Back to browse
GitHub Repository

Non-human assistant that actually does things. Sends emails, makes calls, posts to social media, and researches the web — on your behalf. Self-hosted, open source.

2 starsPython

Non-Human Assistant with near AGI capabilities

by amplifyco·Mar 4, 2026·1 point·1 comment

AI Analysis

MidBold Bet

Local agentic assistant that posts to X and LinkedIn, but full AGI claim is pure marketing.

Strengths
  • Self-hosted eliminates vendor lock-in and privacy concerns—genuine differentiator vs SaaS agents.
  • Real integrations (Telegram, email, calendar, X, LinkedIn, phone) suggest working prototype beyond slides.
  • Persistent memory + LanceDB vector store means contextual continuity across interactions.
Weaknesses
  • 'Near AGI' in title is embarrassing hyperbole; autonomous agents that draft emails exist (Gmail, Superhuman).
  • GitHub shows 2 stars and sparse recent commits—unclear if this is production-ready or abandoned experiment.
Category
Target Audience

Solo founders, small teams, users wanting local LLM agents without SaaS fees

Similar To

Superhuman · Zapier · n8n

Post Description

Nova exists to be the proactive half of your intelligence — noticing what you'd notice if you had infinite time, acting on what needs doing before you ask, and learning enough about you to anticipate rather than just respond.

A fully autonomous Non-Human Assistant you run on your own server. It connects to you via Telegram (and optionally voice, email, WhatsApp, and X), builds a persistent memory of who you are, and can take real-world actions on your behalf — from writing emails to making phone calls to researching the web.

Acts on your behalf Sends emails, posts to X and LinkedIn, makes phone calls, books calendar events, and follows up with contacts. Nova takes action. You just ask.

Learns who you are Your contacts, preferences, and working style. The more you use it, the more Nova thinks and writes like you.

Nova applies 18 defence layers to every message.

Stays on your server Zero third-party data sharing. Open-source, No monthly SaaS fee. You own the infrastructure, the data.

Similar Projects

AI/ML●●Solid

Zero Human Company in Go

Recursive self-governance lets agents patch their own role definitions based on audit findings.

Big BrainWizardry
alex_mia
102mo ago
Security●●Solid

IC-AGI – Threshold auth for AI agents, formally verified in TLA+

Impressively concrete safety architecture: K-of-N threshold approval via Shamir SSS, capability tokens with TTL/scope/consumable budgets, an append-only audit ledger and shard-isolated workers all backed by TLA+ proofs for many properties. It reads like a research-to-prototype push — there's real formal rigor and test counts shown — but the repo looks early-stage and would benefit from runnable demos, deployment examples, and clearer integration docs before I'd recommend it for production.

Big BrainBold BetNiche Gem
saezbaldo
224mo ago