Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Most power users wanting a self-hosted AI assistant today that runs 24/7 and learns preferences have been either (a) running Open Interpreter or PrivateGPT as a single-binary CLI with no operator dashboard, (b) reaching for vendor-controlled cloud assistants (Replit Agent / Cursor Background Agents / GitHub Copilot Workspace) that lock-in the user's data + workflows, or (c) maintaining separate Sl
Who should use it
Who should skip it
Pass on Vellum Assistant: MIT Open-Source 24/7 AI Assistant Platform (TS/Bun + Vite/React + Agent Skills, Better-SQLite3) if its scope or audience does not match what your team is building right now.
About this signal
Vellum Assistant: MIT Open-Source 24/7 AI Assistant Platform (TS/Bun + Vite/React + Agent Skills, Better-SQLite3) is tracked by RepoRadar as a tool in the Radar section. It was first seen on 2026-07-08 and last updated on 2026-07-08. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, Vellum Assistant: MIT Open-Source 24/7 AI Assistant Platform (TS/Bun + Vite/React + Agent Skills, Better-SQLite3) is strongest on workflow potential (9.1) and open-source/build quality (8.4) and weakest on maturity (6.3) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned Vellum Assistant: MIT Open-Source 24/7 AI Assistant Platform (TS/Bun + Vite/React + Agent Skills, Better-SQLite3) a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 0.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The 843* / 126-fork / 5-subscriber repo is at active maintenance but the consumer SHOULD note 843* is below the typical 1; 000+ star threshold for RepoRadar try_now picks -- the niche audience (power users wanting a self-hosted MIT AI assistant + multi-channel AI assistant users + decoupled-frontend AI platform adopters) is real but small; the consumer SHOULD note the project requires Bun (or Node.js) + better-sqlite3 + a target AI provider API key (Anthropic Claude / OpenAI / local model) -- the consumer SHOULD verify their runtime environment has Bun installed (or fall back to `npm install` + Node.js 20+); the consumer SHOULD note the better-sqlite3 zero-dependency DB stores per-user preferences + provider config + audit logs in `assistant.db` (the consumer SHOULD back up `assistant.db` regularly + review the schema migrations).