AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Multi-Agent/
moltis
moltis logo

moltis

Active·★ 3.0k·MIT·Updated 2026-10-23
★ Essential

Moltis is a personal agent server written in Rust and shipped as one binary with no Node.js or Python runtime. Its README stresses that commands run in sandboxed containers rather than on the host and that API keys stay on your machine. Features listed include multi-provider LLM support with streaming and sub-agent delegation, a web UI and channels such as Telegram, Signal, Microsoft Teams and Discord, voice I/O (8 TTS and 7 STT providers), long-term memory with SQLite, full-text and vector search, scheduling, browser automation, MCP servers over stdio and HTTP/SSE, and skills with an OpenClaw import.

On security the README lists safe Rust for core code with unsafe isolated to FFI and WASM boundaries, Docker and Apple Container sandboxes with per-session isolation, password and passkey authentication, SSRF protection, origin validation, hooks that can block tool calls, and signed releases with attestations. It claims the agent runner and model interface fit in about 7.5K lines inside a ~270K-line workspace of 59 crates. Install with a script, Homebrew, Docker or `cargo install`. The README includes a comparison table against OpenClaw and Hermes Agent; those are the authors' own figures, so verify them against your needs. It is MIT licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-15.

License
MIT
Latest release
20261023.01 · 2026-10-23
Last commit
2026-10-23
Contributors
71
Forks
363
Open issues and PRs
121
First published
2026-01-29

Source: GitHub, npm and PyPI public APIs.

#Rust#AI Agent#Personal Server#Sandboxing#LLM Gateway#Multi-channel#Local-first#Security
$ Install
$ curl -fsSL https://www.moltis.org/install.sh | sh
↗ Visit site★ GitHub
01

Features

01AI Gateway: Supports multiple LLM providers (OpenAI Codex, GitHub Copilot, Local), streaming responses, agent loop with sub-agent delegation, and parallel tool execution.
02Secure & Sandboxed Execution: Ensures secure operation with sandboxed command execution (Docker, Apple Container), encryption-at-rest vault, and robust authentication mechanisms.
03Persistent Memory & Recall: Features per-agent memory workspaces, embeddings-powered long-term memory, hybrid vector + full-text search, and cross-session recall for durable state.
04Multi-Channel Communication: Offers a Web UI, API access, and integrations with popular messaging platforms like Telegram, Signal, Discord, along with built-in voice I/O.
02

Why choose it

+Single Rust binary with no Node.js or Python runtime to manage
+Commands run in sandboxes (Docker, Podman, Apple Container, WASM) instead of on the host
+Broad feature set: chat channels, voice, memory, scheduling, browser automation and MCP
+Security measures are spelled out, including passkeys, SSRF protection and signed releases
03

Trade-offs

!The comparison table with OpenClaw and Hermes Agent comes from the project itself
!Sandboxed execution depends on Docker, Podman or Apple Container being available
!The README says it recently reached the Hacker News front page and asks for issues about any friction, which suggests rough edges for newcomers
!The 59-crate codebase is large to audit, even if the core agent loop is small
04

Maintenance check

ActiveChecked: 2026-11-07
Last commit
2026-10-23
Commits, last 90 days
100+
Releases, last 90 days
15
Latest release
20261023.01 (2026-10-23)
Open issues
121
Recent issues with at least one comment
4/18
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 74, 24, 20, 5, 6, 2, 0, 0, 1, 15, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #748 [Feature]: easy way to "retry" a prompt on error7 comments · 2026-04-16
  • #574 [Feature]: Model Routing Per topic5 comments · 2026-04-06
  • #136 [Bug]: With some models, moltis says it will do something then stops5 comments · 2026-02-15
  • #235 PTY-based interactive Claude Code CLI control for autonomous multi-agent orchestration6 comments · 2026-02-25

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Rust
Runtime
Verified via docs
macOS
OS
Verified via docs
Linux
OS
Verified via docs
Docker
Containerization
Verified via docs
WASM
Execution Environment
Verified via docs
06

Quick start

1
$ curl -fsSL https://www.moltis.org/install.sh | sh
07

Use cases

↳Deploying a personal, secure AI assistant on your own hardware.
↳Automating tasks and managing AI agent interactions across various communication platforms like Telegram or Discord.
↳Integrating and managing multiple large language model providers through a single, secure, local-first gateway.
↳Building custom AI skills and sophisticated workflows with persistent memory and sandboxed execution.
08

Alternatives

⚡Top VS:
VSthClaws★1.3k→VSintentkit★6.5k→VSBotSharp★3.1k→VSii-agent★3.4k→
thClaws logo
thClaws★ 1.3k
Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.
VSCompare→
mayros logo
mayros★ 13
Production-ready AI agent framework — semantic memory, multi-agent mesh, MCP server, intelligent routing, governance, and 67+ platform integrations.
intentkit logo
intentkit★ 6.5k
An open and fair framework for everyone to build AI agents equipped with powerful skills. Launch your agent, improve the world, your wallet, or both!
VSCompare→
BotSharp logo
BotSharp★ 3.1k
AI Multi-Agent Framework in .NET
VSCompare→
ii-agent logo
ii-agent★ 3.4k
II-Agent: a new open-source framework to build and deploy intelligent agents
VSCompare→
wanwu logo
wanwu★ 2.4k
China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intelligent agents, workflows, and rag, and also supports model management. The platform features a developer-friendly license, and we welcome all developers to build upon the platform.
VSCompare→
zeroshot logo
zeroshot★ 2.2k
Your autonomous engineering team in a CLI. Point Zeroshot at an issue, walk away, and return to production-grade code. Supports Claude Code, OpenAI Codex, OpenCode, and Gemini CLI.
VSCompare→
madcop logo
madcop★ 26
MadCop — local-first AI agent desktop workstation (v0.9). Multi-model chat, tool-use, MCP servers, 12 workflow modes, knowledge base, AI design tool, persistent workspace.
VSCompare→
See all alternatives →

Featured in these lists

  • Best Open-Source AI Agent Sandboxes and Code Execution Runtimes

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
moltis-org /
moltis
↗

Persistent, sandboxed personal agent server in a single Rust binary

3.0k363MIT
Last commit1mo ago
StatusActive
CategoryMulti-Agent
Contributors71
Latest release20261023.01
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.