Run Kendr locally with the desktop app, CLI, and shared API runtime.

What the local runtime already ships

Kendr in this repository is more than a hosted API client. The local runtime already supports the full research workspace loop.

Install Kendr

Kendr publishes desktop packages and separately versioned CLI ZIPs across six platform channels. A platform appears here once every canonical file for its own version has been published; platforms publish independently, so they can sit on different versions.

Surface matrix

The local runtime is shared, but each surface exposes a different amount of control.

Run Kendr from source

A normal local development session runs the FastAPI backend from source. The CLI talks to the same runtime and can be used with or without the desktop app.

cd research-service
python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install -r requirements.txt
PYTHONPATH=python uvicorn kendr_api.app:app --reload --port 8765

kendr --help

cd research-service
PYTHONPATH=python python3 -m kendr_cli.main --help

Use the desktop UI

The desktop app is the richest local surface. It exposes the shell, the research rail, settings, knowledge bases, skills, and the full run-details workspace.

• Deep research runs pause after plan generation until a user approves the plan.
• Agentic runs start immediately, but pause when a proposed tool is not read-only.
• Knowledge bases can be created from uploaded files, web links, or YouTube URLs and then attached to the composer.
• The Skills overlay shows both built-in skill health and installed external skill packs.
• Completed deep research runs can regenerate report artifacts and spawn slide or spreadsheet follow-up runs from the UI.

Use the CLI

The CLI already covers the core day-to-day workflows: connection setup, runs, approvals, KBs, skills, vector-store settings, and local model management.

kendr connection set --mode api --provider openai --credential "$OPENAI_API_KEY"
kendr models list
kendr chat ask "Summarize the architecture"

kendr research start "Compare AI coding assistants for enterprise use" \
  --depth comprehensive \
  --web \
  --news \
  --papers

kendr runs approve <run-id>
kendr runs events <run-id> --follow
kendr runs artifacts <run-id>

kendr kb create \
  --name "Quarterly sources" \
  --file ./docs/q1.pdf \
  --link https://example.com/brief \
  --algorithm hybrid \
  --wait

kendr chat ask "Use the KB to summarize the key risks" --kb <kb-id>

kendr agentic start "Inspect the docs MCP and summarize useful tools" \
  --folder ./docs \
  --link https://example.com/notes

kendr runs action-approve <run-id> <step-id>
kendr runs action-reject <run-id> <step-id> --reason "Do not modify anything"

Shared API runtime and event stream

The desktop app uses a FastAPI service that you can call directly. Route groups are organized around settings, runs, uploads, knowledge bases, and the shared event stream.

curl http://127.0.0.1:8765/api/runs \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Compare local OCR model options for desktop research workflows",
    "mode": "research",
    "composer_mode": "deep-research",
    "depth": "Standard",
    "search_backend": "Auto",
    "output_formats": ["md", "html", "pdf", "docx"]
  }'

curl http://127.0.0.1:8765/api/runs/<run-id>/approve \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{"actor":"api-user"}'

Current boundaries