[NeurIPS 2026] DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models
- data-mixture
- data-science
- data-selection
- data-reweighting
Repository Index
81,588 visible repositories in the index
1,273–1,296 of 4,424 · Most stars
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
Automatically create and sync Home Assistant backups into Google Drive
- home-assistant
- google-drive
Adaptive Lighting custom component for Home Assistant
- home-assistant
- adaptive-lighting
- automation
- lights
Because sometimes you need to do it live
- command-line
- presentations
- python
- live-coding
:duck: DuckDuckGo from the terminal
- duckduckgo
- command-line
- standalone
- terminal
Classic papers and resources on recommendation
- recommender-system
- deep-learning
- machine-learning
- recommendation
Chatbot继续沿着LLM前进，近期更新小参数量SLM的和训练脚本，支持本地训练。新增ChatAgent,实现各种有实际场景价值的Agent实现。
Quickly and accurately render even the largest data.
- holoviz
- datashader
- data-visualizations
- rasterization
DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coordinate multiple specialized lower-level agents, enabling automated task decomposition and efficient execution across diverse and complex domains.
- gaia
- general-purpose
- multiagent-systems
- multimodel
A deep learning library for video understanding research.
Sprix AI at 屿智同行 — state-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks.
- a2a
- agent-orchestration
- agent-routing
- ai-agents
Graph Attention Networks (https://arxiv.org/abs/1710.10903)
- graph-attention-networks
- attention-mechanism
- self-attention
- tensorflow
Converts text input or URL into knowledge graph and displays
A simple app to get songs from YouTube in mp3 format with artist name, album name etc from sources like iTunes, Spotify, LastFM, Deezer, Gaana etc.
- songs
- youtube
- metadata
- itunes
[CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation
- visual-tracking
- video-object-segmentation
- read-time
- pytorch
A Dockerized python Script to fetch Garmin health data and populate that in a InfluxDB Database, for visualization long term health trends with Grafana
- garmin
- garmin-api
- garmin-connect
- garmin-data
Hummingbird compiles trained ML models into tensor computation for faster inference.
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
- api
- gymnasium
- multi-agent-reinforcement-learning
- reinforcement-learning
Open-source AI assistant ecosystem with MCP integrations, multimodal workflows, IoT support, and cross-platform voice interaction.
Open source Python library for converting PDF to DOCX.
- pdf-converter
- docx
- pdf-to-word
- extract-table
Automated generation of real Swagger/OpenAPI 2.0 schemas from Django REST Framework code.
📐 Compute distance between sequences. 30+ algorithms, pure python implementation, common interface, optional external libs usage.
- distance
- algorithm
- python
- textdistance
A DNS meta-query spider that enumerates DNS records, and subdomains.