#llm Repositories
2,314 repositories total
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
ใYuriba: Decoding Agent Harnessใ420,000 words dissecting the Harness framework and nerves of AI Agents โ In-depth analysis of Claude Code architecture, 15 chapters from conversation loops to building your own Agent Harness. Online reading website:
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS
Global edition of ARTEX โ an LLM multi-agent autonomous penetration-testing framework. English by default, with Korean, Chinese, Spanish, and Japanese available. For authorized defensive and detection use only. (Upstream: Autumn-27/ARTEX, AGPL-3.0)
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
Long-term memory runtime for AI agents โ plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.
Excel MCP server: let AI (Claude, Cursor, Codex) create and edit Excel files with charts, PivotTables, slicers, and formulas. No Excel required.
Preswald is a WASM packager for Python-based interactive data apps: bundle full complex data workflows, particularly visualizations, into single files, runnable completely in-browser, using Pyodide, DuckDB, Pandas, and Plotly, Matplotlib, etc. Build dashboards, reports, and notebooks that run offline, load fast, and share like a document.
Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions โ with one command.
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
ChatGPT Jailbreaks, GPT Assistants Prompt Leaks, GPTs Prompt Injection, LLM Prompt Security, Super Prompts, Prompt Hack, Prompt Security, Ai Prompt Engineering, Adversarial Machine Learning.
Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.
Build a modern LLM from scratch. Every line commented. Explained like we are five.
Hold a key, speak, release โ AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows.
Agent Skills for NVIDIA products โ install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
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.
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! โญ๏ธ
197 production-ready AI agent templates for OpenClaw. SOUL.md configs across 24 categories. Submit yours!
GUI for the Windows Subsystem for Linux โ and native Linux/macOS VMs on Mac. Install, back up, move and configure distros without CLI flags; AI assistant with tools, MCP server for agents, remote WSL over SSH.
Soul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI, Telegram or More.
The missing DevTools for Claude Code โ inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
TimeGPT-2.1: production-ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. A generative pre-trained transformer for time series, trained on over 100B data points. It can accurately predict across various domains, such as retail, electricity, finance, and IoT, with just a few lines of code ๐.
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
A-share multi-agent investment research framework โ Adapted to A-share data sources (Longhu Bang, hot money, unlocking of shares, etc.), 7 analysts debate and make decisions based on A-share rules, deeply modified from TradingAgents to adapt to the A-share market. A-share multi-agent investment research framework โ 7 AI analysts, bull/bear debate, risk assessment.
LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths.
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).
Claraverse is an open-source privacy-focused ecosystem to replace ChatGPT, Claude, N8N, ImageGen with your own hosted LLM, keys, and compute. With desktop, iOS, Android Apps.
Interview experiences compiled by Datawhale members, contents include machine learning, CV, NLP, recommendation, development, etc. Welcome everyone to star
[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents โ Text & Multimodal
A Chinese NLP Preprocessing & Parsing Package, accurate, efficient, easy to use www.jionlp.com
A practical, open-source guide to mastering WorkBuddy through real-world workflows, tutorials, skills, MCP, automation, and multi-agent practices.
Deep dive into Claude Code internals โ architecture, agent loop, context engineering, and more.
Vibe-Research: An investment research workbench for China A-shares, US stocks, and Hong Kong stocks ยท Watchlists and holdings, daily reviews, industry news, industry research, in-depth stock analysis, backtesting, and a research report library, with 168 data endpoints. Supports subscriptions to Claude Code, Codex, and WorkBuddy, or any model API. | A research workbench for China A-shares, US and HK stocks.