🌐 US-Proxy
data-sveltekit-preload-data="hover">
OPEN SOURCE AGENT RUNTIME

Install agents,
not frameworks.

Open-source runtime for specialist AI agents

Stop wiring MCP servers, glue code, and credentials. One command gives you a specialist with the right model, tools, and prompts — ready to run.

$ octomind run assistant:concierge
Benchmarked on 25 real PRs: octomind + an open model solved 24/25 — ahead of Claude Code and Codex →
Apache 2.0 20+ AI Providers Adaptive Compression Single Binary

Why Octomind?

The four pains every agent builder hit in 2026 — and what Octomind does instead

The Problem

  • Config Wars Stitching three tools, writing glue code nobody wants to own. No central registry, no quality signal.
  • Generic AI fails in expert domains Wrong drug dosages. Hallucinated case citations. NY moving to ban AI chatbots posing as lawyers.
  • Sessions break at hour 4 Naive truncation drops the decisions you need. Quality collapses. Restart.
  • Bills surprise you $7K daily overages. No per-task budget. No kill switch.

Octomind

  • Tap registry One command installs a specialist with the right model, MCP servers, and prompts — pre-wired by domain experts.
  • 117 specialists across 28 domains Lawyer (9 jurisdictions), doctor, engineer, devops, finance, security, content, launch. Grounded MCP, not vibes.
  • Adaptive compression Cache-aware, structurally preserving. 4-hour sessions stay sharp. Smaller context, faster responses, lower cost.
  • Hard spending caps Per-request and per-session enforced — agent stops, falls back, or warns before the bill.
Benchmarked on real PRs

The harness matters as much as the model

25 tasks harvested from pull requests merged in 2026 — python, php, rust, c++, js — graded by each project's own held-out tests. Four agents, stock settings, no tuning.

AgentModelSolvedJudge Σ / 2500CostWall time
octomindglm-5.2 (open)24/252264$63.433.6h
claude codeclaude-opus-523/252262$81.796.7h
codexgpt-5.6-sol21/252127$14.861.0h
opencodeglm-5.2 (open)19/252093$129.543.3h
  • Same model, same endpoint as opencode — 24 vs 19 solved at half the cost. The difference is pure harness: context discipline and supervision.
  • octomind's cost is its worst case. glm-5.2 ran via Ollama cloud with no prompt caching — every token at list price — while Opus billed ~97% of its context re-reads at 1/10 cache rates, and still came out behind on solves, cost, and time.
  • Every task is a real merged fix — mostly landed after model training cutoffs — proven fail-to-pass before benching, validated by hidden maintainer-written tests plus an LLM judge.

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 117 specialists in the Tap registry. Or build and share your own.

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

One command runs a whole team

A workflow chains specialists into a pipeline: research hands the writer a brief, an auditor scores the result, an editor fixes it — and the run halts rather than making things up. Pipe something in; a finished piece comes out.

$ octomind workflow promote.toml

promote turns one article into platform-native social drafts — a researcher grounds it, a writer drafts, and the polish loop re-edits until the audit signs off.

Built for Customizable AI Agents

No-code agent runtime that doesn't box you in

🧠 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

20+ 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.

New

Nothing to install — run it in the cloud

Octomind Cloud is open to everyone: your agents on our machines, models included, zero API keys, sessions you can pick up from any device. Free tier, no card required.

Get Started in 30 Seconds

Three steps. No config files. No API keys to collect. Just run.

1

Install

brew install muvon/tap/octomind

Install via Homebrew on macOS

2

Connect Models

octomind login

One login connects the Hub — free models included, no provider accounts. Or bring your own keys: OpenRouter, OpenAI, Anthropic, Ollama, and 20+ providers.

3

Run

octomind run developer:general

Pick any specialist. Zero config required.

Alternative Install Methods

Install Script curl -fsSL https://octomind.run/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 build agents that are actually yours.

Rust + Zero Dependencies · Community Tap · Self-Hostable