Deepr

Persistent domain experts built from bounded, auditable research.

Deepr turns research into durable beliefs, gaps, contradictions, confidence, citations, provenance, and outcomes. It prefers owned local models, then proven subscription quota, with no automatic fallback to a paid API.

Demo CLI session only (fictional expert and spend). Not a live account or real research content. Regenerated with python scripts/render_cli_demo_screenshot.py.

Demo web UI only (fictional operator data). Regenerated with python scripts/render_web_demo_screenshot.py.

Capacity

Class	Current posture
Local Ollama	Preferred for expert setup, maintenance, evaluation, and consultation after endpoint ownership is proven.
Prepaid plan quota	Runs only when authentication, tool confinement, remaining quota, and disabled paid overage are proven. Claude Code is the current executable adapter.
Metered API	No automatic fallback. Production dispatch is currently blocked pending a provider-authenticated account-control adapter.

A budget is a hard ceiling, not permission to spend. Metered work requires a durable reservation, a final pre-dispatch check, append-only settlement, and a live provider control bound to the exact account, credential, client, and request. Unknown state blocks. Paid dispatch is currently frozen.

deepr budget set 5
deepr costs show
deepr costs doctor

See Capacity and Cost for billing reconciliation and the complete no-surprise-spend contract.

Install

Windows PowerShell:

powershell -ExecutionPolicy ByPass -c "irm https://raw.githubusercontent.com/blisspixel/deepr/main/scripts/install.ps1 | iex"

Linux and macOS:

curl -fsSL https://raw.githubusercontent.com/blisspixel/deepr/main/scripts/install.sh | bash

Installers use the latest verified GitHub Release wheel in an isolated pipx environment. PyPI publication is not enabled.

Quick start

deepr init
deepr doctor --skip-connectivity
deepr capacity
deepr expert make "My Domain Expert" --local -d "The decisions this expert supports"
deepr expert consult "What should we decide next?" --expert "My Domain Expert" --local

See Quick Start, Supported Surface, and the MCP Agent Guide for workflows across the current 36 MCP tools. The MCP server implements the final 2026-07-28 protocol revision (stateless per-request negotiation, server/discover, subscriptions/listen, Streamable HTTP header and Origin validation) while still serving legacy initialize-era clients on both transports. Operators can prove the offline host-interop posture with deepr mcp conformance ($0, no network, no model).

Documentation

• Approach contract - what the method claims, refuses, and leaves experimental
• Supported Surface - what currently runs
• Experts
• Architecture
• Models
• Threat Model
• Roadmap
• Changelog
• Contributing

Development

uv pip install -e ".[dev,full]"
pytest tests/unit/ --ignore=tests/data -q
ruff check src/deepr/
ruff format --check src/deepr/
python scripts/check_file_sizes.py
python scripts/check_ratchets.py
python scripts/check_paid_api_boundaries.py

Do not run bare pytest: integration tests can contact real providers. The blocking unit suite requires at least 80 percent branch coverage.

License

Apache 2.0