fru-dev3/glyph-studio
fru-dev3/glyph-studio has 37 GitHub stars and 2 forks. GitHot measured 0 in 7 days and 0 in 15 days. Last checked 2026-11-09 14:48 UTC. Last push 2026-10-31.
Glyph Studio (formerly Prevail): a private, local-first AI harness for your life. Part of the Glyph family.
What you can do
- Demo-first: launches into a pre-populated sample household (11 domains, realistic data). Explore freely, then switch to your own vault in one click.
- Starter packs: ready-made domain sets (Family · High-Income · Freelancer · Creator · Small Business · Student).
- Self-learning memory: raw intent ledger → distilled per-domain _memory.md, always reusable.
- Council & benchmarks: multi-model deliberation plus a built-in benchmark viewer.
Measured star growth
- in 24h
- Update delayed
- in 7 days
- 0
- in 15 days
- 0
- in 1 month
- Update delayed
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
README.md
OriginalGlyph Studio
Your private AI that learns you, and gets sharper every time you use it.
Formerly Prevail. Glyph Studio is a private AI harness for your life: a local-first macOS app that runs AI per life domain (wealth, health, tax, career), grounded in a markdown vault on your machine. Any model. No terminal. Nothing leaves unless you say so.
Part of the Glyph family: Glyph Studio, Glyph Dictate, Glyph Mobile, Glyph Record and Glyph Code. glyph.fru.dev/studio

Star this repo if it is useful. It helps others find it.
Install
macOS (Apple Silicon, macOS 13+)
Download the .dmg and drag Glyph Studio.app to Applications. It is signed and notarized, so there is no Gatekeeper warning.
Already running Prevail? It updates itself in place: same app, same data, now called Glyph Studio.
Windows (x64)
Download the installer and run it.
· glyph.fru.dev/studio · all releases
Why Glyph Studio
- It's yours. Your vault, chats, and the durable intent ledger stay on your machine. Local-first by default: nothing leaves until you turn on an integration.
- It learns you. Every message is captured as an intent the instant you send it (raw, never lost), then distilled into per-domain memory that's fed back into future chats. The more you use it, the sharper it gets.
- Grounded, not generic. Each life-domain answers from its own real state and history, not a blank slate every time.
- Any model, one cockpit. Installed CLIs (Claude · Codex · Antigravity · Ollama) or bring-your-own via the OpenRouter gateway: one key, 200+ models. Switch per turn; context carries across.
- Council. Fan one question to multiple models in parallel; a chair model synthesizes a single verdict.
- Private by default. Zero telemetry unless you explicitly opt in. Secrets live in the macOS Keychain.
What's new
- Agents, not just models. Validated harness runtimes (Hermes · Pi · OpenCode · OpenClaw) can now run work, not just chat. Each harness is invoked with its own real headless/agent flags (e.g. Hermes
-z --safe-mode), and every run is gated by the autonomy broker: safe (read-and-propose) by default, full agency only when you opt in.- Run with agent: on any Work-board task, hand it to a harness agent; it streams progress, then drops its result back as a comment and moves the task to Review.
- Loops on an agent: give any automation a per-loop executor so a recurring loop runs through the agent of your choice.
- Smarter runtime detection: Re-check now actually re-detects (a repaired install recovers without a restart), and the Runtimes list tells "won't run" (broken) apart from "not installed."
- Calmer sidebar: the benchmark/backup/process strips collapse into one Processes icon + modal; the Work/Editor switch goes full-width and the footer slims to Beta + a tiny theme toggle.
Key features
- Demo-first: launches into a pre-populated sample household (11 domains, realistic data). Explore freely, then switch to your own vault in one click.
- Starter packs: ready-made domain sets (Family · High-Income · Freelancer · Creator · Small Business · Student).
- Self-learning memory: raw intent ledger → distilled per-domain
_memory.md, always reusable. - Council & benchmarks: multi-model deliberation plus a built-in benchmark viewer.
- Gateway (Telegram), MCP (consume and expose), Providers, and a Remote WebUI: the same UI in a browser, allowlisted and off by default. Loopback only until you turn on "Reachable from other devices", which adds your Wi-Fi and Tailscale addresses, and an optional one-tap Cloudflare tunnel for an https address you can reach from anywhere.
- Phone, with your voice: open the WebUI on a phone and it becomes a thumb-sized client of your Mac, installable to the home screen. Hold the mic to talk instead of typing. Transcription runs on the Mac, never on a third-party service, so the Mac needs one local engine:
brew install whisper-cppplus aggml-*.binmodel in~/.prevail/models(a good default isggml-base.en.bin), orbrew install hearfor Apple's on-device speech.ffmpegconverts the phone's recording. Browsers only open the microphone on a secure origin, so voice needs the https address from "Share over the internet" (brew install cloudflared); over plain Wi-Fi everything else still works. - Quality of life: usage dashboard, in-app auto-update, start-on-boot, tray, export/import config.
Screenshots
| Domain-grounded chat | Every model, one cockpit |
|---|---|
![]() |
![]() |
Develop
npm install
npm run tauri dev # hot-reload
npm run tauri build # signed .dmg under src-tauri/target/release/bundle/dmg/
The engine sidecar (Glyph Engine, still the prevail command) is built from the sibling glyph-engine repo (formerly prevail-cli) by scripts/prepare-sidecar.sh (wired into beforeBuildCommand), so the install is fully self-contained. Stack: Tauri 2 · React 19 · Tailwind 4; the frontend talks to the Rust backend only through src/bridge.ts. See CONTRIBUTING.md.
Security & privacy
Secrets live in the Keychain; the WebUI is loopback-only + allowlisted when enabled. Telemetry is off by default: if you opt in, only an anonymous UUID and a fixed allowlist of event names are sent (never your name, paths, or vault content), and every event is mirrored to a local log you can read. See SECURITY.md.
License
GPL-3.0-only · © 2026 example.com. Free to use, study, share, and modify; redistributed forks stay open under the same license.
Explore related projects
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
300,759 starsNousResearch/hermes-agent
The agent that grows with you
262,426 starsmultica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
231,843 starsfirecrawl/firecrawl
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
200,444 stars