moltis

作者 moltis-org已验证

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on your hardware.

2,833
Stars
340
Forks
Rust
语言
2026/8/23
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/moltis-org/moltis

快速入门

使用 moltis 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

Moltis

Moltis — A secure persistent personal agent server in Rust

One binary — sandboxed, secure, yours.

CI codecov CodSpeed License: MIT Rust Discord

InstallationComparisonArchitectureSecurityFeaturesHow It WorksContributing


Moltis recently hit the front page of Hacker News. Please open an issue for any friction at all. I'm focused on making Moltis excellent.

Secure by design — Your keys never leave your machine. Every command runs in a sandboxed container, never on your host.

Your hardware — Runs on a Mac Mini, a Raspberry Pi, or any server you own. One Rust binary, no Node.js, no npm, no runtime.

Full-featured — Voice, memory, cross-session recall, automatic edit checkpoints, scheduling, Telegram, Signal, Discord, browser automation, MCP servers, SSH or node-backed remote exec, managed deploy keys with host pinning in the web UI, a live Settings → Tools inventory, Cursor-compatible project context, and context-file threat scanning — all built-in. No plugin marketplace to get supply-chain attacked through.

Auditable — The agent runner and model interface fit in ~7.5K lines, with providers in ~19K more. The Rust workspace is ~270K lines across 59 modular crates you can audit independently, with 470+ Rust files containing tests. Unsafe code is isolated to FFI and precompiled runtime boundaries, not the core agent loop.

Installation

# One-liner install script (macOS / Linux)
curl -fsSL https://www.moltis.org/install.sh | sh

# macOS / Linux via Homebrew
brew install moltis-org/tap/moltis

# Docker (multi-arch: amd64/arm64)
docker pull ghcr.io/moltis-org/moltis:latest

# Or build from source
cargo install moltis --git https://github.com/moltis-org/moltis

Comparison

OpenClawHermes AgentMoltis
Primary stackTypeScript + Swift/Kotlin companion appsPython + TypeScript TUI/web surfacesRust
RuntimeNode.js + npm/pnpm/bunPython + uv/pip, optional Node UI piecesSingle Rust binary
Local checkout size*~1.1M app LoC~152K app LoC~270K Rust LoC
ArchitectureBroad gateway, channel, node, and app ecosystemCLI/gateway agent with learning loop and research toolingPersistent personal agent server with modular crates
Crates/modulesnpm packages, extensions, appsPython packages, plugins, tools, TUI59 Rust workspace crates
Sandbox/backendsApp-level permissions, browser/node toolsLocal, Docker, SSH, Daytona, Singularity, ModalDocker/Podman + Apple Container + WASM
Auth/accessPairing and local gateway controlsCLI and messaging gateway setupPassword + Passkey + API keys + Vault
Voice I/OVoice wake and talk modesVoice memo transcriptionBuilt-in STT + TTS providers
MCPPlugin/integration supportMCP integrationstdio + HTTP/SSE
SkillsBundled, managed, and workspace skillsSelf-improving skills and Skills Hub supportBundled/workspace skills + autonomous improvement + OpenClaw import
Memory/RAGPlugin-backed memory and context engineAgent-curated memory, session search, user modelingSQLite + FTS + vector memory

* LoC measured with tokei, excluding node_modules, generated build output, dist, and target.

Full comparison in the docs →

Architecture — Crate Map

Current Rust workspace: ~270K LoC across 59 crates. The table below groups the main crates by role so the architecture stays scannable.

Core runtime:

CrateLoCRole
moltis-gateway37.4KHTTP/WS server, RPC, auth, startup wiring
moltis-tools37.0KTool execution, sandboxing, WASM tools
moltis-providers18.9KLLM provider implementations
moltis-agents14.5KAgent loop, streaming, prompt assembly
moltis-chat14.2KChat engine, agent orchestration
moltis-config10.3KConfiguration, validation
moltis-httpd9.9KHTTP server primitives and middleware
moltis (CLI)4.7KEntry point, CLI commands
moltis-sessions3.5KSession persistence
moltis-common1.5KShared utilities
moltis-service-traits1.2KShared service interfaces
moltis-protocol0.7KWire protocol types

Feature and integration crates:

CategoryCratesCombined LoC
Channelsmoltis-telegram, moltis-whatsapp, moltis-signal, moltis-discord, moltis-msteams, moltis-matrix, moltis-slack, moltis-nostr, moltis-channels34.0K
Web and APIsmoltis-web, moltis-graphql, moltis-webhooks10.8K
Extensibilitymoltis-mcp, moltis-mcp-agent-bridge, moltis-skills, moltis-plugins11.5K
Memory and contextmoltis-memory, moltis-qmd, moltis-code-index, moltis-projects11.7K
Voice and browsermoltis-voice, moltis-browser9.2K
Auth and securitymoltis-auth, moltis-oauth, moltis-vault, moltis-secret-store, moltis-network-filter, moltis-tls8.5K
Scheduling and automationmoltis-cron, moltis-caldav, moltis-auto-reply4.7K
Setup and importmoltis-provider-setup, moltis-openclaw-import, moltis-onboarding11.7K
Native and node hostsmoltis-swift-bridge, moltis-node-host, moltis-courier5.7K
WASM toolsmoltis-wasm-precompile, moltis-wasm-calc, moltis-wasm-web-fetch, moltis-wasm-web-search1.4K
Supporting cratesmoltis-media, moltis-metrics, moltis-tailscale, moltis-routing, moltis-canvas, moltis-schema-export, benchmarks2.1K

Use --no-default-features --features lightweight for constrained devices (Raspberry Pi, etc.).

Security

  • Small unsafe surface — core agent/gateway code stays safe Rust; unsafe is isolated to Swift FFI, local model wrappers, and precompiled WASM boundaries
  • Sandboxed execution — Docker + Apple Container, per-session isolation
  • Secret handlingsecrecy::Secret, zeroed on drop, redacted from tool output
  • Authentication — password + passkey (WebAuthn), rate-limited, per-IP throttle
  • SSRF protection — DNS-resolved, blocks loopback/private/link-local
  • Origin validation — rejects cross-origin WebSocket upgrades
  • Hook gatingBeforeToolCall hooks can inspect/block any tool invocation
  • Supply chain integrityartifact attestations, Sigstore keyless signing, GPG signing (YubiKey), SHA-256/SHA-512 checksums

See Security Architecture for details. Verify releases with gh attestation verify <artifact> -R moltis-org/moltis or see Release Verification.

Features

  • AI Gateway — Multi-provider LLM support (OpenAI Codex, GitHub Copilot, Local), streaming responses, agent loop with sub-agent delegation, session modes, parallel tool execution
  • Communication — Web UI with command-palette agent prompts and Markdown copy/export, Telegram, Signal, Microsoft Teams, Discord, Slack with native live tool cards, Nostr DMs + NIP-29 group chat (incl. Block's Buzz channels), API access, voice I/O (8 TTS + 7 STT providers), mobile PWA with push notifications
  • Memory & Recall — Per-agent memory workspaces, embeddings-powered long-term memory, hybrid vector + full-text search, session persistence with auto-compaction, cross-session recall, Cursor-compatible project context, context-file safety scanning
  • Managed Files - Authenticated nested file management in Settings, with an agent-advertised host path and independent read-only-by-default mounts for Docker, Podman, and Apple Container sandboxes
  • Safer Agent Editing — Automatic checkpoints before built-in skill and memory mutations, restore tooling, session branching
  • Extensibility — MCP servers (stdio + HTTP/SSE), skill system, 15 lifecycle hook events with circuit breaker, destructive command guard
  • Agent Client Protocol — drives external ACP agents (codex-acp, claude-agent-acp, Cursor), and serves Moltis to ACP clients over stdio via moltis acp
  • Security — Encryption-at-rest vault (XChaCha20-Poly1305 + Argon2id), password + passkey + API key auth, sandbox isolation, SSRF/CSWSH protection
  • Operations — Cron scheduling, durable local CalDAV, Gmail, Himalaya email, and reusable Slack/Discord/Matrix/Teams message datasets, provider-specific read-only agent tools, fast full-text search, JSONL/Markdown projections, agent instrumentation (Langfuse for LLM traces, OTLP for Grafana/Datadog), Prometheus metrics, cloud deploy (Fly.io, DigitalOcean), Tailscale integration, managed SSH deploy keys, host-pinned remote targets, live tool inventory in Settings, and CLI/web remote-exec doctor flows

How It Works

Moltis is a local-first persistent agent server — a single Rust binary that sits between you and multiple LLM providers, keeps durable session state, and can meet you across channels without handing your data to a cloud relay.

┌─────────────┐  ┌─────────────┐  ┌─────────────┐
│   Web UI    │  │  Telegram   │  │  Discord    │
└──────┬──────┘  └──────┬──────┘  └──────┬──────┘
       │                │                │
       └────────┬───────┴────────┬───────┘
                │   WebSocket    │
                ▼                ▼
        ┌─────────────────────────────────┐
        │          Gateway Server         │
        │   (Axum · HTTP · WS · Auth)     │
        ├─────────────────────────────────┤
        │        Chat Service             │
        │  ┌───────────┐ ┌─────────────┐  │
        │  │   Agent   │ │    Tool     │  │
        │  │   Runner  │◄┤   Registry  │  │
        │  └─────┬─────┘ └─────────────┘  │
        │        │                        │
        │  ┌─────▼─────────────────────┐  │
        │  │    Provider Registry      │  │
        │  │  Multiple providers       │  │
        │  │  (Codex · Copilot · Local)│  │
        │  └───────────────────────────┘  │
        ├─────────────────────────────────┤
        │  Sessions  │ Memory  │  Hooks   │
        │  (JSONL)   │ (SQLite)│ (events) │
        └─────────────────────────────────┘
                       │
               ┌───────▼───────┐
               │    Sandbox    │
               │ Docker/Apple  │
               │  Container    │
               └───────────────┘

See Quickstart for gateway startup, message flow, sessions, and memory details.

Getting Started

Build & Run

Requires just (command runner) and Node.js (for Tailwind CSS).

git clone https://github.com/moltis-org/moltis.git
cd moltis
just build-css                  # Build Tailwind CSS for the web UI
just build-release              # Build in release mode
cargo run --release --bin moltis

For a full release build including WASM sandbox tools:

just build-release-with-wasm    # Builds WASM artifacts + release binary
cargo run --release --bin moltis

Open https://moltis.localhost:3000. On first run, a setup code is printed to the terminal — enter it in the web UI to set your password or register a passkey.

Optional flags: --config-dir /path/to/config --data-dir /path/to/data

Docker

# Docker / OrbStack
docker run -d \
  --name moltis \
  -p 13131:13131 \
  -p 13132:13132 \
  -p 1455:1455 \
  -v moltis-config:/home/moltis/.config/moltis \
  -v moltis-data:/home/moltis/.moltis \
  -v /var/run/docker.sock:/var/run/docker.sock \
  ghcr.io/moltis-org/moltis:latest

Open https://localhost:13131 and complete the setup. For unattended Docker deployments, set MOLTIS_PASSWORD, MOLTIS_PROVIDER, and MOLTIS_API_KEY before first boot to skip the setup wizard. See Docker docs for Podman, OrbStack, TLS trust, and persistence details.

Cloud Deployment

ProviderDeploy
DigitalOceanDeploy to DO

Fly.io (CLI):

fly launch --image ghcr.io/moltis-org/moltis:latest
fly secrets set MOLTIS_PASSWORD="your-password"

All cloud configs use --no-tls because the provider handles TLS termination. See Cloud Deploy docs for details.

License

MIT

常见问题

What is moltis?

moltis is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by moltis-org. A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on your hardware. It has 2,833 GitHub stars.

Is moltis safe to use?

Yes. moltis passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install moltis?

Clone the repository with "git clone https://github.com/moltis-org/moltis" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is moltis written in?

moltis is primarily written in Rust. It is open-source under moltis-org on GitHub, so you can review or fork the full source.

Are there alternatives to moltis?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh moltis against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情