#2121st of 51 in RAG, knowledge and search
aihot
Self-hosted site that scores, clusters and summarizes news feeds into daily digests
- Stars
- 10.4k
- License
- MIT
- Last commit
- Nov 2026
- Language
- TypeScript
3,593 on 29 Sept 202610,373 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Engine behind aihot.news. It ingests RSS, web lists, JSON APIs, X accounts and WeChat accounts, pre-filters with an LLM, scores each item twice, and writes Chinese titles and summaries. Reports of the same event are clustered and ranked by heat, and daily, weekly and monthly editions are compiled. Prompts and thresholds are editable files, so the site can be retargeted to another industry.
Who it is for: Self-hosters building an industry news site with LLM scoring and digests
Strengths
- Selection and writing prompts and admission thresholds are published and editable without code changes
- Event clustering with per-source heat scoring, so repeated coverage from one outlet counts once
- Exposes RSS, public API, MCP, llms.txt and an /agent page for agent consumers
- Admin panel with source test-fetch, per-step model choice, budget cutoff and a calibration script
Weaknesses
- Synced from the live site, not a polished generic framework; upstream sync not guaranteed
- Needs an OpenAI-compatible LLM API key, so token costs recur
- Ships only 18 demo overseas AI sources; you must build your own source list
- Default output and docs are Chinese-oriented; AI-specific features stay on aihot.news only
What it needs
- no GPU
- Docker + Compose
- Needs PostgreSQL 17, Node.js 24, Docker Compose, OpenAI-compatible LLM API
- Models: OpenAI-compatible APIs (DeepSeek, Qwen, Zhipu)
- port 3000
Quick answers
Is aihot open source?
Yes. Its code is on GitHub under the MIT license.
Can you run aihot with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does aihot need a GPU?
No, it runs without one.
Also in RAG, knowledge and search
See all 51| Rank | Project | Score |
|---|---|---|
| 1 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 90 out of 100 |
| 2 | LightRAGGraph-based RAG framework with a REST API server and web UI | 90 out of 100 |
| 3 | deeptutorSelf-hosted AI tutor with knowledge bases, guided learning, books and quizzes | 89 out of 100 |
| #4 | Open NotebookSelf-hosted NotebookLM alternative for research notebooks, chat, and podcasts | 89 out of 100 |
| #5 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 87 out of 100 |