existence-master/Sentient

A personal AI assistant for everyone

Sentient – Open‑Source Personal AI Assistant

What it is – Sentient is an open‑source, self‑hostable AI‑powered personal assistant. It aims to be a “central command centre” that can chat (text + voice), learn your habits, run multi‑step or recurring tasks, and keep an eye on your email and calendar. The project’s stated ambition is to evolve into fully autonomous agents that take care of boring busy‑work so you can focus on higher‑level goals.

Key capabilities

  • Chat – Conversational interface via text or voice.
  • Memory – Stores “memories” about you to personalize responses and actions.
  • Task automation – Create, schedule, trigger, or run recurring “swarm” tasks from a dedicated Tasks page.
  • Proactive scheduling – Reads your email and calendar, suggests slots and sends reminders.
  • App integration – Connects to more than 20 everyday tools (the exact list isn’t in the README).

How to try it

  1. Visit the hosted demo at sentient.existence.technology.
  2. For a private setup, clone the repo and follow the Running Sentient from source guide in the GitBook docs: https://sentient-2.gitbook.io/docs/getting-started/running-sentient-from-source-self-host.

Self‑hosting & privacy – The whole platform is released under the GNU AGPL, and the authors emphasise that you can run it locally so your data never leaves your machine.

Community & contribution

  • Contributions are welcomed; a contributor‑rocks badge shows activity.
  • A full contributing guide and code‑of‑conduct are provided.
  • The core team listed consists of two developers (Sarthak and Kabeer) with links to their GitHub profiles.

License – GNU Affero General Public License (AGPL), meaning any public deployment must also share its source code.

Where to learn more

All information above is taken directly from the repository’s README; no additional features are inferred.

Related

  • Project
    itwanger/PaiAgent

    PaiAgent is an open‑source, enterprise‑grade platform that lets users visually compose AI workflows with drag‑and‑drop nodes. It supports multiple large‑model providers via Spring AI, offers two execution engines (a classic DAG engine and a LangGraph4j state‑graph engine), includes a declarative “Skills” system for LLM‑driven function calls, and provides real‑time SSE debugging. The stack is React + TypeScript on the front‑end and Spring Boot 3 + Java 21 on the back‑end, with MySQL (and optional MinIO) for persistence.

  • Project
    FireRedTeam/FireRedASR2S

    An industrial-grade all-in-one ASR system that combines speech recognition, voice activity detection, language identification, and punctuation prediction, with specialized support for Chinese dialects.

  • Project
    OpenClaudia/openclaudia-skills

    OpenClaudia is a free, MIT‑licensed collection of 77 markdown‑based “skills” that let an AI coding agent (Claude Code, Codex, etc.) perform end‑to‑end marketing tasks—SEO audits, blog writing, ad copy, email sequences, social‑media posting, analytics, and more—by invoking simple slash commands. Install with `npx openclaudia install --all`, configure any needed API keys, and the agent can generate, publish, and send marketing assets locally, offering a fully customizable alternative to paid AI‑marketing SaaS.

  • Project
    Picovoice/speech-to-text-benchmark

    A minimalist framework for benchmarking speech-to-text engines across various datasets to compare accuracy, latency, and computational efficiency.