> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pnbr.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Give every agent the same world to reason from

> Penumbra gives agents a governed, source-backed model of your domain, available through MCP in the harness where work already happens.

Codex, Claude Code, Cursor, and similar tools are agent harnesses: they provide
a capable model, a workspace, and tools for the work in front of it. What they
do not provide is a durable, governed understanding of your domain.

Every new session begins with a reconstruction: a prompt, a handful of files,
search results, and whatever context happens to fit. The pieces may be accurate
while the overall meaning still drifts. A customer, a risk, or a decision can
mean something different to each agent, with no durable record of why.

Penumbra provides that cognitive substrate: a shared model of your domain that
persists across agents and sessions. Sources remain attached to the knowledge
derived from them. Shapes express the types, relationships, and standards that
matter. Consequential changes can be inspected before they become shared
truth.

<Columns cols={2}>
  <Card title="Connect your agent" icon="plug" href="/getting-started/connect-agent">
    Add Penumbra to Codex, Claude, Cursor, or another MCP-capable harness.
  </Card>

  <Card title="Run the first workflow" icon="play" href="/getting-started/quickstart">
    Save a source, retrieve it, and verify the exact wording in a few minutes.
  </Card>
</Columns>

```mermaid theme={null}
flowchart LR
  S["Your sources<br/>documents · systems · conversations"] --> P
  F["Your frameworks<br/>types · relationships · standards"] --> P
  P["Penumbra<br/>governed cognitive substrate"] --> M["MCP"]
  M --> H["Your agent harness<br/>Codex · Claude · Cursor · others"]
```

## Why coherence beats more context

Longer context windows and better retrieval are useful, but they solve a
different problem. They help an agent see more material in one moment. They do
not decide what that material means, preserve the provenance of an
interpretation, or keep the interpretation consistent across tools and time.

Penumbra holds the layer those systems leave implicit: the domain model,
source-backed knowledge, review state, and memory agents use to orient
themselves. Different agents can then enter the same project with the same
definitions, evidence, and operating boundaries.

## One shared substrate, three capabilities

<Columns cols={3}>
  <Card title="Shape the domain" icon="shapes" href="/shapes/overview">
    Make your way of understanding a domain explicit as types, fields, relationships, and constraints.
  </Card>

  <Card title="Work from evidence" icon="database" href="/runtime/overview">
    Let agents find sources, retrieve structured knowledge, and stage reviewed changes against a live project.
  </Card>

  <Card title="Carry what matters" icon="brain" href="/memory/overview">
    Preserve decisions, preferences, and lessons across sessions without confusing memory with source-backed truth.
  </Card>
</Columns>

Shapes, Runtime, and Memory are separate MCP servers because they govern
different kinds of work. Together, they let an agent understand the project it
has entered, act within its boundaries, and return reviewed knowledge or
proposed changes to the same project.

## Use it in the harness you already have

MCP makes the substrate available without forcing the work into a new chat
surface. Codex, Claude Code, Claude.ai, Google Antigravity, Cursor, and other
harnesses keep providing the agent, workspace, and interaction model. The
Penumbra MCPs give that agent access to the persistent project.

Connect the MCPs in the harness where you already work, then describe the
outcome in plain language. The agent can inspect the active project, discover
the Shapes it should use, retrieve the underlying evidence, and show you
proposed changes before applying them. Moving between harnesses does not require
rebuilding the project's context from scratch.

## See the system at work

<Columns cols={2}>
  <Card title="Turn documents into governed knowledge" icon="wand-magic-sparkles" href="/recipes/cognitive-etl-pipeline">
    Preserve the original material, extract it through a Shape, and verify the result against the source.
  </Card>

  <Card title="Build a team brain" icon="users" href="/recipes/team-brain">
    Give people and agents shared project knowledge plus decisions and lessons that persist across sessions.
  </Card>

  <Card title="Answer from stored evidence" icon="badge-check" href="/recipes/grounded-copilot">
    Gather records and source passages, then make gaps and inferences explicit before acting.
  </Card>

  <Card title="Run an expert interview" icon="comments" href="/recipes/interview-agent">
    Preserve the conversation and review the findings before they become part of the project.
  </Card>
</Columns>

<Note>
  Penumbra is in preview for design partners and developer testers. Request
  access at [shep@getpenumbra.ai](mailto:shep@getpenumbra.ai?subject=Penumbra%20access).
</Note>

## Feedback

If a workflow is missing, confusing, or wrong, email
**[shep@getpenumbra.ai](mailto:shep@getpenumbra.ai?subject=Penumbra%20docs%20feedback)**.