Code Stars
1.88K subscribers
8.5K photos
8.79K links
Code Stars provides notifications about GitHub repositories that are gaining a significant number of stars in a short period of time. Be the first to find out about trending repositories that everybody will be talking about soon.
#AI #chatGPT #python
Download Telegram
khoj-ai/khoj
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
Language:Python
Total stars: 24430
Stars trend:
13 Jan 2025
9pm ▋ +5
10pm ▎ +2
11pm ▉ +7
14 Jan 2025
12am ▋ +5
1am ▊ +6
2am ▊ +6
3am █ +8
4am █▏ +9
5am ▉ +7
6am ▍ +3
7am █▎ +10
8am ██▏ +17

#python
#agent, #ai, #assistant, #chat, #chatgpt, #emacs, #imagegeneration, #llama3, #llamacpp, #llm, #obsidian, #obsidianmd, #offlinellm, #productivity, #rag, #research, #selfhosted, #semanticsearch, #stt, #whatsappai
hiyouga/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Language:Python
Total stars: 38120
Stars trend:
14 Jan 2025
12am ▏ +1
1am ▏ +1
2am ▊ +6
3am █▍ +11
4am ▋ +5
5am ▋ +5
6am █▏ +9
7am ██▍ +19
8am █ +8
9am █▎ +10
10am ▋ +5
11am ▊ +6

#python
#agent, #ai, #chatglm, #finetuning, #gpt, #instructiontuning, #languagemodel, #largelanguagemodels, #llama, #llama3, #llm, #lora, #mistral, #moe, #peft, #qlora, #quantization, #qwen, #rlhf, #transformers
mudler/LocalAI
:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed, P2P inference
Language:Go
Total stars: 28664
Stars trend:
19 Jan 2025
7am ▊ +6
8am ▉ +7
9am ▎ +2
10am ▍ +3
11am ▎ +2
12pm ▍ +3
1pm ██▍ +19
2pm █▋ +13
3pm █▋ +13
4pm █ +8

#go
#ai, #api, #audiogeneration, #distributed, #gemma, #gpt4all, #imagegeneration, #kubernetes, #libp2p, #llama, #llama3, #llm, #mamba, #mistral, #musicgen, #rerank, #rwkv, #stablediffusion, #textgeneration, #tts
refly-ai/refly
Refly is an open-source AI-native creation engine. Its intuitive free-form canvas interface combines multi-threaded dialogues, AI knowledge base integration, contextual memory, intelligent search, WYSIWYG AI editor and more, empowering you to effortlessly transform ideas into production-ready content.
Language:TypeScript
Total stars: 176
Stars trend:
24 Jan 2025
9am ███▍ +27
10am ████▎ +34
11am ████▊ +38
12pm ███ +24
1pm ███▍ +27

#typescript
#agent, #ai, #aimemory, #anthropic, #artifacts, #blogs, #canvas, #contentcreation, #deepseek, #documentation, #editor, #gemini, #gpt4, #knowledgebase, #llama3, #notetaking, #qwen, #rag, #wiki, #workflow
unslothai/unsloth
Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
Language:Python
Total stars: 21477
Stars trend:
27 Jan 2025
10pm ▍ +3
11pm ▍ +3
28 Jan 2025
12am ▍ +3
1am ▉ +7
2am ▌ +4
3am ▌ +4
4am ▌ +4
5am █ +8
6am ▋ +5
7am █▎ +10
8am ▊ +6
9am ██▍ +19

#python
#finetuning, #finetuning, #gemma, #gemma2, #llama, #llama3, #llm, #llms, #lora, #mistral, #phi3, #qlora, #unsloth
ScrapeGraphAI/Scrapegraph-ai
Python scraper based on AI
Language:Python
Total stars: 17596
Stars trend:
31 Jan 2025
6am ▌ +4
7am ▏ +1
8am ▉ +7
9am █ +8
10am ▋ +5
11am ▉ +7
12pm ▉ +7
1pm █▍ +11
2pm █ +8
3pm █▏ +9
4pm ▉ +7
5pm ▊ +6

#python
#ai, #automatedscraper, #gpt3, #gpt4, #llama3, #llm, #machinelearning, #sc, #scraping, #scrapingpython, #scrapingweb, #webscraping
Mintplex-Labs/anything-llm
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, and more.
Language:JavaScript
Total stars: 31528
Stars trend:
31 Jan 2025
9am ▌ +4
10am █ +8
11am ▌ +4
12pm ▍ +3
1pm █▍ +11
2pm █▏ +9
3pm ▉ +7
4pm ▊ +6
5pm ▊ +6
6pm ▌ +4
7pm █▏ +9
8pm ▌ +4

#javascript
#agentframeworkjavascript, #aiagents, #crewai, #customaiagents, #desktopapp, #llama3, #llm, #llmapplication, #llmwebui, #lmstudio, #localllm, #localai, #multimodal, #nodejs, #ollama, #rag, #vectordatabase, #webui
sgl-project/sglang
SGLang is a fast serving framework for large language models and vision language models.
Language:Python
Total stars: 8931
Stars trend:
7 Feb 2025
10pm ▊ +6
11pm ▊ +6
8 Feb 2025
12am ▍ +3
1am █ +8
2am █▋ +13
3am █▎ +10
4am ▌ +4
5am █▊ +14
6am █▋ +13
7am █ +8
8am █▊ +14
9am █▊ +14

#python
#cuda, #deepseek, #deepseekllm, #deepseekv3, #inference, #llama, #llama2, #llama3, #llama31, #llava, #llm, #llmserving, #moe, #pytorch, #transformer, #vlm
fatwang2/siri-ultra
The most intelligent Siri powered by LLMs
Language:TypeScript
Total stars: 554
Stars trend:
10 Feb 2025
1am ▏ +1
2am +0
3am +0
4am ▍ +3
5am ▌ +4
6am █▎ +10
7am █▉ +15
8am ██▎ +18
9am ███▌ +28
10am ██ +16
11am ██ +16
12pm ██▋ +21

#typescript
#apple, #groq, #llama3, #llms, #openai, #shortcuts, #siri
b4rtaz/distributed-llama
Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
Language:C++
Total stars: 1786
Stars trend:
15 Feb 2025
3pm ▏ +1
4pm █▋ +13
5pm █▊ +14
6pm ██▎ +18
7pm █▎ +10
8pm ▌ +4
9pm ▊ +6
10pm ▋ +5
11pm ▍ +3
16 Feb 2025
12am ▏ +1
1am +0
2am ▏ +1

#cplusplus
#distributedcomputing, #distributedllm, #llama2, #llama3, #llm, #llminference, #llms, #neuralnetwork, #openllm
1Panel-dev/MaxKB
💬 MaxKB is an open-source AI assistant for enterprise. It seamlessly integrates RAG pipelines, supports robust workflows, and provides MCP tool-use capabilities.
Language:Python
Total stars: 15823
Stars trend:
22 Apr 2025
12am ▏ +1
1am +0
2am ▋ +5
3am ██ +16
4am ██▉ +23
5am █▉ +15
6am ██ +16

#python
#chatbot, #deepseekr1, #knowledgebase, #langchain, #llama3, #llm, #maxkb, #mcpserver, #ollama, #pgvector, #qwen2, #rag
hiyouga/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Language:Python
Total stars: 49776
Stars trend:
24 May 2025
6am ▏ +1
7am █ +8
8am ▋ +5
9am █▎ +10
10am █▋ +13
11am ███ +24
12pm █▊ +14
1pm █▌ +12
2pm █▊ +14
3pm ██▌ +20
4pm ███▏ +25
5pm ██▏ +17

#python
#agent, #ai, #chatglm, #finetuning, #gpt, #instructiontuning, #languagemodel, #largelanguagemodels, #llama, #llama3, #llm, #lora, #mistral, #moe, #peft, #qlora, #quantization, #qwen, #rlhf, #transformers
datawhalechina/self-llm
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调(全参数/Lora)、部署国内外开源大模型(LLM)/多模态大模型(MLLM)教程
Language:Jupyter Notebook
Total stars: 16594
Stars trend:
8 Jun 2025
10pm ▏ +1
11pm ▏ +1
9 Jun 2025
12am █ +8
1am █▌ +12
2am █▌ +12
3am █▎ +10
4am ▌ +4
5am ▌ +4
6am █ +8
7am █▏ +9
8am ▊ +6
9am ▌ +4

#jupyternotebook
#chatglm, #chatglm3, #gemma2bit, #glm4, #internlm2, #llama3, #llm, #lora, #minicpm, #qwen, #qwen, #qwen15, #qwen2