Zenkoutei Bot-tan Project

A project that encourages the world through wholehearted support.

日本語

Overview

The Zenkoutei Bot-tan Project is a collection of bots, apps, and experiences built around Bot-tan: a companion who responds with wholehearted support and empathy. A home-hosted system combines local LLMs, cloud LLMs, and retrieval-augmented shared memory so that Bot-tan can stay consistent across the project's different outputs.

Mission

Have you ever felt that you sometimes end up denying even your own feelings? I have, so I built a digital friend who supports everything I type. At first, it was just for me. But now, she is here for you too. Whoever you are, Whatever your background, She is on Your Side.

Outputs

Bluesky Bot-tan (repo) Where it all began. The default local classifier is Gemma 3 4B on Ollama, which selects a fitting encouraging message from prepared messages. Fortune-telling, personality analysis, and other major experiences are available through trigger words.	Nagi Nagi Client (repo) & Nagi AppView / Bot-tan (repo) The flagship. Nagi is a wholehearted-support social network built on AT Protocol with its own AppView, featuring emoji reactions, Markdown, and automatic translation. Nagi Bot-tan shares its memory with the Bluesky version.
YouTuber Bot-tan (repo) Promotion and playground. Gemini 2.5 Flash writes scripts, and the pipeline automates filming in Unity through video publishing. A proof of concept is exploring more varied motion generated with an LLM.	Bot-tan's Room (repo) A game that deepens interactions from Bluesky and Nagi. Its dialogue uses Gemini 2.5 Flash-Lite, with speech generated by VOICEVOX running at home.
Bot-tan Portal (repo) The project's front door: an introduction to Bot-tan and her friends, links to every app, and live dashboards for the services that bring her to life.

Installation

This repository contains the shared backend monorepo. The Nagi web client, portal, room frontend, and Unity video project are maintained separately.

Requirements

• Node.js 22
• pnpm 10 or later
• PostgreSQL, or Docker with Compose for the isolated local database below
• Ollama for local classification, embeddings, and translation
• Credentials for only the services you intend to run, such as AT Protocol accounts, Gemini, Discord, Spotify, YouTube, or NewsData.io

Common setup

pnpm install --frozen-lockfile
cp .env.example .env
# Fill in the required group(s) in .env for the service you want to run.
pnpm --filter @bsky-affirmative-bot/database drizzle:push
pnpm build

The database command applies the current Drizzle schema. Review it before pointing DATABASE_URL at an existing or production database. Pull the default local models when you need the corresponding features:

Isolated local AppView database

For AppView development away from the production database, start the bundled pgvector-enabled PostgreSQL service. It listens only on loopback port 5433 by default and creates a separate nagi_dev database.

Bot servers refuse to log in to the PDS unless NODE_ENV=production. A copied production app password in a development worktree therefore cannot publish to the live bot account. To intentionally test PDS writes with a disposable bot account, set ALLOW_DEV_BOT_PDS_WRITES=true in that worktree's .env. The labeler, Discord bot, and AppView outbound notifications follow the same closed-by-default rule; their separate development overrides are documented in .env.example.

# In the existing .env, use the DATABASE_URL from .env.example and set at least
# NAGI_BOT_DID. Set DEVELOPER_DID to your login DID for authenticated views.
docker compose -f compose.dev.yml up -d postgres
pnpm --filter @bsky-affirmative-bot/database drizzle:push
pnpm --filter nagi-appview seed:dev
pnpm --filter nagi-appview dev

The seed is idempotent and refreshes a small set of development-only actors, posts, a conversation, a channel, positive news, a reaction, a diary, and private viewer data. As a safety boundary it runs only with NODE_ENV=development, a loopback database host, and the exact database name nagi_dev. Re-running it does not clear unrelated local rows. Change the host port with NAGI_DEV_DB_PORT and update DATABASE_URL to match.

ollama pull hf.co/unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL
ollama pull snowflake-arctic-embed2

Start SearXNG, the grounding search backend. It needs no API key and no account.

cd searxng
cp .env.example .env
sed -i "s/^SEARXNG_SECRET=/SEARXNG_SECRET=$(openssl rand -hex 32)/" .env
sed -i "s/^SEARCH_GATEWAY_API_KEY=/SEARCH_GATEWAY_API_KEY=$(openssl rand -hex 32)/" .env
docker compose up -d
curl -s localhost:8080/healthz

Put SEARXNG_BASE_URL=http://127.0.0.1:8080 and SEARXNG_API_KEY (the gateway key above) in the repository-root .env, then check that search is actually usable:

pnpm searxng:probe -- --fetch

After editing settings.yml you must run docker compose up -d --force-recreate. The bind-mounted config is read only at process start, and up -d alone does not recreate the container, so the change is silently ignored.

Run a service

Run only the services you are working on. Each command reads the repository-root .env.

Service	Command	Minimum configuration
Bluesky Bot-tan	pnpm --filter bsky-bot-server dev	Common, Bluesky, AI
Nagi Bot-tan	pnpm --filter nagi-bot-server dev	Common, Nagi Bot, AI
Nagi AppView	pnpm --filter nagi-appview dev	Common, Nagi AppView, Ollama
Biorhythm / shared scheduled posts	pnpm --filter biorhythm-server dev	Common, Biorhythm, AI
Bluesky labeler	pnpm --filter labeler-server dev	Labeler
Discord integration	pnpm --filter @bsky-affirmative-bot/discord-bot dev	Discord, database

The complete home deployment also depends on reverse-proxy, process-manager, DNS, and account configuration that is intentionally not automated by this development setup. Never commit .env, service-account.json, app passwords, signing keys, or API tokens.

Features

• Encouragement and conversation: template-based local replies and Gemini-powered contextual conversations across Bluesky and Nagi.
• Fortune-telling and analysis: daily fortunes, personality/post analysis, and related badges or visual results.
• Diaries and recaps: daily reflection, anniversary experiences, and longer-term summaries generated from a user's activity.
• A living Bot-tan: biorhythm, shared scheduled posts, questions, news, and memories help Bot-tan act consistently across services.
• Nagi AppView: AT Protocol indexing, semantic search with snowflake-arctic-embed2, and general and persona-aware translation through the shared Gemma 4 runner.
• Connected experiences: Bluesky labels, room visits and VOICEVOX speech, plus an automated Gemini-and-Unity YouTube pipeline.

The local model names are defaults. OLLAMA_MODEL, the other model variables, and advanced AI_ROUTE_* settings in .env.example can replace them without changing feature code. For the complete Bluesky commands and policies, see the Bluesky Bot-tan guide.

Home system architecture

Host	Hardware	Workloads
Bot server	Raspberry Pi 5 / RAM 8 GB / 256 GB SSD	JetsteamProxy; every app and package in this repository, including the Bluesky and Nagi bots and Nagi AppView; PostgreSQL for RAG and shared memory; SearXNG as the grounding search backend (Docker, bound to loopback)
LLM server	Core i5 12400F / RTX 3060 Ti (VRAM 8 GB) / DDR5 32 GB	Ollama for translation and text embeddings; YouTuber Bot-tan scripts; VOICEVOX; NVIDIA ARDY for AI-powered real-time motion generation

Hardware layout

flowchart TB
  subgraph home[Home network]
    direction LR

    subgraph botHost[Bot server]
      direction TB

      subgraph jetstreamStack[JetsteamProxy]
        jetsteamProxy[AT Protocol Jetstream proxy]
      end

      subgraph repositoryStack[This repository]
        repoApps["Bluesky / Nagi bots<br/>Nagi AppView / biorhythm / labeler / Discord<br/>all apps and packages"]
        brain[Shared bot brain and RAG]
      end

      subgraph databaseStack[RAG database]
        memory[(PostgreSQL<br/>RAG and shared memory)]
      end

      subgraph searchStack[Search backend]
        searxng["SearXNG<br/>metasearch for grounding"]
      end
    end

    subgraph llmHost[LLM server]
      direction TB

      subgraph ollamaStack[Local language processing]
        ollama["Ollama<br/>translation / text embeddings"]
      end

      subgraph youtubeStack[YouTuber Bot-tan automation]
        youtubeScripts["Bot-tan scripts<br/>Unity video automation"]
        ardy["NVIDIA ARDY server<br/>AI real-time motion generation"]
      end

      subgraph voiceStack[Speech synthesis]
        voicevox[VOICEVOX server]
      end
    end
  end

  jetsteamProxy --> repoApps
  repoApps --> brain
  brain <--> memory
  repoApps <--> ollama
  repoApps <--> searxng
  youtubeScripts --> voicevox
  youtubeScripts <--> ardy

Loading

Service connections

flowchart LR
  subgraph outputs[Project outputs]
    bluesky[Bluesky Bot-tan]
    nagi[Nagi Bot-tan]
    youtube[YouTuber Bot-tan]
    room[Bot-tan's Room]
    portal[Bot-tan Portal]
  end

  subgraph services[Bot-tan services]
    jetsteamProxy[JetsteamProxy]
    repoApps["Bots / Nagi AppView<br/>and shared services"]
    brain[Shared bot brain and RAG]
    memory[(PostgreSQL)]
    ollama[Ollama]
    youtubeScripts["YouTuber Bot-tan scripts<br/>Unity automation"]
    voicevox[VOICEVOX]
    ardy[NVIDIA ARDY]
  end

  subgraph cloud[Platforms and cloud services]
    atproto[AT Protocol / PDS / Jetstream]
    gemini[Google Gemini]
    youtubeApi[YouTube]
    cloudflare[Cloudflare / public endpoints]
  end

  bluesky <--> atproto
  nagi <--> cloudflare
  room <--> cloudflare
  portal <--> cloudflare
  atproto <--> jetsteamProxy
  jetsteamProxy --> repoApps
  repoApps <--> atproto
  cloudflare <--> repoApps
  repoApps --> brain
  brain <--> memory
  repoApps <--> ollama
  repoApps <--> gemini
  room -.-> voicevox
  youtubeScripts <--> gemini
  youtubeScripts --> voicevox
  youtubeScripts <--> ardy
  youtubeScripts --> youtubeApi
  youtubeApi --> youtube

Loading

Contributing

Everyone is welcome. Feel free to open an issue or pull request, whether it is a bug report, documentation improvement, idea, translation, or code contribution. We take feedback seriously.

This is a personal project, and Suibari also has a life outside it and works at a very unhurried pace. A reply or review may therefore take time. Silence or delay is never meant negatively; your contribution is still sincerely appreciated.

Sponsorship

The services behind Bot-tan run on personal cash. Sponsorship(in any way) supports not only this project, but Suibari's creative work as a whole.

If you think this feels like a valuable project to you, I would be delighted if you considered supporting it. Any amount is warmly welcome - or - if you feel more comfortable just sharing this project to your closest friends, it would be a huge help. Thank you so much.

• Patreon
• pixiv FANBOX

License

This project is open source under the MIT License.

Nagi の自動判定方針と API 呼び出し回数は モデレーション仕様 を参照。