new constraints, decisions made during execution — all candidate KB entries with full provenance requirements.

The KB improves as work progresses. Reads are value. Writes are compounding value.

THREE LAYERS

01CODEBASE SOURCESIMMUTABLE
Source code files, configs, dependency graphs,
commit logs, pull requests, and git metadata.
The platform reads from these — never modifies them.
They are the source of truth.
02THE KNOWLEDGEBASECOMPILED
A version-controlled collection of knowledge files
organized into typed sections. The LLM writes
and maintains this layer. Humans review it.
Agents consume it. It grows richer with every interaction.
03THE SCHEMAGOVERNANCE
A configuration document that defines how
the knowledgebase is structured, what conventions
apply, what workflows govern ingestion and updates.
Co-evolved by the team and the platform.
LAYERTRACKSANSWERS
GIT (CODE)What the system isWhat changed
KNOWLEDGEBASEWhy the system isWhy it was built this way

KB HEALTH

STALENESS

Content hash comparison between knowledge claims and source files. When a source changes, all derived claims are flagged for review. Immediately.

CONTRADICTIONS

Periodic passes identify conflicting claims. Contradictions are filed as Open Questions — never silently resolved. The team decides.

ORPHANS

Knowledge pages with no inbound links represent isolated, unintegrated knowledge. Surfaced and flagged for connection or review.

COVERAGE

Analysis against the active codebase identifies components and subsystems with insufficient KB coverage. These become research tasks.

Composite health score — staleness rate, contradiction count, orphan rate, coverage gaps. Visible on team dashboard. Trends over time.

WHAT THIS ENABLES

01

INDIVIDUAL DEVELOPERS

No more reconstructing project understanding on every session. No more manually writing CLAUDE.md. The KB is the configuration. Point the agent, start working.

02

TEAMS

A shared cognitive layer. Every agent on every machine operates with the same constraints, the same architectural understanding, the same coding practices.

03

ONBOARDING

New developers and new agents get full project context from day one. The KB is the onboarding document, the architecture guide, the decision log, and the agent configuration simultaneously.

04

PROJECT CONTINUITY

The KB is the institutional memory. When a developer leaves, their knowledge doesn't leave with them. When a team wants to understand why a decision was made two years ago — checkout the KB at that point in history.

05

MULTI-AGENT

Multiple agents working concurrently consult the same KB. Work trails prevent conflicting changes. The KB becomes the coordination layer, not just the context layer.

WHAT THIS IS NOT

NOT A NOTE-TAKING APPIt is a knowledge compiler and governance system.
NOT A DOCUMENTATION GENERATORThe KB is generated for agents to consume, not just humans to read.
NOT A RAG SYSTEMRAG re-derives knowledge on demand. This compiles and accumulates.
NOT AN AI ASSISTANTIt provides the context layer that makes coding assistants coherent.
A KNOWLEDGE OPERATING SYSTEM
FOR AI-DRIVEN DEVELOPMENT.
> JOIN_WAITLIST.exe
[]