Octomind
About
Open-source AI agent runtime CLI in Rust — MCP host with dynamic server registration, 48+ specialist agents, and 13+ LLM providers.
Details
- Author
- muvon
- Categories
- Developer Tools, AI
Jump to
Setup
Install Octomind in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/muvon/octomind
Follow the installation instructions in the repository README, then restart your MCP client.
Octomind is an open-source AI agent client: the model calls MCP tools to do real work — read and write files, run shells, search code, delegate to sub-agents. Most agent CLIs are chat interfaces that happen to run in a terminal. Octomind is a runtime that happens to have one: the same session runsinteractively,piped through stdin, as abackground daemon, overWebSocket, or as anACP sub-agentinside another agent's stack. Models, tools, roles, guardrails, budgets — all of it is TOML, no framework code.
# Interactive octomind run developer:general # Piped — CI, scripts, automation echo "Explain the auth module" | octomind run developer:general --format plain # Daemon — long-running, inject messages from anywhere echo "watch the build" | octomind run --name watcher --daemon --format jsonl octomind send --name watcher "run the test suite"
- Quick Start
- Benchmarks — Real PRs, Held-Out Tests
- Why Octomind?
- One Binary, Five Surfaces
- Guardrails — Policy as Code
- Cost as a Control Plane
- Sessions That Stay Sharp at Hour 4
- Intent-Driven Context
- Specialists & Taps
- Built-in MCP Tools
- Power Users — Roles, Workflows, Layers
- Installation
- Configuration
- Architecture
- Contributing
- Documentation
- License
Octomind v0.40.2 Role: developer · Model: octohub:auto ~/your/project > _
You're in a session with an agent that can read your code, run commands, edit files, and grow capabilities as needed. Plain-line interface with markdown rendering and shell completions — no TUI to learn, works over SSH, intmux, in CI logs.
octomind loginconnects you toOctomind Cloud— a subscription that includes model access through the octohub gateway, so there's nothing to configure. Prefer your own keys? Skip login entirely andbring any provider: OpenRouter, Anthropic, OpenAI, DeepSeek, Ollama, and more. Cloud is the baseline; BYOK is always a first-class path.
developer:general(andlawyer:sg,doctor:blood, …) come from the built-in default tapmuvon/tap, not your local config. The config's own default tag isassistant:concierge, so plainoctomind runstarts that. The banner above is illustrative (the real one renders a pixel icon to the left of the text block).
Other installs:cargo install octomind(Rust 1.95+) orbuild from source.
- The harness is the leverage.opencode ran the same model on the same endpoint at the same prices — a pure harness A/B. octomind solved 24 vs 19, at half the cost: context discipline plus supervision on exactly the deep-root-cause tasks where unsupervised agents declare victory too early.
- Worst-case pricing, still ahead.glm-5.2 ran without prompt caching (every token at list price) while Opus billed ~97% of context re-reads at 1/10 cache rates — and octomind still led on solves, cost, and wall time.
- Reproducible.Full per-case table, run artifacts, and reproduction guide:BENCHMARK.md @ 8aa3968. The story behind the benchmark:blog post.
Agent CLIs in 2026 all do interactive chat well. The gaps open up the moment you leave the keyboard:
- Autonomy needs policy, not popups.Other CLIs make the human the safety layer — every dangerous call waits for an approval click. That breaks in CI, daemons, and scheduled runs. Octomind enforces deterministic guardrails from a TOML file instead. SeeGuardrails.
- Config wars.No central registry. Skills here, MCP servers there, agent configs nowhere. The community calls it"solidarity in frustration."Octomind ships a tap registry: each agent is one TOML file in a Git repo,octomind run category:variantand it works.
- Generic AI hallucinates in expert domains.ChatGPT writes wrong drug dosages. Lawyers cite cases that don't exist. Multi-agent specialization is nowthe default architecturefor serious work — Octomind runs packaged specialists, one command each.
- One generic assistant for every task.Rust debugging, blood-test interpretation, contract review — same prompt, same tools. Drift compounds.
- Sessions break at hour 4.Naive truncation drops the decisions you need. Quality collapses. You restart. Octomind's compaction is cache-aware and structurally preserving. SeeSessions.
- Bills surprise you.Cursor users posting $7K daily overages. No per-task budget, no kill switch. Octomind enforces hard spending caps — before the bill, not after. SeeCost.
- Context is preloaded and bloated.Most harnesses load every tool and skill up front. Octomind activates skills and capabilities on intent. SeeIntent-Driven Context.
The same session engine, exposed however your workflow needs it:
# ACP — drop into any multi-agent system as a sub-agent octomind acp developer:general # Non-interactive — the message is read from stdin (pipe it in), output as plain text echo "Explain the auth module" | octomind run developer:general --format plain # Structured JSONL output for pipelines echo "List TODO items" | octomind run developer:general --format jsonl # Daemon — keep a session alive and inject messages into it from anywhere echo "first task" | octomind run --name watcher --daemon --format jsonl octomind send --name watcher "now run the test suite" # Structured output — constrain replies to a JSON Schema (structured-output models only) echo "List TODO items as JSON" | octomind run developer:general --format jsonl --schema todos.schema.json
octomind runhasno message argument— when--formatis set, input comes from piped stdin.--formatisrun-only (it accepts onlyplainorjsonl;serverandacpdo not take it). Setting--formattriggers non-interactive mode only when stdin isnota terminal:octomind run developer:general --format plaintyped at a TTY stays interactive, while piping into it runs once and exits. Pass--schema <file.json>to force replies to match a JSON Schema (requires a structured-output-capable model — Anthropic models error out); see theCLI reference.
SeeWebSocket Server,ACP Protocol, and[Daemon & Hooksfor the integration modes.
Other agent CLIs make the human the safety layer: every dangerous tool call pops a modal, every file write waits for a click. That works for one developer at the keyboard. It breaks the moment you point an agent at a long-running task, a CI job, or an autonomous loop.
…
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
