[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-openclaw-persistent-ai-assistant-chat-apps-en":3,"article-related-openclaw-persistent-ai-assistant-chat-apps-en":30,"series-ai-agent-db847758-5b48-41ca-9b1b-94de1aba5ac8":75},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":22,"views":26,"created_at":27,"published_at":28,"topic_cluster_id":29},"db847758-5b48-41ca-9b1b-94de1aba5ac8","openclaw-persistent-ai-assistant-chat-apps-en","OpenClaw turns chat apps into a persistent AI","\u003Cp data-speakable=\"summary\">\u003Ca href=\"\u002Ftag\u002Fopenclaw\">OpenClaw\u003C\u002Fa> is a persistent AI assistant built from messaging, memory, tools, and a custom system prompt.\u003C\u002Fp>\u003Cp>OpenClaw’s June 20, 2026 gist walks through how to build a personal assistant that lives inside Telegram, remembers past chats, and can act on your computer. The post frames the project as a step-by-step path from a bare-bones bot to a multi-channel \u003Ca href=\"\u002Ftag\u002Fagent\">agent\u003C\u002Fa> with shared memory and tool use.\u003C\u002Fp>\u003Ch2>What changed\u003C\u002Fh2>\u003Cp>The gist starts with a minimal Telegram bot that sends each user message to \u003Ca href=\"https:\u002F\u002Fwww.anthropic.com\u002F\" target=\"_blank\" rel=\"noopener\">Anthropic\u003C\u002Fa> and returns the reply. From there, it adds session storage in JSONL files so each user gets a durable transcript instead of a stateless chat.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782559965920-xpnc.png\" alt=\"OpenClaw turns chat apps into a persistent AI\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>That memory layer is paired with a markdown-based personality file, \u003Ccode>SOUL.md\u003C\u002Fcode>, which defines the agent’s name, tone, and boundaries. The post then adds structured tools so the model can run commands, read and write files, and search the web.\u003C\u002Fp>\u003Cul>\u003Cli>Telegram bot as the first interface\u003C\u002Fli>\u003Cli>JSONL session files for append-only memory\u003C\u002Fli>\u003Cli>\u003Ccode>SOUL.md\u003C\u002Fcode> for identity and behavior rules\u003C\u002Fli>\u003Cli>Tool calls for shell, file, and web actions\u003C\u002Fli>\u003C\u002Ful>\u003Cp>The architecture also points to a model loop: the assistant chooses a tool, the host app executes it, and the result goes back into the conversation. The gist says OpenClaw stores sessions under \u003Ccode>~\u002F.openclaw\u002Fagents\u002F...\u002Fsessions\u002F\u003C\u002Fcode> and loads the workspace prompt from \u003Ccode>~\u002F.openclaw\u002Fworkspace\u002FSOUL.md\u003C\u002Fcode>.\u003C\u002Fp>\u003Ch2>Why it matters\u003C\u002Fh2>\u003Cp>For developers, the value is not the bot code itself but the pattern: persistent memory, explicit identity, and tool execution are enough to move an \u003Ca href=\"\u002Ftag\u002Fllm\">LLM\u003C\u002Fa> from chat toy to usable assistant. The post makes that stack concrete with code, file paths, and a loop you can copy into your own app.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782559965075-u4aa.png\" alt=\"OpenClaw turns chat apps into a persistent AI\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>For the market, it signals where personal AI is heading: not one more web tab, but an agent that can live across WhatsApp, Telegram, Slack, and local machines while keeping one identity. That matters for anyone building assistants that need context across days, not just prompts across minutes.\u003C\u002Fp>\u003Cp>The sharp question is whether users want one assistant with long-lived memory across every channel, or several smaller agents with narrower jobs and less risk.\u003C\u002Fp>","OpenClaw’s gist shows how a Telegram-first bot grows into a persistent assistant with memory, tools, and a custom identity.","gist.github.com","https:\u002F\u002Fgist.github.com\u002Fdabit3\u002Fbc60d3bea0b02927995cd9bf53c3db32",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782559965920-xpnc.png","ai-agent","en","d0a20a18-1c6f-40ad-b438-e10b5c48ed2e",[17,18,19,20,21],"OpenClaw","persistent AI","Telegram bot","LLM tools","session memory",[23,24,25],"OpenClaw is presented as a persistent assistant, not a standard chatbot.","The gist builds memory with JSONL transcripts and a SOUL.md prompt file.","Tool use extends the bot from replies to actions on files, commands, and web search.",0,"2026-06-27T11:32:22.022011+00:00","2026-06-27T11:32:22.014+00:00","d2a03b30-1026-48d0-89e1-c63c92c5e386",{"tags":31,"relatedLang":34,"relatedPosts":38},[32],{"name":17,"slug":33},"openclaw",{"id":15,"slug":35,"title":36,"language":37},"openclaw-persistent-ai-assistant-chat-apps-zh","OpenClaw 把聊天 App 變成持久 AI","zh",[39,45,51,57,63,69],{"id":40,"slug":41,"title":42,"cover_image":43,"image_url":43,"created_at":44,"category":13},"c6bb2883-2975-4050-bc36-316a5d941ab7","openclaw-agent-control-layer-matters-en","OpenClaw shows the agent control layer matters more than the model","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782561763577-p0xp.png","2026-06-27T12:02:20.58809+00:00",{"id":46,"slug":47,"title":48,"cover_image":49,"image_url":49,"created_at":50,"category":13},"2c7cd1c3-a757-4c0b-a0a5-12a894d479e0","extracted-prompts-turn-model-behavior-into-a-map-en","Extracted prompts turn model behavior into a map","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782529389258-una3.png","2026-06-27T03:02:47.607032+00:00",{"id":52,"slug":53,"title":54,"cover_image":55,"image_url":55,"created_at":56,"category":13},"b4fd1081-03b2-4a5a-a164-63abf5aae4a7","hippo-deploys-devin-insurance-engineering-en","Hippo rolls out Devin across insurance engineering","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782482571866-ikl0.png","2026-06-26T14:02:25.423732+00:00",{"id":58,"slug":59,"title":60,"cover_image":61,"image_url":61,"created_at":62,"category":13},"c4d10424-4e13-4b5c-98f0-8a0a5e75ce72","doubao-pro-turns-agent-into-office-tool-en","豆包专业版把办公Agent做成了日常工具","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782479013354-okfy.png","2026-06-26T13:03:05.457828+00:00",{"id":64,"slug":65,"title":66,"cover_image":67,"image_url":67,"created_at":68,"category":13},"42a4132d-fedc-4592-8831-b14e85168947","valkey-bots-backporting-pipeline-en","Valkey’s bots turn backporting into a pipeline","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782457402483-yzo4.png","2026-06-26T07:02:55.253806+00:00",{"id":70,"slug":71,"title":72,"cover_image":73,"image_url":73,"created_at":74,"category":13},"7d80deb7-681b-4ebd-aa99-1ae041890f2b","loop-engineering-ru-men-gou-jian-ke-chi-xu-die-dai-de-zhi-ne-en","Loop Engineering 入门：构建可持续迭代的智能体","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782443868495-4h1i.png","2026-06-26T03:17:20.204174+00:00",[76,81,86,91,96,101,106,111,116,121],{"id":77,"slug":78,"title":79,"created_at":80},"03db8de8-8dc2-4ac1-9cf7-898782efbb1f","anthropic-claude-ai-agent-task-automation-en","Anthropic's Claude AI Agent: A New Era of Task Automation","2026-03-25T16:25:06.513026+00:00",{"id":82,"slug":83,"title":84,"created_at":85},"045d1abc-190d-4594-8c95-91e2a26f0c5a","googles-2026-ai-agent-report-decoded-en","Google’s 2026 AI Agent Report, Decoded","2026-03-26T11:15:23.046616+00:00",{"id":87,"slug":88,"title":89,"created_at":90},"e64aba21-254b-4f93-aa21-837484bb52ec","kimi-k25-review-stronger-still-not-legend-en","Kimi K2.5 review: stronger, still not a legend","2026-03-27T07:15:55.385951+00:00",{"id":92,"slug":93,"title":94,"created_at":95},"30dfb781-a1b2-4add-aebe-b3df40247c37","claude-code-controls-mac-desktop-en","Claude Code now controls your Mac desktop","2026-03-28T03:01:59.384091+00:00",{"id":97,"slug":98,"title":99,"created_at":100},"254405b6-7833-4800-8e13-f5196deefbe6","cloudflare-100x-faster-ai-agent-sandbox-en","Cloudflare’s 100x Faster AI Agent Sandbox","2026-03-28T03:09:44.356437+00:00",{"id":102,"slug":103,"title":104,"created_at":105},"04f29b7f-9b91-4306-89a7-97d725e6e1ba","openai-backs-isara-agent-swarm-bet-en","OpenAI backs Isara’s agent-swarm bet","2026-03-28T03:15:27.849766+00:00",{"id":107,"slug":108,"title":109,"created_at":110},"3b0bf479-e4ae-4703-9666-721a7e0cdb91","openai-plan-automated-ai-researcher-en","OpenAI’s plan for an automated AI researcher","2026-03-28T03:17:42.312819+00:00",{"id":112,"slug":113,"title":114,"created_at":115},"fe91bce0-b85d-4efa-a207-24ae9939c29f","harness-engineering-ai-agent-reliability-2026","Harness Engineering: From Bridle to Operating System, The Missing Link in AI Agent Reliability","2026-03-31T06:36:55.648751+00:00",{"id":117,"slug":118,"title":119,"created_at":120},"7a09007d-820f-43b3-8607-8ad1bfcb94c8","mcp-explained-from-prompts-to-production-en","MCP Explained: From Prompts to Production","2026-04-01T09:24:40.089177+00:00",{"id":122,"slug":123,"title":124,"created_at":125},"116d5ee9-a4f1-4b5a-aac5-5d035dd22bbe","amazon-bedrock-agents-multi-agent-workflows-en","Amazon Bedrock Agents Gets Multi-Agent Workflows","2026-04-01T09:30:30.197685+00:00"]