CortexGraph Vault

Apersonalcontextgraphforhumans&agents.

CortexGraph is a markdown-native personal context graph and agent context graph where your notes, sources, decisions, and agents share the same durable context. It gives humans and AI systems a common memory layer they can actually build on together.

cg_vault_runtime_v1.0.2
_
The Current State

Most AI workflows are entirely stateless.

Even when agents record history, it's siloed in their specific platform. You ask a model for help, get an answer, and the context fades into chat history or a proprietary database. Prompts get longer. Cross-collaboration becomes impossible.

The Paradigm Shift

Build a personal context graph instead.

  • 01Notes connect to notes natively
  • 02Sources connect to conclusions
  • 03Agents leave visible, durable trails
  • 04Checkpoints make complex work resumable

System
Architecture

MULTI_ACTOR

Agents Share Context

Our architecture is completely harness-agnostic. Let ChatGPT read a thread, have a self-hosted Ollama model summarize it, and let a custom autonomous agent execute the result—all sharing the exact same reality.

MD_NATIVE

Markdown Default

Built on plain markdown files. Portable, inspectable, and future-proof.

DURABLE

Decision Traces

Preserve who did what, what changed, and what decisions were made.

PROTOCOL_MCP

MCP Connectivity

Use your vault across tools and clients through the Model Context Protocol. Connect external agents to a shared context graph.

The Operating
Loop

01

Capture

Ingest notes, web research, and external sources.

02

Organize

Turn raw material into typed primitives and shared threads.

03

Collaborate

Let multiple agents update notes and leave checkpoints.

04

Resume

Return to active threads and unresolved work with full context.

Active Context Seeking

Agents that know
when to ask.

When autonomous workers hit a clarity gap, they shouldn't guess or hallucinate. Instead, they ping the context graph. Cortex then proactively reaches out to you via iMessage to clarify ambiguities, feeding the answer back to the agent.

CortexiMessage
Agent 'research-01' is summarizing the Q3 roadmap but hit a roadblock. The doc mentions a "Phase 2 Pivot", but there are no notes explaining what it is.
Was this decision documented somewhere, or can you clarify the pivot?
Ah right. We dropped the standalone app idea and decided to build it as an MCP server instead.
Got it. I've updated the context graph with that decision and pinged 'research-01' to resume the summary.
iMessage