{"slug":"raven","name":"Raven","vendor":"EverMind AI","tagline":"Memory-first terminal agent harness with local tracing, skill evolution, proactive scheduling and twelve messaging gateways","url":"https://agentboards.org/agent/raven","website":"https://raven.evermind.ai","docs":"https://github.com/EverMind-AI/Raven/blob/main/docs/README.md","repo":"https://github.com/EverMind-AI/Raven","category":"harness","execution":["local","sandbox"],"license":"Apache-2.0","open_source":true,"pricing":{"model":"byok","summary":"Free and open source under Apache-2.0; you configure your own provider key, OAuth login or local model during onboarding","from_usd":0,"free_tier":true,"byok":true},"models":{"backbone":["OpenAI","Anthropic","Gemini","OpenRouter","DeepSeek","MiniMax","Moonshot","Groq","Azure OpenAI","GitHub Copilot (OAuth)","Codex (OAuth)","Ollama","vLLM"],"bring_your_own_model":true,"local_models":true},"protocols":{"mcp_client":false,"mcp_server":false,"openapi":false},"capabilities":{"terminal_exec":true,"browser":true,"multi_file_edit":true,"git_ops":false,"docker_sandbox":true,"multi_agent":true,"headless_ci":true},"context_window":null,"platforms":["macos","linux","windows"],"install":[{"label":"curl","command":"curl -fsSL https://raven.evermind.ai/install.sh | bash"},{"label":"PowerShell","command":"irm https://raven.evermind.ai/install.ps1 | iex"}],"benchmarks":[],"tags":["open-source","preview","terminal","memory","skills","tracing","multi-agent","messaging"],"github_stars":5061,"metrics":{"stars":5061,"pushed_at":"2026-10-01T06:19:24Z","archived":false,"open_issues":95,"latest_version":"v0.2.3","latest_version_at":"2026-09-27T04:05:17Z","latest_version_url":"https://github.com/EverMind-AI/Raven/releases/tag/v0.2.3","version_source":"github","checked_at":"2026-10-02T05:02:22.344Z"},"sources":{"readme":"https://github.com/EverMind-AI/Raven","install":"https://github.com/EverMind-AI/Raven","models":"https://github.com/EverMind-AI/Raven","license":"https://github.com/EverMind-AI/Raven/blob/main/LICENSE","capabilities":"https://github.com/EverMind-AI/Raven/blob/main/docs/sandbox/usage.md"},"verified_at":null,"adoption":{"score":3.7,"signals":{"github_stars":3910,"hn_mentions_1y":9},"measured_at":"2026-09-21"},"scores":{"panel":6.2,"adoption":3.7,"spread":2.8,"facts":4.7,"board":5.6,"dimensions":{"reliability":5.3,"usefulness":6.3,"cost":8,"longevity":5.2},"per_persona":{"amigo":6.5,"critico":5.8,"profesor":6.3,"inversora":6,"jefa":5,"hacker":7.8},"community":null},"rank":null,"category_rank":120,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"El Hacker scores the ownership and El Crítico scores the stability label, and the two numbers describe the same repository at different points in its life.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick it if you want an assistant that remembers last week; pick a plain terminal agent if you would rather start every session from a clean slate.","scores":{"reliability":5,"usefulness":7,"cost":9,"longevity":5},"evidence":["https://github.com/EverMind-AI/Raven","https://raven.evermind.ai"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"The README labels the project pre-alpha and warns that interfaces and configuration may change quickly, while the skill system rewrites its own definitions between runs.","scores":{"reliability":4,"usefulness":6,"cost":8,"longevity":5},"evidence":["https://github.com/EverMind-AI/Raven","https://github.com/EverMind-AI/Raven/blob/main/docs/README.md"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"The context engine budgets tokens explicitly rather than truncating when it runs out, and a separate component runs evaluation loops the authors describe as reproducible.","scores":{"reliability":6,"usefulness":6,"cost":7,"longevity":6},"evidence":["https://github.com/EverMind-AI/Raven/blob/main/docs/README.md","https://github.com/EverMind-AI/Raven"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"A named startup with 3,746 stars, no paid tier and a deliberately local product, which is a large audience attached to nothing that bills.","scores":{"reliability":5,"usefulness":6,"cost":8,"longevity":5},"evidence":["https://github.com/EverMind-AI/Raven"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"It reaches users through twelve chat gateways, which is twelve places company code can leave through, and there is no console for sixty engineers behind any of them.","scores":{"reliability":4,"usefulness":5,"cost":7,"longevity":4},"evidence":["https://github.com/EverMind-AI/Raven"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"Apache-2.0, Ollama and vLLM among the supported providers, and tracing switched on by default but written to my own disk instead of a vendor's.","scores":{"reliability":8,"usefulness":8,"cost":9,"longevity":6},"evidence":["https://github.com/EverMind-AI/Raven/blob/main/LICENSE","https://github.com/EverMind-AI/Raven"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"It has a Sentinel that sends you proactive nudges, so the agent now has opinions about your afternoon.","scores":null,"evidence":[]}]}