# MoonshotAI/Kimi-K3

> Kimi K3 is an open-weight native multimodal agentic MoE language model with 2.8T parameters and a 1M-token context window, understanding text, images and video. It targets long-horizon coding, agentic knowledge work and complex reasoning.

- Magnitude: 1.4 out of 10 — Steady
- Stars: 9,006 total · +2 stars measured 2026-10-29, 00:11–03:01 UTC, ≈ 9 by evening
- Star trust: star growth looks organic
- Category: Language models · Created: 2026-07-27 · Last push: 2026-08-06
- GitHub: https://github.com/MoonshotAI/Kimi-K3 · Page: https://gitnova.dev/en/r/MoonshotAI/Kimi-K3

## Useful for

- Run the model locally for long coding sessions across large repositories
- Build a deep-research agent producing visualizations and dashboards
- Process long documents and video within a single 1M-token context

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:11–03:01: 9004 → 9006 stars (+2). This is the change over that interval.
- Estimated end-of-day forecast: about +9 stars, using observed gains and the previous day.
- Top new repositories in the last 4 months: #73.

## 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: 767
- Issues and pull requests: 47
- Watchers: 40
- Average over the last week: 9 per day
- Usual pace: 6 per day
- Stars in the last hour (measured): 1

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

2026-09-30 … 2026-10-29: 4, 5, 2, 3, 4, 2, 4, 4, 5, 6, 9, 3, 4, 6, 4, 8, 6, 8, 5, 8, 7, 5, 6, 11, 12, 5, 12, 5, 7, 2

## Magnitude by day, last 14 days

10-16 1.4, 10-17 1.2, 10-18 1.4, 10-19 1.1, 10-20 1.5, 10-21 1.1, 10-22 1.2, 10-23 1.5, 10-24 1.7, 10-25 1.6, 10-26 1.4, 10-27 1.6, 10-28 1.1, 10-29 1.4

## Spotted in now

- Top new repositories in the last 4 months: #73

## More in this category

1. **togg53192-cmd/jailbreaks** — 7.7 · Breakout · Language models · +200 stars measured 2026-10-29, 00:02–02:52 UTC, ≈ 1,362 by evening
   A collection of 31 system prompts, persona locks, and AGENTS.md files for 25+ models (Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, Gemma, GPT-OSS). Intended for research on how instruction hierarchies and policy overrides affect model…
   Full card: https://gitnova.dev/en/r/togg53192-cmd/jailbreaks.md
2. **OpenBMB/MiniCPM-OCR** — 6.2 · Early signal · Language models · Python · +49 stars measured 2026-10-29, 00:03–02:52 UTC, ≈ 268 by evening
   MiniCPM-OCR is an open-source OCR model family for parsing Chinese and English documents and PDFs into Markdown or JSON, with a 2B model (Jev) that scores recognition quality per region.
   Full card: https://gitnova.dev/en/r/OpenBMB/MiniCPM-OCR.md
3. **thomasunise/casecite** — 5.7 · Early signal · Language models · Python · +12 stars measured 2026-10-29, 00:03–02:52 UTC, ≈ 70 by evening
   Self-hosted legal research platform: upload your firm's documents, ask questions with citations, review contracts, draft documents and research judges. Runs on your own infrastructure with your own API keys.
   Full card: https://gitnova.dev/en/r/thomasunise/casecite.md
4. **google-deepmind/detectorscope** — 5.6 · Early signal · Language models · Python · +8 stars measured 2026-10-29, 00:03–02:52 UTC, ≈ 90 by evening
   A toolkit for building AI-text detectors whose decisions are mechanistically grounded and auditable: each prediction is a sum of named features localized in the text. Built on sparse autoencoders and a concept bottleneck over the language…
   Full card: https://gitnova.dev/en/r/google-deepmind/detectorscope.md
5. **NVIDIA/auto-ontology** — 5.5 · Early signal · Language models · Python · +13 stars measured 2026-10-29, 00:03–02:52 UTC, ≈ 122 by evening
   NVIDIA's Python framework that builds a semantic ontology graph over enterprise metadata, giving LLM agents trusted metric and entity definitions for reliable text-to-SQL.
   Full card: https://gitnova.dev/en/r/NVIDIA/auto-ontology.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 2026-10-29 03:04 UTC, updated every 30 minutes.