solstone 0.1.2

Navigate Life Intelligently

solstone

your co-brain — observers experience your day along with you, sol curates your memories, and your journal holds everything.

solstone runs in the background on your computer, experiencing your day along with you. AI agents transcribe, extract entities, detect meetings, build knowledge graphs, and surface daily insights — all without any manual input. everything stays on your machine in daily journal directories. open source, local-first, no cloud required.

Python 3.11+, Linux + macOS, AGPL-3.0-only, maintained by sol pbc.

Daily dashboard — goal, todos, upcoming events, and detected entities, all generated from observations. Facet tabs organize your life by project or context.

what you get

a system of intelligence, not just a system of record.

• automatic transcription — standalone observers take in audio continuously with speaker identification. every conversation, transcribed and searchable.
• people and projects — extracted from your conversations and remembered across time.
• knowledge graphs — relationships between entities mapped automatically. who works with whom, which projects connect to which people.
• meeting detection — meetings identified, summarized, and linked. meeting prep that surfaces what you discussed last time and personal context you'd forget.
• commitments — todos extracted from natural conversation. no manual entry.
• facet organization — group everything by project or context (work, personal, client-name) with scoped views across all apps.
• AI chat — talk to your journal. ask anything about your digital life and get answers grounded in your actual data.
• full-text search — find anything you've ever seen or heard.
• 30 AI agents — configurable workflows for activities, scheduling, research, media analysis, and more. extensible via the agent skill framework.
• local-first — all data in daily journal directories on your filesystem. configurable AI providers (Google Gemini, OpenAI, Anthropic). no cloud dependency.

Transcript viewer — dual-timeline navigation, speaker-diarized dialogue, audio playback, screen analysis. every conversation browsable by time.

People and projects — automatically extracted and remembered across your journal with mention counts and relationship data.

architecture

  +---------+       +----------------+       +---------+
  | observe | ----> |    journal     | ----> |  think  |
  | capture |       | YYYYMMDD/ dirs |       | process |
  +---------+       | media, jsonl,  |       | index   |
                    | entities       |       +----+----+
                    +-------+--------+            |
                            ^                     |
                            |  agent outputs      |
                       +----+----+                |
                       | cortex  | <--------------+
                       | agents  |
                       +---------+
                            |
  ==== callosum (event bus) | ==========================
                            |
                     +------+------+
                     |   convey    |
                     | web UI      |
                     +-------------+

• observe — receives audio and screen observations from standalone observers (solstone-linux, solstone-tmux, solstone-macos) via observer ingest. processes FLAC audio, WebM screen media, and timestamped metadata.
• think — transcribes audio (faster-whisper), analyzes screen observations, extracts entities, detects meetings, and indexes everything into SQLite. runs 30 configurable agent/generator templates from solstone/talent/.
• cortex — orchestrates agent execution. receives events, dispatches agents, writes results back to the journal.
• callosum — async message bus connecting all services. enables event-driven coordination between observe, think, cortex, and convey.
• convey — Flask-based web interface with 17 pluggable apps for navigating journal data.
• journal — journal/YYYYMMDD/ daily directories. the single source of truth — transcripts, media, entities, agent outputs, and the SQLite index all live here.

quick start

git clone https://github.com/solpbc/solstone.git
cd solstone
make install

# Configure API keys and password in journal.json
# See docs/INSTALL.md for setup instructions

# Install the CLI on PATH and start the background service (port 5015)
.venv/bin/sol setup

# Or start manually for development
sol supervisor

See docs/INSTALL.md for platform-specific dependencies, detailed configuration, and first-run guidance.

CLI

solstone is operated through the unified sol command (33 subcommands).

sol                    # Status overview and command list
sol supervisor         # Start the full stack (capture + processing + web)
sol chat               # Interactive AI chat from the terminal
sol transcribe <file>  # Transcribe an audio file
sol indexer            # Rebuild the search index

Run sol help for the full command reference.

documentation

Topic	Document
Installation and setup	docs/INSTALL.md
Journal structure and data model	talent/journal/SKILL.md
Capture pipeline	docs/OBSERVE.md
Processing and agents	docs/THINK.md
Web interface	docs/CONVEY.md
App development	docs/APPS.md
Agent runtime	docs/CORTEX.md
Message bus	docs/CALLOSUM.md
AI provider configuration	docs/PROVIDERS.md
Troubleshooting	docs/DOCTOR.md
Project direction	docs/ROADMAP.md

development

See AGENTS.md for development guidelines, coding standards, and testing instructions.

Use make dev to run the full stack against test fixtures and make ci for pre-commit checks.

contributing

See CONTRIBUTING.md for contribution terms.

license

AGPL-3.0-only. See LICENSE for details. Maintained by sol pbc.