ConductLoop

Your notes, searchable and askable, on your own computer. Free and open source (MIT).

ConductLoop reads your notes (an Obsidian vault or any folder of Markdown) and lets you search them and ask questions about them. Answers come from your notes, with their sources. Everything stays on your computer: the index is a local SQLite file, and the AI is the model you choose, with your own key (Anthropic, OpenAI, MiniMax, any OpenAI-compatible server, or a local Ollama). Without a key it still searches, and answers with the lines of your notes that match.

It never writes into your notes folder: its own notes (daily briefing, agent notes) go to a folder of their own.

Download

System	Download	Notes
macOS 13 or later, Apple Silicon	ConductLoop.dmg	Signed and notarized. Updates itself (ConductLoop → Check for Updates…). The in-app browser needs macOS 14 or later.
Linux x86_64 · beta	AppImage · .deb	Tested on Ubuntu 22.04 and 24.04. No in-app browser; no automatic updates yet.
Windows 10/11 x64 · beta	setup.exe	Not code-signed, so SmartScreen says "Windows protected your PC": click More info, then Run anyway. No in-app browser; no automatic updates yet.

All releases, with checksums: conductloop-releases.

The first minute

1. Open it. The welcome page asks for the folder with your notes ("Choose…") and indexes it.
2. Ask or search from the home page. Each result opens the note.
3. Optional: paste an AI key in Credentials for written answers. It is stored in the system keychain (the Keychain on a Mac) or in an encrypted file, and never shown again.

Ask your notes	Search them

And beyond your notes

• A team of AI agents. Ask the CEO agent and it splits the work across a CTO, Head of Product, CMO and CFO, and writes one answer. Or create your own agents with tools and a schedule.
• Connectors for GitHub, Slack, Gmail and more, read-only unless you allow writes; every write waits for your confirmation. They keep their tokens in the system keychain only, so they need macOS or Linux with a keyring.
• MCP both ways. Plug MCP servers in as tools for your agents (read-only by default; anything that writes waits for you). From a source install, ops mcp lets Claude or another agent search and ask your notes.
• Backups of the local database, daily and before every upgrade, restorable from Setup.
• It learns from your 👍/👎: proposed rules that you approve, all stored on your computer.

Ask the team	The CEO's answer

The screenshots use a fictional vault; the team ones ran on a real model (MiniMax-M3). Dark theme: ◐ in the corner.

---

For developers

The Python package is still named ops_dashboard for backwards compatibility. The product name is ConductLoop.

Principles

Local-first

• The server is a stdlib http.server that binds to 127.0.0.1:7777 by default.
• All indexed content, memory, tasks and settings live in a local SQLite file (ops.db). Location, in order of precedence:
  1. $OPS_DATA_DIR/ops.db
  2. <repo>/data/ops.db (dev checkout, if data/ exists)
  3. macOS ~/Library/Application Support/com.conductloop.desktop/data/ops.db · Linux ~/.local/share/conductloop/ops.db · Windows %LOCALAPPDATA%\ConductLoop\data\ops.db
• At-rest secrets (DB encryption key, connector credentials) go to the macOS Keychain, or to 0600 files in the data dir elsewhere (ops_dashboard/secrets_store.py). Connector credentials are Fernet-encrypted in the DB.
• Network calls only happen for features you turn on: your model provider, connectors you configure (GitHub, Slack, Telegram, Discord, Google Search Console/Analytics, Sentry, …), URL health checks, webhooks, and the Tauri auto-updater in the desktop app.
• Error reporting to Sentry is opt-in (only if you set SENTRY_DSN).
• If you install sentence-transformers, the embedding model (all-MiniLM-L6-v2) is downloaded once from Hugging Face and then runs locally.

BYOK (bring your own key)

The Brain talks directly to the provider you configure; nothing is proxied through ConductLoop servers.

Provider (BRAIN_PROVIDER)	Needs
anthropic	ANTHROPIC_API_KEY
openai	OPENAI_API_KEY
minimax	MINIMAX_API_KEY (OpenAI-compatible; MINIMAX_BASE_URL optional)
gateway	GATEWAY_API_KEY for an OpenAI-compatible gateway (GATEWAY_BASE_URL, default Vercel AI Gateway)
ollama	a local Ollama on localhost:11434 (OLLAMA_MODEL, OLLAMA_BASE_URL optional)
mock	nothing — offline/testing

BRAIN_PROVIDER=auto (default) picks the first available provider; BRAIN_MODEL overrides the model. Keys can also be set from the UI (/credentials), which stores them in the macOS keychain or, where there is none, in an encrypted file protected by a passphrase — never in plain text. Other settings live in your local config.json ($OPS_CONFIG_PATH, or in the data directory); it is gitignored — never commit it.

---

Install

From source (macOS / Linux)

Requires Python 3.13+ (CI runs 3.14).

git clone https://github.com/EVMCOD/conductloop.git
cd conductloop
python3 -m venv .venv && .venv/bin/pip install -r requirements.txt
make serve            # → http://127.0.0.1:7777

Then, optionally, point it at your content and index it:

cp .env.example .env  # the make targets load .env automatically
make index            # index all configured sources

Dependency sets:

• requirements-core.txt — lean runtime (server, CLI, auth, search). No ML.
• requirements.txt — core + Anthropic/OpenAI SDKs + local semantic search: fastembed (ONNX, no PyTorch; what the app uses) and sentence-transformers (pulls PyTorch, ~2 GB).
• requirements-optional.txt — Whisper voice notes, Google Analytics, PyJWT, Sentry, MCP server.
• requirements-dev.txt — core + pytest, ruff, mypy, pip-audit, pre-commit.

pip install -e . also installs the ops CLI entry point.

Configuration

A fresh install is empty: no projects, teams or URLs. Point it at your content with environment variables (see .env.example), e.g. OPS_VAULT_ROOT, OPS_WORKSPACE, OPS_SKILLS_DIR, OPS_REPOS, OPS_PROJECTS_FILE, OPS_LIVE_URLS_FILE. Set CONDUCTLOOP_DEMO=1 (with a throwaway CONDUCTLOOP_DB_PATH and OPS_DATA_DIR) to load fictional demo data instead; see docs/FIRST-5-MINUTES.md.

Optional notification webhooks (Slack / Discord / Telegram) are described in config.example.json. Remote access from a phone is documented in docs/REMOTE.md (Tailscale; nothing is exposed publicly by default).

---

Usage

make help        # list targets
make index       # reindex everything
make serve       # start the web UI on :7777
make brain       # ask the Brain from the terminal
make briefing    # morning briefing
make snapshot    # take a daily snapshot
make diff        # diff today vs yesterday

Selected ops / python -m ops_dashboard commands: index, find, brain, briefing, capture, todos, projects, playbook, snapshot, backup, export / import, sync-export / sync-import (passphrase-encrypted bundle), obsidian-sync, calendar-import, mcp (expose the Brain over MCP), setup (readiness checklist). Run ops --help for the full list.

---

Development

python3 -m venv .venv && . .venv/bin/activate
pip install -r requirements-dev.txt
pre-commit install                  # optional: ruff + basic hygiene hooks

ruff check ops_dashboard tests      # lint (blocking in CI)
mypy ops_dashboard                  # type check (advisory in CI; a strict subset is blocking)
pytest -m "not live"                # hermetic test suite (what CI runs)

Tests marked live need the network or real credentials; they never run by default or in CI.

Layout

ops_dashboard/          Python package: server.py (HTTP API + UI), cli.py (typer CLI),
                        db*.py (SQLite schema/queries), brain.py (RAG + providers),
                        indexers/ (vault, memory, repos, skills, urls, …), web/ (vanilla HTML/JS UI)
desktop/                Tauri v2 macOS app (Rust shell + PyInstaller sidecar build)
desktop-demo/           Tauri demo build
scripts/, bin/          launchd jobs, release and maintenance scripts
tests/                  pytest suite

Desktop app

See desktop/README.md and desktop/docs/DISTRIBUTION.md. Building and signing a release needs your own Apple Developer ID and your own Tauri updater key; neither is in this repository.

Linux (experimental) and Windows are not shipped. docs/PORTABILITY.md is the audit of everything that is macOS-only today, with the plan to port it.

---

Contributing & security

• CONTRIBUTING.md
• SECURITY.md — please report vulnerabilities privately, not in public issues.

License

MIT. The ConductLoop name and logo are not covered by the license.