vibedonate
Serves on-device inference requests using Ollama models, respecting user consent, peer allowlists, and daily token caps.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@vibedonatecan you handle a 500-token request from alice?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
vibedonate
Package · Setup · Runtime surfaces · Compare
vibedonate is an open-source, self-hosted compute-sharing experiment for developers who use coding agents. Your hardware, opt-in, metered. It provides peer transport, donation controls, and local ledgers in the Vibe Suite. The current CLI mesh runs an echo stub; its separate Ollama runner is not connected to mesh jobs.
Install
npm install -g vibedonateRequires Node.js 18 or later. Includes TypeScript declarations and three direct runtime dependencies.
Related MCP server: myai-mcp
Run your first local check
vibedonate statusOn a fresh installation, the output reports that the node is not armed.
No credentials or environment variables are required. No sharing starts from this command.
The CLI reads exported environment variables; it does not load .env files.
For an opt-in transport demo, run this donor in one terminal:
vibedonate share --compute --idle 00:00-23:59 --cap 2M --pool allowlist:consumer --handle donorRun the consumer in another terminal:
vibedonate request "hello" --pool allowlist:consumer --handle consumerWith reachable peers inside the UTC window, the consumer prints olleh. This is the echo stub, not AI inference.
Stop the donor with Ctrl+C, then run vibedonate stop to revoke persisted consent.
How it works
share -> saved config + consent -> Hyperswarm pool discovery
|
consumer prompt -> donor checks -> echo stub -> result + metering receipt
status / MCP preflight -> separate Ollama availability check
payment flags -> stub wallet + local payment ledgerAnnouncements contain handle, pool, compute tier, and optional payment terms. Prompts and results cross connected peer links.
Raw usage totals are not announced. Local files default to ~/.vibedonate.
Why it exists
vibedonate explores opt-in donation controls around spare local compute. Petals distributes model execution; Ray Serve provides model-serving infrastructure. This package focuses on consent, schedules, recipient pools, and metering, with experimental peer transport.
Compare
Checked 2026-10-14 against the Petals research paper and Ray Serve documentation.
Property | vibedonate | Petals | Ray Serve |
Scope | Donation controls and echo mesh demo | Collaborative model inference and fine-tuning | Distributed model serving |
Execution | Default mesh uses echo stub | Distributed model blocks | Deployed model-serving applications |
Interface | Node.js library, CLI, agent preflight | Model inference interface | Python deployment and inference APIs |
Coverage
Integration or tier | Status | Source behavior |
Hyperswarm | Implemented | Same-pool peer discovery and request/result transport |
Ollama | Separate runner | Detects executable; invokes |
Echo mesh model | Stub | Reverses prompts; records 100 tokens per default job |
USDC / x402-style payments | Stub | Deterministic wallet proofs and local ledger; no settlement |
Base | Scaffold | Accepted payment chain label |
Ethereum | Scaffold | Accepted payment chain label |
Polygon | Scaffold | Accepted payment chain label |
Subscription sharing | — | No shipped tier |
API-credit routing | — | No shipped tier |
There is one default chat runner, one default echo mesh model, and two MCP tools. Source inspection and local tests support these distinctions. No credentials, on-chain transactions, or public-network service guarantees were verified.
Common use cases
Node.js developers: test consent and capacity decisions through the exported library.
Hyperswarm experimenters: exchange echo jobs between same-pool peers.
Ollama users: inspect local chat-runner availability before building a custom integration.
Agent builders: call MCP
request_capacityto check a proposed donation without executing a job.Vibe Suite users: inspect hash-chained usage and payment records on their own machine.
Features
Consent:
sharegrantsdonate:compute;stoprevokes it in persisted storage.Schedules: UTC idle windows and configurable daily token caps.
Recipient pools:
open,org:<id>,<member>, andallowlist:<peers>.Metering: local hash-chained receipts with a chain verification method.
Payments: optional price metadata and stub payment records; free jobs by default.
Suite hooks: exported donation lifecycle hooks use vibe-core events and notifications.
Runtime surfaces
The Node.js package exports configuration parsers, consent helpers, capacity evaluation, metering, payment stubs, and compute resolution.
vibedonate share --compute --idle HH:MM-HH:MM --cap 2M --pool open
[--handle name] [--price 0.001] [--chain base|ethereum|polygon]
vibedonate request "prompt" --pool open
[--handle name] [--timeout milliseconds] [--pay 0.001]
vibedonate status
vibedonate stop
vibedonate wallet
vibedonate mcp
vibedonate --help / -h
vibedonate --version / -vvibedonate mcp starts a stdio Model Context Protocol (MCP) server with exactly two tools:
Tool | Behavior |
| Config, consent, compute availability, schedule state, and totals |
| Preflight |
Delivery and behavior limits
The CLI donor defaults to createEchoModel(). Installing Ollama does not replace it with model inference.
The separate local runtime records capacity receipts; it does not execute a prompt.
The CLI uses stubWallet(). Payment success means a synthetic proof passed, not that USDC moved on Base, Ethereum, or Polygon.
Peer authorization compares announced handles. It does not authenticate organization membership or bind handles to trusted identities.
CLI activity checks default to “not busy”; no automatic machine-idle detector is wired into the donor.
The running donor holds its initial config and consent objects. Use Ctrl+C to stop it; a separate stop process does not close it.
The mesh checks whether today's total is below the cap before a job; a job can exceed the remaining allowance.
The capacity preflight has a stricter request-fits check. Do not assume both paths enforce identical bounds.
Discovery defaults to 15 seconds; each attempted donor gets up to six seconds. Total elapsed time can exceed the discovery timeout.
Hash chains detect inconsistent record content; they do not prevent someone from rewriting the whole local ledger.
Integration guides
Ollama runner: install Ollama and pull
qwen2.5:7b; setVIBEDONATE_OLLAMA_MODELto choose another installed model.Separate state: export
VIBEDONATE_DIRto override~/.vibedonate.Demo pool (not access control): use the same
allowlist:consumerstring on both peers and--handle consumerfor requests. Any peer that announces a matching handle passes the check.Organization pool: include explicit members, such as
org:team,alice;org:teamalone authorizes no members.Agent setup: configure your MCP host to launch
vibedonate mcpover stdio.
Status
Version 0.4.3 is experimental and pre-1.0. Public case studies are not yet published.
No public documentation site is configured; the operational guidance is self-contained here.
Use GitHub issues for support; repository access may be required.
For contributions, run npm ci, npm run typecheck, npm run build, and npm test.
FAQ
Which integrations are verified?
vibedonate has source-backed peer transport and a separate Ollama runner. Local tests do not certify public peers or blockchain settlement.
Does vibedonate provide a managed inference service?
vibedonate runs on your hardware. It provides no managed inference pool, availability guarantee, or hosted account service.
Does the CLI run Ollama for donated jobs?
vibedonate uses an echo stub for default CLI mesh jobs. The Ollama chat runner exists as a separate library path.
How is vibedonate different from Petals?
vibedonate experiments with donation controls and a request/result mesh. Petals distributes model execution across participants.
How is vibedonate different from Ray Serve?
vibedonate supplies local donation controls and a CLI experiment. Ray Serve supplies infrastructure for deployed model-serving applications.
Can I earn real USDC with vibedonate?
vibedonate ships a stub wallet and local payment records. The CLI does not submit or verify real blockchain payments.
Does stop terminate an active donor?
vibedonate stop changes persisted config and consent. Stop the active donor process with Ctrl+C to leave the mesh.
Does vibedonate share subscription quotas or API credits?
vibedonate ships only the compute tier. Subscription and API-credit routing are not implemented.
License
MIT.
This server cannot be deployed
Maintenance
Related MCP Connectors
HiveCompute MCP Server — decentralized inference router for AI agents
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Create, browse, remix, collaborate on, and run durable AI workflow nodes from MCP hosts.
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
Related MCP Servers
AlicenseAqualityCmaintenanceUnified MCP server for managing local model runtimes (Ollama, LM Studio, etc.), enabling provider-agnostic discovery, lifecycle management, hardware-fit checks, and delegated inference.1617 npmCreative Commons Attribution Non Commercial No Derivatives 4.0 International- AlicenseNot gradedqualityCmaintenanceMCP server for the MyAi decentralized AI inference network, giving MCP-compatible agents access to inference, model listing, agent browsing, network stats, wallet balance, and agent hiring.MIT
- AlicenseCqualityAmaintenanceEnables AI operators to interact with a local-first personal AI assistant, including content discovery, recommendations, signed content publishing, and peer exchange through MCP tools.39MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to discover, reserve, and dispatch inference to GPU nodes via MCP tools, using signed handles for stateless reservation management.Apache 2.0