GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Repository Index
59,621 visible repositories in the index
217–240 of 375 · Most stars
Optimizing inference proxy for LLMs
- agent
- agentic-ai
- agentic-workflow
- agents
Translated53AI Hub is an open-source AI portal and knowledge base for managing enterprise knowledge, AI agents, prompts, and AI tools, seamlessly integrating with Coze, Dify, FastGPT, RAGFlow. An AI knowledge base and Agent portal
- coze
- dify
- fastgpt
- go
SQL Translator is a tool for converting natural language queries into SQL code using artificial intelligence. This project is 100% free and open source.
- data-analysis
- data-engineering
- dataquery
- datascience
Open Source version of Claude Cowork with 500+ SaaS app integrations
- anthropic
- anthropic-claude
- claude-code
- claude-cowork
TranslatedChinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
- nlu
- benchmark
- chinese
- corpus
Open-Source Generative UI Framework
- agent-native
- agentic-ai
- agents
- ai-agents
PyTorch code and models for V-JEPA self-supervised learning from video.
🔍 导出并模糊搜索 Telegram 聊天记录 | Export and fuzzy search your Telegram chat history
- embedding
- telegram
- telegram-bot
- mcp
A client implementation for ChatGPT and Bing AI. Available as a Node.js module, REST API server, and CLI app.
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.
- apple-silicon
- local-llm
- macos
- mlx
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。
- chinese-nlp
- pretrained-models
- pytorch
- distributed-training
The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 50+ connectors) into a permission-aware workspace that agents can search, grep, navigate and cite. MCP, SDKs and built-in agents. Self-hosted.
- glean
- knowledge-graph
- ollama
- python
Open-source framework for the research and development of foundation models.
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
- onednn
- oneapi
- performance
- cpp
CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️
- ai
- huggingface
- llm
- management-system
The all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. No Docker, no terminal, no cloud required.
- ai-chat
- image-generation
- llm
- local-ai
An Open-Source Package for Knowledge Embedding (KE)
- knowledge-embedding
The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
Sourcebot is a self-hosted tool that helps humans and agents understand your codebase.
- code-search
- code-intelligence
- sourcebot
- fair-source
External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
RAG that intelligently adapts to your use case, data, and queries
A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。