An open, programmable decision layer for models and compute.
- mixture-of-models
- semantic-router
- vllm
- ai-gateway
Repository Index
47,133 repositories indexed
97–120 of 214 · Most stars
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
- llava
- llm
- mlx
- vision-transformer
Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.
Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.
- llm-observability
- agent-monitoring
- agent-observability
- ai-error-monitor
Sellbird (formerly Harvey): the open-source outreach platform that runs on your Claude or ChatGPT plan. Finds companies and decision makers, verifies emails, writes personal cold email, sends it and handles the replies.
The Ruby AI framework.
Fully featured & enhanced replacement for copilot.vim complete with API for interacting with Github Copilot
- copilot
- github-copilot
- lsp-server
- lua
TranslatedFull-text PDF translation with layout preserved and bilingual side-by-side display · Search 240 million papers and add them to your library in one click · Q&A over your library knowledge base · AI close reading of papers, literature reviews, and mind maps · Journal quartile / Chinese Academy of Sciences (CAS) ranking / JCR / impact factor shown directly in the list · Plugin-free web version app.ai4paper.pro · Compatible with Zotero 7–10
- academic-writing
- ai-research
- literature-review
- paper-reading
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
OpenAI API + Ruby! 🤖❤️ GPT-5 & Realtime WebRTC compatible!
README file generator, powered by AI.
- readme-generator
- readme
- readme-md-generator
- ai
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
Global edition of ARTEX — an LLM multi-agent autonomous penetration-testing framework. English default, switchable to Korean/Chinese/Spanish/Japanese. For authorized, defensive and detection use only. (upstream: Autumn-27/ARTEX, AGPL-3.0)
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.
- ai-video
- awesome
- bytedance
- prompt-engineering
A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
- ai-gateway
- observability
- simulation
- ai-agents
UNIGIT public brand and ecosystem hub — AI should work for everyone.
- agentic-ai
- ai-tools
- ai-workbench
- ecosystem
Supercharged experience for multiple models such as ChatGPT, DALL-E and Stable Diffusion.
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
- healthcare
- data-mining
- deep-learning
- preprocessing
🦎 A lightweight, streaming-native, multi-protocol gateway for AI, APIs, and real-time data. Route LLM requests across providers, govern MCP tools, and connect Kafka, MQTT, and HTTP through one high-performance engine with shared security and observability.
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
- agents
- calibration
- classification
- decision-making
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy