# Octomind.run

> Open-source coding agent harness and agent runtime: a single Rust binary that runs any LLM with MCP tools in the terminal, CI, as a daemon, over WebSocket, or via ACP.

Octomind is an open-source coding agent harness and agent runtime built by Muvon. It gives any LLM tools to read and edit files, run shells, search code and delegate to sub-agents through MCP, and runs the result as an interactive CLI, a stdin pipe, a daemon, a WebSocket server, or an ACP agent in an editor. It is released under Apache 2.0, with latest release 0.70.1.

## What It Is

Octomind is a single Rust binary that wraps a model in a session engine with tools, roles, guardrails and a supervising model. An agent is defined in TOML (model, tools, prompts, guardrails), so the same agent behaves the same on a laptop, a cloud machine or a CI pipeline. Running a specialist such as `octomind run developer:general` fetches its manifest from a tap registry, installs required tools, and opens a session.

## How a Session Works

Context is assembled per user message from AGENTS.md, matching skills (standard SKILL.md folders) and recalled lessons from earlier sessions. A second supervisor model keeps the plan, trims oversized tool results and refuses a self-reported "done" until evidence checks out. Adaptive compression folds older turns into summaries while raw messages stay in a per-session archive that a recall tool can restore verbatim. Sessions can be named and resumed across days.

## Policy as Code

Instead of approval popups, a `.agents/guardrails.toml` file defines pre-call guards, post-result hooks and post-turn validators that run deterministically, so agents can run unattended in CI, daemons or scheduled jobs. An optional `--sandbox` flag restricts writes to the working directory using Landlock on Linux or Seatbelt on macOS. Spending caps can be set per request and per session; non-interactive runs stop with exit code 75 when over budget.

## Models, Surfaces and Extensions

Models can come from the Octomind hub or from your own keys (OpenRouter, Anthropic, OpenAI, Google, DeepSeek, Bedrock, Ollama and others) and can be swapped mid-session with `/model`. Extension is via MCP servers, local scripts in `.agents/tools/`, skills and plugins; the tap system shares installable agents, workflows and skills. Structured output is available as JSONL or JSON Schema.

## Benchmark Claims

The project reports that on 25 tasks from merged pull requests in 2026, Octomind with glm-5.2 solved 24, versus 19 for OpenCode with the same model, and 23 for Claude Code with claude-opus-5. The authors publish a reproduction guide (octobench).

## Features
- Single Rust binary with any-model support, switchable mid-session
- Guardrails in TOML: pre-call guards, post-result hooks, post-turn validators
- Supervisor model that plans and verifies completion
- Adaptive context compression with recall of archived blocks
- Interactive CLI, stdin/JSONL, daemon, WebSocket server and ACP surfaces
- MCP client with dynamic server management
- Agent Skills (SKILL.md) and local project tools
- Tap registry of specialist agents and workflows
- Multi-step workflows with parallel and looped steps
- Cross-session learning
- OS-level sandbox option (Landlock/Seatbelt)
- Per-request and per-session spending caps
- Session sharing and local analysis (/share, /analyze)
- Structured output via JSON Schema

## Integrations
Model Context Protocol (MCP), Agent Client Protocol (ACP), Zed, JetBrains, Neovim, VS Code, OpenRouter, Anthropic, OpenAI, Google, DeepSeek, AWS Bedrock, Ollama, Octomind Hub, GitHub webhooks, Telegram, WhatsApp, Slack

## Platforms
WINDOWS, MACOS, LINUX, WEB, API, VSC_EXTENSION, JETBRAINS_PLUGIN, CLI

## Pricing
Open Source, Free tier available

## Version
0.70.1

## Links
- Website: https://octomind.run
- Documentation: https://octomind.run/docs
- Repository: https://github.com/Muvon/octomind
- EveryDev.ai: https://www.everydev.ai/tools/octomind-run