Open Source · Local First · v0.1 Experimental

What does your SOP actually say, and where did that come from?

Knowledge Layer for Agents is a local, open-source pipeline for knowledge engineers turning SOPs, policies, and procedures into open, source-traced knowledge bundles, reviewable by domain experts, readable directly by agents.

Run the quickstartBrowse the source

Apache-2.0 · No database · No API key required to try it

cd tools/sopkb
pip install -e .

sopkb init demo-bundle
sopkb scan sources \
  --bundle demo-bundle
sopkb mine demo-bundle
sopkb serve .

Why This Exists

Enterprises run on SOPs. Agents still have to interpret them.

Procedures written for people remain buried in Word files, PDFs, and wikis. Retrieval can find a relevant document, but it does not by itself show which instruction the agent received, where it came from, or whether a domain expert agreed with it.

Knowledge Layer for Agents makes that knowledge explicit: extracted claims, retained source evidence, recorded review decisions, and agent-readable output in one portable bundle.

How It Works

  1. 01

    Ingest

    SOPs and policies

  2. 02

    Extract

    Claims, rules, concepts

  3. 03

    Ground

    Retained source evidence

  4. 04

    Review

    Domain-expert decisions

  5. 05

    Connect

    Web UI for people. MCP for agents.

One Bundle · Two Interfaces

Domain experts review it. Agents retrieve from it.

Both interfaces operate over the same files. There is no separate hosted knowledge service to keep synchronized and no opaque copy of the SOP hidden behind an API.

Domain Expert

Review in the browser

sopkb serve .

Inspect claims and evidence, then approve, reject, defer, edit, or comment.

Shared Local ArtifactSOP Knowledge BundleMarkdown · YAML · review history
Agent

Retrieve through MCP

sopkb mcp serve <bundle_dir>

Search knowledge, retrieve evidence, resolve citations, and request task-scoped context.

Local by default: the MCP preview uses JSON-RPC over stdio, is read-only by default, and reads the bundle from your filesystem. Your MCP client and model configuration determine where retrieved excerpts are sent. Read the MCP preview documentation →

Human Review

Review the knowledge itself, not only the agent's answer.

The knowledge module itself is reviewable. A domain expert can inspect each proposed claim beside its source evidence, then approve, reject, defer, edit, or comment on it. This is knowledge review, not an audit of agent behavior.

You review the knowledge once, so you don't have to review every answer forever.

For knowledge engineers
Ingest a document set, inspect what got extracted and why, and hand off a clean bundle.
For domain experts
Review what was extracted without reading application code.
For agent developers
Expose the same inspectable artifact through the local MCP server.
Knowledge Layer for Agents review screen showing an extracted claim, its source evidence, and review actions
Claims, evidence, and review actions in one view.

The Output

A static SOP Knowledge Bundle.

The output is a static collection of plain Markdown and YAML based on the Open Knowledge Format. People can open it with a text editor and diff it with Git. The Web UI provides the review interface; the local MCP server lets agents retrieve from the bundle. Graph JSON and RDF exports are also available.

sop-knowledge-bundle/
├── sources/       # document context
├── knowledge/     # structured claims
├── evidence/      # supporting spans
├── rules/         # decision logic
└── log.md         # review history

The Release Premise

A simple change can make the agent work better.

Give the same agent reviewed, structured SOP knowledge instead of asking it to interpret documents at runtime, then measure the difference. This is the release hypothesis, not a blanket performance claim.

Build With Us

Start with one SOP.

Version 0.1 is experimental. Try one procedure, inspect the resulting bundle, and tell us where the format or workflow falls short.

Project boundary

This project owns creating and exporting knowledge bundles. It does not own operationalizing them at enterprise scale. Runtime enforcement, auditing agent behavior, governed multi-tenant operation, and production monitoring are separate concerns. Read the open-core boundary →

Knowledge Layer for Agents · Fortnightly

Follow what we learn.

Build notes, worked SOP examples, releases, and lessons from practitioner testing.

Subscribe for updates

Knowledge Layer for Agents implements the Open Knowledge Format. It is not affiliated with or endorsed by the OKF project.