Yaver
Supports integration with AMP as one of the AI agents that can be used for autonomous development tasks within the Yaver ecosystem.
Supports Android device testing and deployment through the Yaver mobile app, enabling hot reload and real-device testing for Android applications.
Supports Apple ecosystem integration including iOS development, App Store deployment, and native iOS app testing through the Yaver mobile app.
Enables deployment to Apple's App Store as part of the automated shipping process, with one-tap deployment capabilities for iOS applications.
Supports deployment to Cloudflare platforms as one of the deployment targets that can be automatically detected and used for shipping applications.
Enables deployment to Cloudflare Workers as part of the automated shipping process for serverless applications.
Enables delivery of daily development summaries and notifications through Discord as part of the morning summary feature.
Provides containerization capabilities for exporting and running promoted backends on user's own cloud infrastructure using Docker.
Supports Expo framework hot reload over P2P connections for React Native development within the Yaver ecosystem.
Supports Firebase as an escape hatch/alternative backend system that can be used instead of Yaver's native backend solution.
Supports Flutter framework development with hot reload capabilities and Feedback SDK integration for Flutter applications.
Enables deployment to Fly.io as one of the deployment targets that can be automatically detected and used for shipping applications.
Provides git integration as part of the 473 MCP tools available for version control and development workflow management.
Integrates with GitHub for version control, repository management, and potentially GitHub-based deployment workflows.
Supports GitHub Actions integration as part of the CI/CD tooling available through the MCP server's 473 tools.
Integrates with GitLab for version control and repository management within the development workflow.
Enables deployment to Google Play Store as part of the automated shipping process, with one-tap deployment capabilities for Android applications.
Provides Kubernetes integration as part of the 473 MCP tools available for container orchestration and deployment management.
Supports Next.js framework development with hot reload capabilities over P2P connections within the Yaver ecosystem.
Integrates with Ollama AI agent for autonomous development tasks and code generation within the Yaver workflow.
Integrates with OpenAI's Codex AI agent for autonomous development tasks, code generation, and bug fixing within the Yaver workflow.
Enables delivery of daily development summaries and notifications through Slack as part of the morning summary feature.
Provides native SQLite-backed data persistence for local phone-project sandboxing with schema, auth personas, and CRUD operations.
Supports Stripe integration for payment processing as part of automated feature implementation tasks like 'add Stripe' to applications.
Supports Supabase as an escape hatch/alternative backend system that can be used instead of Yaver's native backend, with deployment capabilities.
Enables delivery of daily development summaries and notifications through Telegram as part of the morning summary feature.
Supports Turso as an escape hatch/alternative database system that can be used instead of Yaver's native backend solution.
Enables deployment to Vercel as one of the deployment targets that can be automatically detected and used for shipping applications.
Supports Vite framework development with hot reload capabilities over P2P connections within the Yaver ecosystem.
What Yaver is
AI writes the code in seconds. The loop around it — build, install, reproduce, describe what's wrong, get back to the agent — still takes hours. Yaver closes that loop.
The yaver agent runs on hardware you already own: a Mac, a Linux box, a WSL machine, a Pi, or a VPS. Your coding agent works there, against your real repo. Every other surface — phone, watch, TV, car, AR/VR, browser — is a remote control and a preview target for that one machine.
It runs on the AI subscription you already pay for — no token markup, and your code never leaves your machine.
iOS and Android are the deepest path today. Watch, TV, car, and AR/VR surfaces live in this repo and share the same core.
Related MCP server: slm-mesh
Quick start
npm install -g yaver-cli
yaver auth
yaver serveOn a headless box (Pi, VPS, SSH-only), yaver auth --headless prints a short code and a URL you can open from any browser.
npm is the only supported install path, on macOS (Apple Silicon + Intel), Linux (x64 + arm64), and Windows via WSL2. It downloads a signed, notarized agent binary for your platform.
Then grab the app and pair it with that machine:
Open Yaver, pick a project from your dev box, preview it on your phone, shake to vibe-code — fix a bug, ship a small feature, or tweak a style — and a fresh bundle lands in seconds. One screen, real device, no extra hardware.
Install or use it from your coding agent
Install the CLI directly, or register Yaver as an MCP server so Claude Code, Codex, or opencode can drive your machine from chat. MCP does not need a global install first — npx pulls the server on first run.
# direct CLI
npm install -g yaver-cli
yaver auth
# or as MCP
# Claude Code
claude mcp add --scope user yaver -- npx -y yaver-cli yaver-mcp
# Codex
codex mcp add yaver -- npx -y yaver-cli yaver-mcp
# opencode
npx -y -p yaver-cli yaver mcp setup opencode
# then, in the agent chat:
call yaver_lazy_setupAlready installed globally? yaver mcp setup claude-code (or codex / opencode) writes the same entry, and yaver auth auto-registers every installed runner on first sign-in. Yaver is published to the official MCP registry as io.github.yaver-io/yaver. Codex Desktop can also load the repo-local plugin in plugins/yaver.
Full tool list and HTTP/remote setup: MCP guide.
How it works
Start
yaver serveon your own machine.Pair a surface — the mobile app, the web dashboard, or another Yaver client.
Send a task to your coding agent from whichever surface is nearest.
Watch terminal, build, and reload progress stream back live.
Push the fix to a real device, or deploy from your own machine when it's ready.
The CLI, agent, relay, and backend are all self-hostable. Client apps currently reach you through a thin hosted coordination plane for identity and device discovery; full client self-host is on the way.
For remote access, Yaver Relay is the default path. The free shared relay is for light personal use and has fair limits; the relay implementation is open source if you want to run your own.
What works today
Drive Claude Code, Codex, OpenCode, Aider, Goose, or another terminal agent from the Yaver agent.
Push React Native / Expo bundles to a paired phone through the native Hermes path.
Capture dev-build feedback with screenshots, logs, and replay context.
Stream task, build, and reload progress to mobile or the web dashboard.
Keep peer discovery, relay, and vault flows local-first.
Build against SDKs and examples for React Native, Flutter, web, Unity, Go, Python, and JS/TS.
What it costs
A solo developer can start with the open-source stack at $0.
Component | Runs on | Cost |
Yaver CLI + agent | Your dev machine | $0 |
Yaver surface apps | iOS / Android / watch / TV / car / AR/VR | $0 |
Web dashboard | Browser | $0 |
Backend on your own machine | Your Mac / Linux / WSL / VPS | $0 + your hardware |
Yaver shared relay | Yaver-hosted, fair-use limited | $0 |
AI models (Ollama) | Your GPU or CPU | $0 |
The open-source stack includes the mobile app, CLI, agent, web dashboard, SDKs, and relay implementation. Yaver's shared relay is available with fair limits for getting started. Your coding agent brings its own login or subscription — Yaver never resells tokens.
V1 is focused on your own devices and self-hosted machines. Managed paid products and machine-sharing surfaces are not part of the launch surface.
Repository map
Path | Purpose |
| Go agent, CLI surfaces, local API, relay/P2P/runtime integrations |
| React Native mobile app and native preview container |
| Apple Watch, Wear OS, and Apple TV client surfaces |
| Next.js marketing site and dashboard |
| Hosted identity, session, and device-discovery metadata |
| QUIC relay service |
| Public SDKs and feedback clients |
| Small fixture apps used to test SDK and push flows |
| Source notes for the landing/demo clips |
| Architecture notes, setup guides, audits, handoffs, and planning material |
Deploying Yaver
Use exactly one local entrypoint:
./deploy/deploy.sh <target> [options]Targets are all, backend, cloudflare, ios, android, npm, and mcp
with aliases listed by ./deploy/deploy.sh --help. The entrypoint delegates to
the maintained vault-aware scripts and yaver deploy commands, but gives
humans, agents, and MCP one path so deploys do not drift.
Deploys are owner-only. The script refuses group/other-writable repo or script paths before touching Convex, Cloudflare, App Store Connect, Play Console, npm, or MCP registry credentials.
This repo is the monorepo
Yaver is one monorepo — this one. Agent, CLI, mobile, watch, TV, car, AR/VR, web, relay, backend, and SDKs all live here and ship together. Splitting them would only buy version skew between surfaces that have to agree.
Everything else in the yaver-io org is a
validation / use-case app — something whose only job is to exercise Yaver
from the outside. Those are separate repos precisely because they must be
clonable, buildable, and breakable on their own, exactly as a user's project
is. If they lived in here they'd inherit this repo's tooling and stop being an
honest test.
The rule: product code goes in this repo; anything that tests the product from outside gets its own repo.
Validation apps
The apps that prove Yaver works live in their own repos, not in this one. They are local-only todo apps — no backend, no accounts, no network — and they are deliberately boring, because they are the control.
The same todo app is built five ways. Yaver reaches each one differently, so when the loop feels different across stacks, it is the transport that differs and not the app:
Repo | Stack | How Yaver reaches it |
Expo / React Native | Hermes — the agent compiles an HBC bundle and the container swaps it in place | |
Native Android (Kotlin) | native-webrtc — runs on a build host, H.264 streamed to the phone, taps sent back | |
Native iOS (SwiftUI) | native-webrtc — same, macOS build host only | |
Flutter / Dart | native-webrtc — Dart has no Hermes equivalent | |
Next.js | dev server — HMR through Yaver's relay path |
Hermes is React-Native-only: native and Flutter apps compile to real binaries and can never be loaded into the Yaver container. That is why three of the five exist — they are the only honest way to exercise the streaming path.
They are separate repos so they can be cloned, built, and broken without touching this one. Each README states what works and what doesn't per stack, including where a feedback SDK does not exist yet.
Documentation
Docs index · Setup · Contributing · Runtime architecture · Protocol · Feedback SDK · Security · License
If an AI coding agent is setting Yaver up for you, point it at the canonical machine guide first:
curl -s https://yaver.io/llms.txtMarkdown in this repo is context, not source of truth. If a doc and the code disagree, trust the code and fix the doc in the same change.
Development
# Web dashboard / landing
cd web && npm install && npm run dev
# Go agent tests
cd desktop/agent && go test ./...Run the narrower package tests for the area you change — the repo spans Go, Node, React Native, Swift, Kotlin, Flutter, Unity, and embedded C.
License
The repo uses a split license: the core is FSL-1.1, which auto-converts to Apache-2.0 after two years, and the client SDKs are Apache-2.0 so you can embed them in closed-source apps. See docs/planning/LICENSING.md.
If your legal team needs the core under different terms, a commercial license is available — email kivanc.cakmak@simkab.com.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceProduction-grade MCP server that gives AI agents safe access to your local dev environment: filesystem, databases, processes, and OpenAPI specs.15483MIT
- AlicenseNot gradedqualityCmaintenanceEnables peer-to-peer communication, discovery, shared state, and file coordination between AI coding agents across machines and sessions.5718Elastic 2.0
- AlicenseAqualityBmaintenanceA minimal, secure MCP server for AI-assisted mobile development, enabling build, install, interact, and inspect Android/iOS apps.33907Apache 2.0
- AlicenseAqualityBmaintenanceOne MCP that turns Claude Code into your whole dev stack by swallowing other MCP servers, delegating to Codex & Gemini on your CLI subscriptions, remembering projects in a searchable knowledge graph, and carrying setup across sessions — secret-free by design.233MIT
Related MCP Connectors
The team layer for AI coding agents: shared contracts, collision alerts, E2EE sessions.
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yaver-io/yaver.io'
If you have feedback or need assistance with the MCP directory API, please join our Discord server