Show HN: Kern Agent – See inside your agent's brain Developer Oguz Bilgic released Kern Agent, an open-source autonomous agent framework that runs on a user's own machine and pairs with the agent-kernel project to manage memory, tools, and multi-channel sessions. Kern Agent unifies terminal, browser, Telegram, Slack, Matrix, and Nostr into a single session, segments and summarizes conversations into an L0-to-L2 hierarchy for semantic recall, and lets agents generate their own HTML dashboards served from the agent. The software ships as a Docker image (ghcr.io/oguzbilgic/kern-ai) and an npm package (kern-ai), supports OpenRouter or fully local Ollama inference, and stores all data in a git-tracked agent folder so users pay only for API tokens. Agents that do the work and show it. Agents that run on your machine, use real tools, remember everything, and publish their own dashboards. Not chatbots — autonomous workers with one brain across every channel. - One brain, every channel — terminal, browser, Telegram, Slack, Matrix, Nostr feed into one session. The agent knows who's talking, what channel it's in, and what happened 10,000 messages ago. - Memory that compounds — conversations segmented by topic, summarized into a hierarchy, compressed into context. Semantic recall over everything. The agent gets better the longer it runs. - Agents build their own UI — dashboards with live data, served from the agent, displayed in a side panel. Not chat — real interfaces that update themselves. - Your infra, your data — runs on your laptop, server, or homelab. The whole agent is a git-tracked folder. Pay only for API tokens — or use Ollama for fully local, zero-cost inference. kern pairs with agent-kernel https://github.com/oguzbilgic/agent-kernel — the kernel defines how an agent remembers, kern runs it. Run an agent docker run -d --restart=unless-stopped \ -p 4100:4100 \ -v my-agent:/home/kern/agent \ -e OPENROUTER API KEY=sk-or-... \ -e KERN AUTH TOKEN=my-secret-token \ ghcr.io/oguzbilgic/kern-ai Run the web UI docker run -d -p 8080:8080 ghcr.io/oguzbilgic/kern-ai kern web run Open http://localhost:8080 , click Add agent , enter http://localhost:4100 and your token. That's it. Or skip the web UI and talk to your agent on Telegram: docker run -d --restart=unless-stopped \ -v my-agent:/home/kern/agent \ -e OPENROUTER API KEY=sk-or-... \ -e TELEGRAM BOT TOKEN=123456:ABC-... \ ghcr.io/oguzbilgic/kern-ai No ports, no web UI — just message your bot. First message auto-pairs you as operator. Agent data lives in the my-agent volume — sessions, memory, dashboards persist across restarts. Mount -v my-agent:/home/kern instead to persist the entire home directory installed packages, SSH keys, etc . Configure with env vars: KERN NAME , KERN MODEL , KERN PORT . See configuration docs /oguzbilgic/kern-ai/blob/master/docs/config.md for other providers and options. npm install -g kern-ai kern init my-agent kern tui The init wizard scaffolds your agent, asks for a provider and API key, then starts it. kern tui opens an interactive chat. kern web start serves the web UI. For automation: kern init my-agent --api-key sk-or-... no prompts, defaults to openrouter + opus 4.6 . For Ollama: kern init my-agent --provider ollama --api-key http://localhost:11434 --model gemma4:31b . Agents create and maintain their own dashboards — HTML pages with live data, served from the agent and displayed in the web UI side panel. Not chat transcripts. Real interfaces that update themselves. dashboards/homelab/ index.html visualization data.json structured data injected as window. KERN DATA The agent writes data.json , creates the HTML, then calls render { dashboard: "homelab" } to display it. Dashboards appear in the sidebar and can be switched from the panel header. Dashboards docs /oguzbilgic/kern-ai/blob/master/docs/dashboards.md · Blog: Why every agent needs a dashboard https://kern-ai.com/blog/agent-dashboards Conversations are automatically segmented by topic, summarized, and rolled up into a hierarchy L0 → L1 → L2 . When old messages are trimmed from context, compressed summaries take their place — the agent sees its full history at decreasing resolution. Semantic recall searches everything. The web UI includes a Memory overlay with five tabs for inspecting sessions, segments, notes, recall, and the full context pipeline with token breakdowns. Memory docs /oguzbilgic/kern-ai/blob/master/docs/memory.md · Blog: Lossless context management https://kern-ai.com/blog/lossless-context-management · Blog: See inside your agent's brain https://kern-ai.com/blog/memory-ui Terminal ─────┐ Web UI ───────┤ Telegram ─────┤── one session Slack ────────┤ Matrix ───────┤ Nostr ────────┘ Every interface feeds into the same session. Message from Telegram, pick up in the terminal, continue in the browser. Each message carries metadata — who said it, which channel, when — so the agent connects context across all of them without losing track. The agent reads and writes its own memory files through tools — takes notes, updates knowledge, commits to git. The next time you talk to it, from any interface, it picks up exactly where it left off. Blog: Why your agent needs one session https://kern-ai.com/blog/why-your-agent-needs-one-session kern init