yifan123/flow_grpo
An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
Language: Python
Stars: 232 Issues: 3 Forks: 9
https://github.com/yifan123/flow_grpo

pea1bee/hotstar-ipl-ad-mute
Mute ads in Hotstar live sport streams
Language: JavaScript
Stars: 134 Issues: 1 Forks: 27
https://github.com/pea1bee/hotstar-ipl-ad-mute

ngxson/smolvlm-realtime-webcam
Real-time webcam demo with SmolVLM and llama.cpp server
Language: HTML
Stars: 701 Issues: 2 Forks: 81
https://github.com/ngxson/smolvlm-realtime-webcam

ByteDance-Seed/Seed1.5-VL
Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.
Language: Jupyter Notebook
#cookbook #large_language_model #multimodal_large_language_models #vision_language_model
Stars: 404 Issues: 0 Forks: 3
https://github.com/ByteDance-Seed/Seed1.5-VL

SakanaAI/continuous-thought-machines
Continuous Thought Machines, because thought takes time and reasoning is a process.
Language: Python
Stars: 382 Issues: 0 Forks: 20
https://github.com/SakanaAI/continuous-thought-machines

Efeckc17/simple-todo-c
A lightweight, native Windows Todo application built with pure C and the Win32 API. Just 54 KB
Language: C
#c #gui #minimal #native #todo #todo_app #tray_application #winapi_application #windows
Stars: 351 Issues: 2 Forks: 8
https://github.com/Efeckc17/simple-todo-c

YonkoSam/whatsapp-python-chatbot
WhatsApp Chatbot using Gemini + WasenderAPI
Language: Python
Stars: 306 Issues: 0 Forks: 84
https://github.com/YonkoSam/whatsapp-python-chatbot

m-ahmed-elbeskeri/Starguard
CLI that detects fake-star campaigns, dependency hijacks, licence red-flags and other signs of repository risk. Inspired by the “4.5 million fake stars” study, StarGuard helps CTOs, security teams and investors perform fast, automated open-source due-diligence.
Language: Python
Stars: 268 Issues: 3 Forks: 6
https://github.com/m-ahmed-elbeskeri/Starguard

stepfun-ai/Step1X-3D
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
Language: Python
Stars: 236 Issues: 4 Forks: 3
https://github.com/stepfun-ai/Step1X-3D

brycebostwick/WidgetAnimation
Proof of concept for Animated iOS Widgets using Public APIs
Language: C
Stars: 211 Issues: 1 Forks: 10
https://github.com/brycebostwick/WidgetAnimation

OpenBMB/AgentCPM-GUI
AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.
Language: Python
Stars: 452 Issues: 11 Forks: 42
https://github.com/OpenBMB/AgentCPM-GUI

pig-dot-dev/muscle-mem
A cache for AI agents to learn and replay complex behaviors.
Language: Python
Stars: 261 Issues: 1 Forks: 7
https://github.com/pig-dot-dev/muscle-mem

dtyq/magic
The first open-source all-in-one AI productivity platform
Language: PHP
#agent #agi #ai #gpt #llm #low_code #mcp #no_code #sandbox #workflow
Stars: 256 Issues: 4 Forks: 31
https://github.com/dtyq/magic

operacle/checkcle
CheckCle is a self-hosted open-source alternative to UptimeRobot, PagerDuty, Better Stack, and more — offering real-time server & service uptime monitoring, incident, multi-channel alerting.
Language: TypeScript
#api #monitoring #pocketbase #realtime #typescript #uptime
Stars: 230 Issues: 1 Forks: 10
https://github.com/operacle/checkcle

xai-org/grok-prompts
Prompts for our Grok chat assistant and @grok bot on X.
Language: Jinja
Stars: 603 Issues: 7 Forks: 51
https://github.com/xai-org/grok-prompts

Zorokee/ArtificialCast
Type-safe transformation powered by inference.
Language: C#
#ai #artificial_intelligence #csharp #dotnet #llm #satire #type_casting
Stars: 270 Issues: 2 Forks: 5
https://github.com/Zorokee/ArtificialCast

cofob/autogenlib
Import wisdom, export code.
Language: Python
Stars: 265 Issues: 0 Forks: 12
https://github.com/cofob/autogenlib

ngxson/vintern-realtime-demo
Language: HTML
Stars: 162 Issues: 2 Forks: 37
https://github.com/ngxson/vintern-realtime-demo

dipampaul17/KVSplit
Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache quantization. KVSplit enables 8-bit keys & 4-bit values, reducing memory by 59% with <1% quality loss. Includes benchmarking, visualization, and one-command setup. Optimized for M1/M2/M3 Macs with Metal support.
Language: Python
#apple_silicon #generative_ai #kv_cache #llama_cpp #llm #m1 #m2 #m3 #memory_optimization #metal #optimization #quantization
Stars: 222 Issues: 1 Forks: 5
https://github.com/dipampaul17/KVSplit

agno-agi/agent-api
A minimal, open-source setup for serving Agents using FastAPI and Postgres. Built for speed, clarity, and dev happiness.
Language: Python
Stars: 165 Issues: 0 Forks: 18
https://github.com/agno-agi/agent-api