Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Repository Index
47,133 repositories indexed
1–24 of 36 · Most stars
A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.
SGLang is a high-performance serving framework for large language models and multimodal models.
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
- machine-learning
- ai
- ml
- mlflow
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
- semantic-search
- information-retrieval
- ai
- python
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
- agent-framework
- pydantic
- python
- genai
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
- agent-skills
- self-evolving-agents
Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view
- agentneo
- agents
- ai-performance-optimization
- llm-testing
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
A framework for building realtime voice AI agents 🤖🎙️📹
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
- nlp
- embedding
- bert
- ernie
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
- python
- real-time
- speaker-diarization
- speech-recognition
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
- cloud-computing
- deep-learning
- gpu
- hyperparameter-tuning
Build, Manage and Deploy AI/ML Systems
- machine-learning
- model-management
- ai
- ml
A framework to enable a multimodal model to operate a computer.
- automation
- openai
- pyautogui
FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models
A collection of libraries to optimise AI model performances
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
Scalable, event-driven, deep-learning-friendly backtesting library
- reinforcement-learning
- deep-reinforcement-learning
- gym-environment
- openai-gym
EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluation code.