One Surface, All Agents: Raven generates DAGs and orchestrates multiple specialized agents for complex tasks.
Raven is The Harness of Harnesses—a self-evolving multi-agent orchestration ecosystem. As a Host Agent, it brings specialized agents together through one unified surface to delegate tasks, coordinate execution, and integrate results. Its long-term vision is to extend this orchestration across devices, environments, and domains.
Built on EverMind’s self-evolving harness engine and powered by EverOS, Raven preserves context across sessions and continuously improves agent harnesses and collaborative workflows.
Built-in Agents: Raven-Research, Raven-Code, Raven-Design, and Raven-Oncall support research, coding, visual design, and unattended workflow automation.
Raven is pre-alpha. Interfaces and configuration may change quickly.
Raven's Performance on the Multi-Agent Orchestration Benchmark
Raven's modular architecture is designed for harness self-evolution and subagent creation. Its four built-in agents deliver state-of-the-art (SOTA) performance in their respective domains, combining reusable harness components with domain-specific tools, skills, and agent loops. Raven can delegate a focused task to a single agent or orchestrate multiple agents within a shared workflow. The harness they share is refined by the Raven Evolver, a separate tool that consumes Raven as a library and evaluates candidate harness changes against benchmarks; it develops the agents rather than running inside them.
All four agents are built in and ready for orchestration out of the box.
Raven-Research enables autonomous deep research for complex questions, literature reviews, and technical analysis. It delivers clear, structured reports with traceable sources, helping users understand unfamiliar domains, compare alternatives, and make informed decisions.
Raven-Research's performance on the DeepResearch Mixed benchmark
Raven-Code enables agentic software development, turning requirements into working, tested code. It supports feature implementation, debugging, refactoring, data processing, and data analysis, helping users build new capabilities, resolve issues, and improve code quality while following their project's conventions.
Raven-Code's performance on coding benchmarks
Raven-Code tops on DataAgentBench for data analysis (2026-08-24 Live)
Raven-Design performs visual design, turning ideas and content into polished visual deliverables. It creates PowerPoint slide decks, brand assets, charts, diagrams, and web interfaces, refining layout, typography, and visual consistency to help users communicate clearly and bring their ideas to life.
Raven-Design tops on PresentBench for slide generation
Raven-Design's performance on visual design benchmarks
Raven-Oncall enables unattended workflow automation for experimentation, optimization, and continuous monitoring. It autonomously manages workflows from start to completion, sustaining progress over hours or overnight, delivering results, and involving users only when human judgment is needed.
Raven-Oncall vs. Claude Code on AI4AI (Nanochat 50M Pretraining) benchmark
Raven-Oncall vs. Claude Code on internal AI4S benchmark
Real runs, each captured from Raven's task graph. The graph shows the orchestration Raven chose for the task; below it is what the run produced.
|
Song-dynasty domestic aesthetics 
|
How ancient Greece was whitewashed 
|
|
How pop music is manufactured 
|
A century of abstract art 
|
Runs that end in something other than a deck.
|
Six orchestration frameworks, compared 
|
A parameter sweep, written, run and plotted 
|
Raven can connect to and orchestrate agents via ACP, CLI, or OpenAI-compatible APIs, with presets for 13 third-party agents to simplify setup, task delegation, and coordination across shared workflows.
Linux, macOS, or WSL2:
curl -fsSL https://raven.evermind.ai/install.sh | bashNative Windows PowerShell:
irm https://raven.evermind.ai/install.ps1 | iexWindows PowerShell 5.1 may reject the redirect. Use the direct installer URL instead:
irm https://raw.githubusercontent.com/EverMind-AI/Raven/refs/heads/main/install.ps1 | iexOr install from a source checkout, to develop against the code or to run what has not been released yet:
git clone https://github.com/EverMind-AI/Raven.git
cd Raven
./install.shRun as a file, install.sh installs that checkout in editable mode: raven and
its bundled plugins link back to your tree, and the TUI bundle and the served
page are built from it. A piped run installs the published wheel even from
inside a clone, so that a one-line install never picks up whatever a working
tree happens to contain. Set RAVEN_LOCAL_SRC=<dir> to force the editable
install through a pipe.
The agent products ship with raven itself: a wheel carries the agents/
product tree and copies it out to your raven home on first use, and a source
checkout reads the tree in place. Setup asks about each product and registers
the ones you take up, on the model it is tuned for or on this raven's LLM.
See agents/README.md.
Everything past the first run lives on the documentation site: self-hosting, Docker deployment, the WebUI, the command reference, the runtime architecture and the repository layout, in English and Chinese.
| System | What it adds |
|---|---|
| Agent Orchestration | Coordinates agents, manages task dependencies and parallel execution, and turns multi-step collaboration into reusable workflows. |
| Evolver | Drives harness self-evolution by diagnosing failures, testing candidate improvements, and retaining changes that outperform the baseline in reproducible evaluations. |
| EverOS Memory | Preserves user context, agent experience, and world knowledge across sessions, recalling relevant memories and reusable skills for future tasks. |
| SkillForge | Retrieves relevant skills from local libraries, EverOS memory, and SkillHub's catalog of 114,190 skills, giving agents specialized expertise on demand. |
| Proactivity | Combines event monitoring and scheduled execution to anticipate user needs, deliver timely reminders, and initiate follow-up work. |
Raven's WebUI brings conversations, multi-agent collaboration, and workspace management into your browser. Chat with agents, follow task progress, inspect files and outputs, and browse memory and skills in one place.
raven webThe command opens the WebUI in your browser and keeps Raven running in the background. Use raven web --stop to stop the background service.
Screenshot placeholder 1: Conversations and workspace.
Screenshot placeholder 2: Agent collaboration and task graph.
Screenshot placeholder 3: Memory and skill management.
EverMind connects memory research, production-ready products, and practical integrations into one open-source ecosystem.
| Products | |
|---|---|
| EverOS | A local-first, Markdown-native long-term memory runtime for agents and users. |
| Raven | A memory-first, self-improving agent harness with proactivity, context control, and skill evolution. |
| EverMe (CLI) | A CLI and agent plugin suite for cross-device, cross-agent personal memory. |
| Research & Evaluation | |
| SkillCorpus | Curated, retrieval-ready agent skill corpora with retrieval and evaluation tooling. |
| EverAlgo | Stateless extraction, ranking, parsing, and memory operators that power EverOS. |
| HyperMem | Hypergraph-based hierarchical memory for coarse-to-fine long-term conversation retrieval. |
| MSA | Memory Sparse Attention for scalable latent memory and 100M-token contexts. |
| EverMemBench | Evaluation of factual recall, applied reasoning, and personalized generalization in memory systems. |
| EvoAgentBench | Longitudinal evaluation of agent self-evolution, transfer efficiency, error avoidance, and skill use. |
| Integrations | |
| OpenClaw | OpenClaw plugin for automatic recall, capture, and session-memory lifecycle management. |
| Hermes Agent | Hermes plugin for persistent memory across Hermes sessions. |
| DeepSeek Harness | DSH plugin for memory-aware DeepSeek Harness agents. |
| Dify | Self-hosted and cloud tools for explicit memory search and storage in workflows and agents. |
Together, these projects form EverMind's research-to-runtime stack: methods and benchmarks become reusable memory infrastructure, products, and agent integrations.
Issues and pull requests are welcome. Start with the developer workflow, follow AGENTS.md for repository rules, and use GitHub Discussions for design conversations.