OPEN SOURCE AI AUTOMATION

AI Agents That Work
For Everyone

No-Code AI Agent Runtime • Open Source • 30-Second Setup

Run plug-and-play specialist agents or build your own. One command for any domain —
medical, legal, DevOps, finance. Zero config. Infinite sessions.

Get Started ⭐ Star on GitHub
Apache 2.0 • 13+ AI Providers • Adaptive Compression • Single Binary

Why Octomind?

The problems every AI agent user hits — and how Octomind solves them

The Problem

  • ✕
    Setup fatigue 45 minutes of MCP config, prompts, and dependencies before your first question
  • ✕
    Context rot Your agent forgets decisions from an hour ago — you repeat yourself constantly
  • ✕
    Rate limit death Hit a limit mid-task, restart from scratch, lose all context
  • ✕
    Generic agents Same one-size-fits-all for every domain — no specialization, no expertise

Octomind

  • →
    Zero config Install, set one API key, run. Productive in 30 seconds
  • →
    Adaptive compression 72.5% token savings — 4-hour sessions stay sharp, nothing forgotten
  • →
    13+ providers Swap mid-session with /model — no restart, no lost context
  • →
    Tap registry One-command specialists for medical, legal, DevOps, finance, and more

One Command. Any Specialist.

Like Homebrew for AI agents — community-built specialists you run with a single command

octomind
$ octomind run doctor:blood
Installed medical specialist. Paste your lab results...
$ "Interpret these blood test results for a 45-year-old male"
WBC slightly elevated — likely infection. LDL/HDL ratio normal...
$ octomind run devops:kubernetes
Installed Kubernetes specialist with kubectl, helm, kustomize...
$ "Why is my pod stuck in CrashLoopBackOff?"
Checking logs... Found OOMKilled. Memory limit too low...

Browse 50+ specialists in the Tap registry. Or build and share your own.

Rust Expert octomind run developer:rust
Contract Lawyer octomind run lawyer:contracts
Financial Analyst octomind run finance:analyst
Security Auditor octomind run security:owasp

Built for Customizable AI Agents

A no-code AI agent runtime with the power developers need

🧠 Memory

Stop Context Rot

Adaptive compression saves 72.5% of tokens automatically. Work for 4+ hours — the agent remembers decisions from hour one. Cache-aware cost analysis ensures compression only triggers when it saves money.

🔄 Flexibility

13+ Providers, Zero Lock-in

OpenRouter, OpenAI, Anthropic, DeepSeek, Google, Ollama, and more. Switch models mid-session with /model. Hit a rate limit? Swap providers instantly — no restart, no lost context.

⚡ Power

Dynamic MCP

Agents extend themselves at runtime. Register new MCP servers mid-session — no restart, no config edits. The agent decides what tools it needs and loads them on the fly.

🚀 Simplicity

Zero Config, Full Control

Single Rust binary — installs in 30 seconds. Works out of the box with sensible defaults. Power users: customize everything with TOML — per-role models, spending limits, sandboxed execution.

Get Started in 30 Seconds

Three steps. No config files. No MCP setup. Just run.

1

Install

brew install muvon/tap/octomind

Install via Homebrew on macOS

2

Set API Key

export OPENROUTER_API_KEY=your_key

Works with 13+ providers: OpenRouter, OpenAI, Anthropic, Google, DeepSeek, Ollama, and more.

3

Run

octomind run developer:rust

Pick any specialist. Zero config required.

Alternative Install Methods

Install Script curl -fsSL https://raw.githubusercontent.com/muvon/octomind/master/install.sh | bash
Cargo cargo install octomind
From Source git clone https://github.com/muvon/octomind cd octomind && cargo build --release
Apache 2.0

100% Open Source

Octomind is fully open source — no vendor lock-in, no hidden costs. Read every line of code, self-host on your infrastructure, and shape the future of AI agents.

Star on GitHub Contribute Report Issues
Rust + Zero Dependencies · Community Tap · Self-Hostable