Back to directory

vococo

A single-user, always-on personal AI assistant built on a Claude subscription that takes voice or text tasks across a TUI, CLI and self-hosted web app, runs scheduled jobs, and keeps long-term memory in plain Markdown.

vococo

vococo is a single-user, always-on personal AI assistant built around a Claude subscription, reachable through a terminal UI, a CLI, or a self-hosted progressive web app so the same session follows the user across devices. It supports push-to-talk speech input, spoken replies, and a hands-free real-time voice mode that can be interrupted.

A background task engine shares one execution model across voice-dispatched tasks, cron jobs and separate sessions, each running in its own git worktree, and long-term memory is injected at startup from a plain Markdown file the assistant saves to and recalls from. It supports hot-swapping between DeepSeek, Kimi and other Anthropic-compatible endpoints, includes a three-tier safety gate with mobile approval for risky actions, and is written in Python.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.