# moeru-ai/airi

> Self-hosted AI companion (waifu/VTuber) with realtime voice chat, Live2D/VRM avatar and the ability to play Minecraft and Factorio; runs in browser, on macOS and Windows.

- Magnitude: 4.5 out of 10 — Breakout
- Stars: 49,673 total · +98 stars today, ≈ 176 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2024-12-01 · Last push: 2026-09-28
- GitHub: https://github.com/moeru-ai/airi · Homepage: https://airi.moeru.ai/docs/ · Page: https://gitnova.dev/en/r/moeru-ai/airi

## Useful for

- Run your own AI VTuber companion locally for voice chat
- Connect the avatar to a Discord voice channel for co-op games
- Build a custom digital character with a Live2D/VRM model and your own LLM

## Why it’s here

- 98 stars so far today, about 176 expected by the end of the day. The usual pace is 39 per day, so that's 4.6× as much.
- Over the last two days the pace is 5.5× that of the previous week and a half.
- The spike has held for 2 days in a row — not a one-off blip.
- GitHub Trending TypeScript today: #5, +216 stars.
- About 33 forks a day — people are taking the code.
- Recent forks include notable developers: @moepoi (671 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 4,943
- Issues and pull requests: 2,566
- Watchers: 200
- Average over the last week: 68 per day
- Usual pace: 39 per day
- Stars in the last hour (measured): 10
- Latest release: v0.12.0-beta.5 (2026-08-29)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-08-30 … 2026-09-28: 46, 59, 48, 29, 42, 32, 31, 58, 42, 50, 61, 36, 24, 31, 37, 34, 31, 41, 35, 31, 22, 30, 31, 30, 23, 30, 29, 34, 158, 98

## Spotted in now

- GitHub Trending TypeScript today: #5, +216 stars

## More in this category

1. **vectorize-io/hindsight** — 9.2 · Breakout · AI agents · Python · +1,234 stars today, ≈ 2,786 by evening
   Hindsight is a long-term memory system for AI agents that stores facts and observations rather than just conversation history, reporting state-of-the-art results on the LongMemEval benchmark. It runs as a server (Docker, pip, Helm) or…
   Full card: https://gitnova.dev/en/r/vectorize-io/hindsight.md
2. **paperclipai/paperclip** — 8.9 · Breakout · AI agents · TypeScript · +898 stars today, ≈ 1,915 by evening
   Open-source Node.js and React platform for orchestrating a team of AI agents: goals, org chart, budgets, tickets and audit. Suits teams running autonomous agents (Claude Code, Codex, Cursor, etc.) and wanting to manage them like employees.
   Full card: https://gitnova.dev/en/r/paperclipai/paperclip.md
3. **dzhng/jevgrep** — 7.5 · Early signal · AI agents · TypeScript · +219 stars today, ≈ 457 by evening
   A CLI for coding agents that finds relevant files and source excerpts in a repository from a question about code behavior. It uses Jev for relevance ranking and requires a Vercel AI Gateway, TypeSafe, or OpenRouter key.
   Full card: https://gitnova.dev/en/r/dzhng/jevgrep.md
4. **mvschwarz/openrig** — 7.1 · Early signal · AI agents · TypeScript · +204 stars today, ≈ 421 by evening
   OpenRig is a harness orchestrator for AI coding agents: a team of agents (Claude Code and Codex) is defined in YAML and booted with one command, turning scattered terminal sessions into a managed team with a lead agent.
   Full card: https://gitnova.dev/en/r/mvschwarz/openrig.md
5. **Contrastive-LM/CLM** — 6.2 · Peaking · AI agents · Python · +103 stars today, ≈ 225 by evening
   CLM is a class of System One language models trained contrastively to connect states and actions; the repo serves CLM-8B behind a TypeSafe-compatible API for fast agent decision-making.
   Full card: https://gitnova.dev/en/r/Contrastive-LM/CLM.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-28 13:02 UTC, updated every 30 minutes.