Back to directory

Moltis

A single-binary, sandboxed personal agent server written in Rust that runs on the user's own hardware and connects to voice, messaging, and browser channels.

Moltis

Moltis is a persistent personal AI agent server distributed as a single Rust binary with no separate runtime to install. Every command it runs executes inside a sandboxed container rather than directly on the host, and API keys stay on the machine it runs on, whether that is a small home server, a single-board computer, or another server the user owns.

It supports voice interaction, cross-session memory recall, automatic edit checkpoints, task scheduling, and connections to Telegram, Signal, and Discord, plus browser automation and SSH or node-backed remote execution, a managed deploy-key system with host pinning, and context-file threat scanning, all without a plugin marketplace that could introduce a supply-chain risk. Its core agent loop and model interface are a small, deliberately auditable portion of a larger Rust workspace organized into modular crates, with unsafe code isolated to FFI boundaries.

It is licensed under the MIT license.

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.