Install agents,
not frameworks.
Open-source runtime for specialist AI agents.
We believe AI agents should be installable.
$ curl -fsSL https://octomind.run/install.sh | bash
$ octomind run assistant:concierge # Singapore law specialist with 523 Acts wired in
Building specialist AI agents in 2026
is a configuration war. It shouldn't be.
Multi-agent specialization became the default architecture in early 2026 — but the tooling didn't catch up. Three pains every team hits:
Config Wars
Stitching three tools, writing glue code nobody wants to own. No central registry, no quality signal — documented in The Agent Config Wars, "written in frustration, published in solidarity."
Generic AI fails in expert domains
ChatGPT writes plausible drug dosages that may be wrong. Lawyers cite cases that don't exist. New York is moving to ban AI chatbots from posing as lawyers. Generic doesn't hold under scrutiny.
Single agent, large task = drift
Drift compounds. Hallucinations grow with context. The fix is structural: break work into specialists, each with smaller, better-defined context — but no tool ships them ready to run.
"AI agents should be installable. The community should build specialist agents — not just models, not just frameworks. One command, ready to run."
One runtime. Infinite specialists.
Octomind is a single Rust binary that runs specialist AI agents. Agents are defined in TOML — no framework code, no glue, no boilerplate. Install from the community registry or build your own.
$ octomind run developer:general
$ octomind run lawyer:us
$ octomind run security:owasp
# Or run as a background daemon
$ octomind run --daemon --name myagent
# Or pipe into CI/CD
$ echo "Fix the auth bug" | octomind run --format jsonl
Tap Registry
Community-built specialist agents. Each tap is a TOML manifest with the optimal model, pre-wired MCP tools, domain system prompt, and auto-installing dependencies.
13+ AI Providers
OpenRouter, Anthropic, OpenAI, Google, DeepSeek, Ollama (local), Bedrock, Mistral, Groq, and more. Switch mid-session. Zero lock-in.
Self-Extension
Agents register new MCP servers and spawn sub-agents at runtime. AI that grows its own capabilities mid-session.
Don't build agents. Compose them.
Chain specialist agents into multi-step pipelines. Use the right model at each step — cheap for routine, frontier for judgment. All defined in TOML.
Cheap models for routine. Frontier for judgment. Adversarial review built in.
Specialists for every job a developer touches.
From software to SRE, security to finance, legal to medical — the tap registry already ships 48 specialist agents across 12 domains, growing fast. Domain experts publish; everyone else installs.
Built to be infrastructure, not just a tool
Single Rust binary. Runs anywhere. Five modes of operation for any integration pattern.
Interactive
CLI for daily work
Pipes
stdin/stdout for CI/CD
WebSocket
Remote clients & dashboards
Daemon
Background agents 24/7
ACP
Sub-agent protocol for editors
MCP Native
Built on the Model Context Protocol — the universal standard for connecting AI to tools. Every MCP server in the ecosystem is a potential capability. Register new servers at runtime, no restart needed.
Adaptive Compression
Work for 4+ hours without context degradation. Compression keeps the decisions that matter and cuts the rest — smaller context, faster responses, lower cost.
Where we're going
"We believe AI agents should be a community resource — like packages, not products. Built by experts, shared freely, composable by anyone."
What's next
Shipping fast. All in the open.
What we stand for
Open source runtime, always
Apache 2.0. The full runtime is free and always will be. Fork it, modify it, run it anywhere. We monetize convenience around the runtime — never the runtime itself.
Your data, your servers
Self-hosted by default. Your documents, code, and conversations stay on your infrastructure. Non-negotiable for regulated industries — legal, medical, finance.
Zero lock-in
13+ providers. Switch models mid-session. Your agent definitions are portable TOML files in your git repo, not someone else's cloud.
Specialists, not generalists
A single agent given a large, ambiguous task hallucinates. Multi-agent specialization is the 2026 default — but only if the specialists are pre-built. We ship them.
Community-built, expert-driven
The best Rust agent is built by a Rust expert. The best Singapore legal agent by someone who reads the 523 SG Acts. The tap registry lets domain experts publish; everyone else installs.
Cost as infrastructure
Hard spending caps, per-request and per-session, enforced — not advisory. Cache-aware accounting. Cost is treated as plumbing, not an afterthought.
Install agents,
not frameworks
Open source. Any model. Any domain.
Built with Rust. Shared by the community.
Octomind.