[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:claraverse":3},"\u003Cdiv align=\"center\">\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fclaraverse-space\u002Fclaraverse\u002FHEAD\u002Fdocs\u002Fimages\u002Fimage-banner.png\" alt=\"ClaraVerse - Your Private AI Workspace\" width=\"800\" \u002F>\u003Ch3>\u003Cstrong>Your Private AI Workspace\u003C\u002Fstrong>\u003C\u002Fh3>\n\u003Cp>\u003Cem>Built by the community, for the community. Private AI that respects your freedom.\u003C\u002Fem>\u003C\u002Fp>\n\u003Cp>\u003C\u002Fp>\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fclaraverse-space\u002Fclaraverse\u002Fblob\u002FHEAD\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-AGPL--3.0-blue.svg\" alt=\"License\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fclaraverse-space\u002FClaraVerse\u002Fstargazers\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fclaraverse-space\u002FClaraVerse?style=social\" alt=\"GitHub Stars\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fhub.docker.com\u002Fr\u002Fclaraverseoss\u002Fclaraverse\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fdocker\u002Fpulls\u002Fclaraverseoss\u002Fclaraverse?color=blue\" alt=\"Docker Pulls\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fdiscord.com\u002Finvite\u002Fj633fsrAne\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20Us-7289da?logo=discord&logoColor=white\" alt=\"Discord\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fclaraverse.space\" rel=\"nofollow ugc noopener\">Website\u003C\u002Fa> · \u003Ca href=\"#documentation\" rel=\"nofollow ugc noopener\">Documentation\u003C\u002Fa> · \u003Ca href=\"#quick-start\" rel=\"nofollow ugc noopener\">Quick Start\u003C\u002Fa> · \u003Ca href=\"#claraverse-vs-open-webui\" rel=\"nofollow ugc noopener\">vs Open WebUI\u003C\u002Fa> · \u003Ca href=\"#community\" rel=\"nofollow ugc noopener\">Community\u003C\u002Fa> · \u003Ca href=\"#contributing\" rel=\"nofollow ugc noopener\">Contributing\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>\u003C\u002Fp>\n\u003C\u002Fdiv>\u003Ch2>What is ClaraVerse?\u003C\u002Fh2>\n\u003Cp>ClaraVerse is a private AI workspace built around three things most AI chat UIs treat as an afterthought: agents that work as an actual team, memory that behaves like a real memory system instead of a flat list of notes, and a license that does not start charging you once people notice your project.\u003C\u002Fp>\n\u003Cp>Chat, Crew (multi-agent teams with human review), a visual workflow builder, and Telegram integration all live in one app, on your own infrastructure. Use OpenAI, Claude, Gemini, or local models like Ollama and llama.cpp. Chats are stored locally on your device by default, with optional encrypted sync if you want them on more than one machine.\u003C\u002Fp>\n\u003Cp>If you have \u003Cstrong>Ollama\u003C\u002Fstrong> or \u003Cstrong>LM Studio\u003C\u002Fstrong> running on your machine, ClaraVerse detects them automatically and imports all your models. Zero configuration.\u003C\u002Fp>\n\u003Chr \u002F>\n\u003Ch2>Quick Start\u003C\u002Fh2>\n\u003Ch3>One-line install (Linux \u002F macOS)\u003C\u002Fh3>\n\u003Cpre>\u003Ccode class=\"language-bash\">curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fclaraverse-space\u002FClaraVerse\u002Fmain\u002Fcli\u002Finstall.sh | bash && claraverse init\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch3>Docker Compose\u003C\u002Fh3>\n\u003Cpre>\u003Ccode class=\"language-bash\">git clone https:\u002F\u002Fgithub.com\u002Fclaraverse-space\u002FClaraVerse.git\ncd ClaraVerse\ndocker compose -f docker-compose.production.yml up -d\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Open \u003Cstrong>\u003Ca href=\"http:\u002F\u002Flocalhost:3000\" rel=\"nofollow ugc noopener\">http:\u002F\u002Flocalhost:3000\u003C\u002Fa>\u003C\u002Fstrong>, register your account (first user becomes admin), and start chatting.\u003C\u002Fp>\n\u003Cblockquote>\n\u003Cp>\u003Cstrong>Have Ollama running?\u003C\u002Fstrong> ClaraVerse auto-detects it and imports all your models. No setup needed.\nMake sure Ollama is listening on \u003Ccode>0.0.0.0\u003C\u002Fcode> (set \u003Ccode>OLLAMA_HOST=0.0.0.0\u003C\u002Fcode> in your Ollama config).\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Ch3>Want it in your terminal too?\u003C\u002Fh3>\n\u003Cpre>\u003Ccode class=\"language-bash\">claraverse agent install   # builds Clara Agent, puts `claracli` on your PATH\nclaracli                   # then run \u002Flogin claraverse to connect it\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>See \u003Ca href=\"#clara-agent-the-same-assistant-in-your-terminal\" rel=\"nofollow ugc noopener\">Clara Agent\u003C\u002Fa> below.\u003C\u002Fp>\n\u003Cdetails>\n\u003Csummary>\u003Cb>Docker run (single command)\u003C\u002Fb>\u003C\u002Fsummary>\u003Cpre>\u003Ccode class=\"language-bash\">docker run -d \\\n  --name claraverse \\\n  -p 3000:3000 \\\n  -v claraverse-data:\u002Fapp\u002Fdata \\\n  -v claraverse-uploads:\u002Fapp\u002Fuploads \\\n  --add-host=host.docker.internal:host-gateway \\\n  ghcr.io\u002Fclaraverse-space\u002Fclaraverse:latest\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>This runs ClaraVerse with a single container. For the full stack with MySQL, MongoDB, Redis, SearXNG, \u003Cstrong>Qdrant and the embeddings sidecar (required for Knowledge bases \u002F RAG)\u003C\u002Fstrong>, use the Docker Compose setup above. Single-container mode boots fine, but the Knowledge tab and \u003Ccode>search_knowledge\u003C\u002Fcode> tool need the sidecars and will surface \"embeddings service unreachable\" without them.\u003C\u002Fp>\n\u003C\u002Fdetails>\u003Cdetails>\n\u003Csummary>\u003Cb>Advanced configuration\u003C\u002Fb>\u003C\u002Fsummary>\u003Ch3>Prerequisites\u003C\u002Fh3>\n\u003Cul>\n\u003Cli>Docker & Docker Compose v2+\u003C\u002Fli>\n\u003Cli>4 GB RAM minimum (8 GB recommended)\u003C\u002Fli>\n\u003Cli>Ollama, LM Studio, or any OpenAI-compatible API\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch3>Environment variables\u003C\u002Fh3>\n\u003Cp>Override defaults by creating a \u003Ccode>.env\u003C\u002Fcode> file next to \u003Ccode>docker-compose.production.yml\u003C\u002Fcode>:\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-bash\"># Port (default 3000)\nCLARAVERSE_PORT=8080\n\n# Point to a custom Ollama or LM Studio URL\nOLLAMA_BASE_URL=http:\u002F\u002Fhost.docker.internal:11434\nLMSTUDIO_BASE_URL=http:\u002F\u002Fhost.docker.internal:1234\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch3>Local AI auto-detection\u003C\u002Fh3>\n\u003Cp>ClaraVerse automatically discovers lo\u003C\u002Fp>\n\u003C\u002Fdetails>",1786232074683]