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 75 · Most stars
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The simplest, fastest repository for training/finetuning medium-sized GPTs.
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
- ai-tutor
- deepresearch
- interactive-learning
- multi-agent-systems
TranslatedChatGLM-6B: An Open Bilingual Dialogue Language Model
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
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
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
TranslatedUse ChatGPT to summarize the arXiv papers. Accelerate the entire research workflow, using ChatGPT for full-text paper summarization + professional translation + polishing + peer review + review replies
- arxiv
- paper
Toolkit for linearizing PDFs for LLM datasets/training
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
TranslatedChinese LLaMA & Alpaca LLMs + local CPU/GPU training and deployment
- llm
- plm
- pre-trained-language-models
- alpaca
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
TranslatedProduction-grade platform for building agentic IM bots - Agent, knowledge base orchestration, plugin system / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信 (Qiye Weixin, "Enterprise WeChat"), 企微智能机器人 (Qiwei Zhineng Jiqiren, "Enterprise WeChat smart bot"), 公众号 (Gongzhonghao, "official account")) / 飞书 (Feishu, "flying book") / 钉钉 (Dingding, "nail nail") / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Kimi, openclaw / hermes agent, deerflow
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
TranslatedChatGLM2-6B: An Open Bilingual Chat LLM
- chatglm
- chatglm-6b
- large-language-models
- llm
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
- chatbot
- chatgpt-api
- chatglm
- claude
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.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Unified framework for building enterprise RAG pipelines with small, specialized models
- parsing
- retrieval-augmented-generation
- agents
- generative-ai-tools
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
TranslatedChatGLM3 series: Open Bilingual Chat LLMs