Open Source · Apache 2.0

Install agents,
not frameworks.

Open-source runtime for specialist AI agents.
We believe AI agents should be installable.

# 30 seconds to a domain-grounded specialist
$ curl -fsSL https://octomind.run/install.sh | bash
$ octomind run assistant:concierge # Singapore law specialist with 523 Acts wired in
What We Believe

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:

1

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."

2

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.

3

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."
The Product

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.

# Install specialist agents from the tap registry
$ 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.

Composable Pipelines

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.

Example: Issue → Reviewed PR
Spec Expander
Gemini Flash
Test Writer
Claude Sonnet
Implementer
Claude Sonnet
Validator
Deterministic
Critic
Claude Opus
PR Creator
Claude Haiku

Cheap models for routine. Frontier for judgment. Adversarial review built in.

Every Domain

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.

</>
Software Development
Rust, Python, TypeScript specialists. Code review. Refactoring.
SRE
DevOps & SRE
Incident response. Runbook execution. Post-mortem writing.
SEC
Security
Penetration testing. Vulnerability scanning. Audit reports.
LAW
Legal & Compliance
Contract review. Compliance monitoring. Document drafting.
FIN
Finance
Invoice processing. Fraud detection. Financial analysis.
MKT
Marketing
SEO writing. Content pipelines. Social scheduling. Analytics.
DATA
Data & Analytics
Database queries. Anomaly detection. Report generation.
MED
Healthcare
Lab analysis. Clinical notes. Patient scheduling.
Self-hosted by default. Your data never leaves your infrastructure. Critical for legal, healthcare, finance, and government deployments where data sovereignty is non-negotiable.
Architecture

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.

Vision

Where we're going

Today
One command installs a specialist agent. 48 taps across 12 domains.
Next
Composable pipelines: per-step models, adversarial review, validate gates.
Then
Premium tap marketplace. Domain experts publish, everyone else installs.
Future
Specialist AI agents as community infrastructure. Built by experts, run anywhere.
"We believe AI agents should be a community resource — like packages, not products. Built by experts, shared freely, composable by anyone."
Roadmap

What's next

Shipping fast. All in the open.

Shipped
Core Runtime
13+ providers, MCP native, adaptive compression, 5 runtime modes (CLI, ACP, WebSocket, daemon, pipes), tap system, multi-agent sessions, OS-level sandbox.
Shipped
48 Specialists Across 12 Domains
Developer (Rust/Python/TS), DevOps, Security, Lawyer (9 jurisdictions: AU/CA/DE/FR/IN/SG/TH/UK/US), Doctor, Finance, Launch, Video, Content. SKILL.md spec native.
Now
Composable Pipelines
Multi-step workflows with per-step models. Adversarial review. Validate scripts as deterministic post-LLM quality gates. Webhook triggers.
Next
Premium Tap Marketplace
Open marketplace for verified specialist taps. Domain experts (lawyers, doctors, engineers) publish; teams install.
Then
Vertical Tap Bundles
Curated tap collections for regulated industries — legal, medical, finance — with signed manifests and provenance.
Vision
Specialist agents as community infrastructure
Every team runs on composable, specialist AI — owned, portable, grounded in domain knowledge. Built by experts, shared freely, run anywhere.
Principles

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.