Raven — AI-native command line agent with memory, proactivity, context control, and skill evolution
How to install raven?
evermind-ai/raven
$git clone https://github.com/evermind-ai/ravenInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install raven by running `git clone https://github.com/evermind-ai/raven`, then use it for the current task and follow its documentation at https://github.com/evermind-ai/raven.
README.md
| 1 | <div align="center" id="readme-top"> |
| 2 | |
| 3 |  |
| 4 | |
| 5 | <p align="center"> |
| 6 | <a href="https://x.com/evermind"><img src="https://img.shields.io/badge/EverMind-000000?labelColor=gray&style=for-the-badge&logo=x&logoColor=white" alt="X"></a> |
| 7 | <a href="https://huggingface.co/EverMind-AI"><img src="https://img.shields.io/badge/🤗_HuggingFace-EverMind-F5C842?labelColor=gray&style=for-the-badge" alt="HuggingFace"></a> |
| 8 | <a href="https://discord.gg/gYep5nQRZJ"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Fv10%2Finvites%2FgYep5nQRZJ%3Fwith_counts%3Dtrue&query=%24.approximate_presence_count&suffix=%20online&label=Discord&color=404EED&labelColor=gray&style=for-the-badge&logo=discord&logoColor=white" alt="Discord"></a> |
| 9 | <a href="https://github.com/EverMind-AI/EverOS/discussions/67"><img src="https://img.shields.io/badge/WeCom-EverMind_社区-07C160?labelColor=gray&style=for-the-badge&logo=wechat&logoColor=white" alt="WeChat"></a> |
| 10 | </p> |
| 11 | |
| 12 | [Website](https://raven.evermind.ai) · [中文](README.zh-CN.md) |
| 13 | |
| 14 | </div> |
| 15 | |
| 16 | <br> |
| 17 | |
| 18 | # Raven |
| 19 | |
| 20 | Raven is **The Self-Improving Agent Harness**, built on [EverOS](https://github.com/EverMind-AI/EverOS), with opt-in Deep Research for multi-source investigation. |
| 21 | |
| 22 | Raven helps agents improve across runs by continuously refining the systems around them: tools, skills, memory, code execution, policies, and working environment. EverOS provides durable user memory, agent memory, and world knowledge across sessions, so successful workflows can evolve into reusable Agent Templates and digital workers. |
| 23 | |
| 24 | **Update:** Raven added Deep Research. Enable it with `raven deep-research enable` |
| 25 | to give the agent access to MiroThinker-backed, multi-source research when a |
| 26 | task needs deeper investigation. |
| 27 | |
| 28 | <p align="center"> |
| 29 | <img src="https://github.com/user-attachments/assets/a4dc5b21-c8e7-4397-95e1-50afeeb826e4" alt="Starting Raven from the command line" width="100%"> |
| 30 | </p> |
| 31 | |
| 32 | <details> |
| 33 | <summary><kbd>Table of Contents</kbd></summary> |
| 34 | |
| 35 | <br> |
| 36 | |
| 37 | - [Quick Install](#quick-install) |
| 38 | - [What You Can Do in 2 Minutes](#what-you-can-do-in-2-minutes) |
| 39 | - [Messaging Gateways](#messaging-gateways) |
| 40 | - [Why Raven](#why-raven) |
| 41 | - [What Raven Is Built For](#what-raven-is-built-for) |
| 42 | - [Agent Templates](#agent-templates) |
| 43 | - [Useful Commands](#useful-commands) |
| 44 | - [Docs by Goal](#docs-by-goal) |
| 45 | - [Architecture](#architecture) |
| 46 | - [Developer Workflow](#developer-workflow) |
| 47 | - [Status](#status) |
| 48 | - [Star Us](#star-us) |
| 49 | - [EverMind Ecosystem](#evermind-ecosystem) |
| 50 | - [Contributing](#contributing) |
| 51 | |
| 52 | <br> |
| 53 | |
| 54 | </details> |
| 55 | |
| 56 | ## Quick Install |
| 57 | |
| 58 | ### Linux, macOS, WSL2 |
| 59 | |
| 60 | ```bash |
| 61 | curl -fsSL https://raven.evermind.ai/install.sh | bash |
| 62 | ``` |
| 63 | |
| 64 | ### Windows (native, PowerShell) |
| 65 | |
| 66 | > **Heads up:** Native Windows runs Raven without WSL. CLI, TUI, gateway, and |
| 67 | > tools install natively. If you would rather use WSL2, the Linux/macOS |
| 68 | > one-liner above works there too. |
| 69 | |
| 70 | Run this in PowerShell: |
| 71 | |
| 72 | ```powershell |
| 73 | irm https://raven.evermind.ai/install.ps1 | iex |
| 74 | ``` |
| 75 | |
| 76 | On **Windows PowerShell 5.1** (the version built into Windows) that command |
| 77 | fails with `Permanent Redirect`. Use the direct URL instead: |
| 78 | |
| 79 | ```powershell |
| 80 | irm https://raw.githubusercontent.com/EverMind-AI/Raven/refs/heads/main/install.ps1 | iex |
| 81 | ``` |
| 82 | |
| 83 | ### After installation |
| 84 | |
| 85 | The installer handles everything: uv, Python 3.12, Node.js 22, and Raven. |
| 86 | |
| 87 | Open a new terminal. On Linux, macOS, or WSL2, you can also reload your current |
| 88 | shell: |
| 89 | |
| 90 | ```bash |
| 91 | source ~/.bashrc # or: source ~/.zshrc |
| 92 | ``` |
| 93 | |
| 94 | Then run: |
| 95 | |
| 96 | ```bash |
| 97 | raven onboard |
| 98 | raven |
| 99 | ``` |
| 100 | |
| 101 | Raven supports OpenRouter, OpenAI, Anthropic, Gemini, DeepSeek, GitHub Copilot, |
| 102 | OpenAI Codex OAuth, and custom OpenAI-compatible endpoints. |
| 103 | |
| 104 | If setup fails or a provider is not ready, run: |
| 105 | |
| 106 | ```bash |
| 107 | raven doctor |
| 108 | ``` |
| 109 | |
| 110 | ### Upgrade an existing installation |
| 111 | |
| 112 | Check for the latest published stable release: |
| 113 | |
| 114 | raven upgrade --check |
| 115 | |
| 116 | Upgrade Raven without resetting configuration, sessions, or memory: |
| 117 | |
| 118 | raven upgrade |
| 119 | |
| 120 | Rav |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
