← Back to .knowledge

// Blog / open source discovery

Open-source agent context layer for coding teams

For coding teams, an agent context layer should be inspectable, versionable, and honest about what the agent should not trust.

// direct answer

Short answer

An open-source agent context layer should keep routing, trust, freshness, evidence, repair work, and local tools in the repository so the team can inspect the agent's operating context alongside the code.

Evaluate whether a free, open-source repository context layer is a better foundation than private prompt memory or hosted-only context.

// the problem

Agent context becomes hidden and vendor-specific

Agent context often becomes a private mix of chat history, local scratch files, hosted memory, and one-off prompts.

That makes it hard for a team to review what the agent is relying on, especially when multiple tools touch the same repo.

For coding teams, the context layer should be inspectable, versionable, and able to mark low-trust material instead of hiding it.

// open repository layer

Keep shared agent context beside the code

.knowledge keeps the core context layer in the repository: routing, module summaries, evidence, linked documentation, items to re-check, metrics, and workflows.

The free, open-source .knowledge core runs locally and does not require a hosted service for setup, health checks, search, or the static Inspector.

Commercial Pro2Pilot tools can add team Inspector views, multi-repository dashboards, policy checks, and advanced PR impact workflows.

// concrete example

Where GitHub, .knowledge, and Inspector fit

GitHub keeps the code, issues, PRs, and review history. .knowledge keeps repository-owned context that agents can read before planning.

The local Inspector shows the free core in a static dashboard. Pro2Pilot Inspector Pro adds interactive team review for follow-up work, policies, and PR impact.

// files you can inspect

What you can inspect in the repository

Some repository-specific files appear only after setup or a health check. Run the documented setup workflow to create routing, confidence, freshness, search, metrics, and PR summary outputs.

Agent integrations INCLUDED IN THE DOWNLOAD

.knowledge/agent-integrations/

The same local context can be exposed to Codex, Claude Code, OpenCode, and command workflows.

Use it for
  • Multi-agent consistency
  • Repeatable onboarding
Do not use it for
  • Locking the team into one chat product
Local tools INCLUDED IN THE DOWNLOAD

.knowledge/tools/

Import, release, metrics, search, graph, and inspector commands are inspectable code.

Use it for
  • Auditing how reports are generated
  • Running checks in local or CI workflows
Do not use it for
  • Treating generated output as permanent truth
CI templates INCLUDED IN THE DOWNLOAD

.knowledge/github-action-templates/

The free core can be copied into repository automation without requiring a hosted management service.

Use it for
  • PR health checks
  • Release evidence
Do not use it for
  • Assuming CI replaces human review
Static Inspector INCLUDED IN THE DOWNLOAD

.knowledge/inspector/

A local read-only dashboard makes trust, graph, and repair state visible.

Use it for
  • Visual sanity checks
  • Team discussion around stale modules
Do not use it for
  • Editing code from the dashboard
  • Bypassing source-of-truth rules
Apache-2.0 license proof INCLUDED IN THE DOWNLOAD

.knowledge/LICENSE

The free core license is inspectable in the public archive together with NOTICE.

Apache-2.0 core: see LICENSE and NOTICE.

Use it for
  • License review
  • Open-core due diligence
Do not use it for
  • Assuming paid Inspector Pro terms
PR summary output CREATED AFTER A HEALTH CHECK

.knowledge/maintenance/pr_summary.md

The health-check workflow can generate reviewer-facing context using the included free tools.

Use it for
  • Review handoff
  • Open-core automation proof
Do not use it for
  • Replacing reviewer judgment

// commands to try

Commands and expected checks

node .knowledge/tools/flow.js release --no-color
what it does
The free core refreshes routing, confidence, metrics, linked documentation, search, and Inspector outputs.
where to look
.knowledge/maintenance/quality_report.json
node .knowledge/tools/serve-inspector.js
what it does
The local static Inspector can be viewed from the generated repository files.
where to look
.knowledge/inspector/index.html
node .knowledge/tools/generate-pr-summary.js
what it does
A PR-facing summary of trust, health, and repair state is generated.
where to look
.knowledge/maintenance/pr_summary.md
Repo tree files and checks

What is included in the free core

01 agent-integrations/ -> Codex, Claude Code, OpenCode
02 docs/cookbook/ -> operational recipes
03 github-action-templates/ -> CI workflows
04 tools/ -> scan, import, release, metrics
05 inspector/ -> local read-only dashboard
06 Quick-Start.md and README.md -> first-read setup docs

// practical reference

Free .knowledge core vs Inspector Pro

The boundary should be explicit so the open source layer remains useful by itself.
Free .knowledge coreInspector Pro
.knowledge routing, trust, freshness, evidence, and local tools.Team dashboards, policy checks, and advanced review workflows.
Local read-only Inspector.Interactive Inspector Pro with follow-up boards and PR impact views.
GitHub Action templates and local command workflows.Commercial support, team operations, and paid build delivery.

// quick FAQ

FAQ

Is the free core useful without Pro2Pilot Inspector Pro?

Yes. The free core contains repo-local routing, trust, freshness, tools, integrations, metrics, and a local read-only Inspector.

Why keep agent context in GitHub?

Because coding teams already review code, tests, docs, and automation there. Keeping agent context in the repo makes it inspectable and versionable.

What works without Pro2Pilot Inspector Pro?

The free core still provides local routing, trust and freshness files, tools, agent integrations, GitHub Action templates, metrics, search, PR summaries, and the local read-only Inspector.

// next step

Use this page when evaluating open agent infrastructure

Start with the GitHub repository and the local .knowledge layer. Add Pro2Pilot Inspector when the team needs visual review and coordination on top of the free core.