#llm Repositories
2,314 repositories total
AIโassisted longโform novel creation, cardโstyle creation, supports structured AI generation and contextual references based on JSON Schema, with strong scalability.
Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.
This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & Vertical Distillation of LLMs.
Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM Top 10), with an evidence-checked attack-path graph. Runs on a local LLM behind a Privacy Gateway. Integrates with GitHub, GitLab, Jenkins, VS Code, JetBrains, n8n, Grafana & Splunk.
[ICLR 2026] Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input
AttackGen is a cybersecurity incident response testing tool that leverages the power of large language models and the comprehensive MITRE ATT&CK framework. The tool generates tailored incident response scenarios based on user-selected threat actor groups and your organisation's details.
EvoOntology: A Self-Evolving Ontology Layer for Data Agents โ๏ธ The EvoOntology plugin builds and evolves an ontology layer for Claude Code/Codex
Reverse engineered Windows Copilot into an OpenAI-compatible API. Access GPT-4 and GPT-5 models through a simple REST interface without API keys or billing.
Even when theyโre not by your side, theyโre still here. Upload real chat logs and recreate a digital persona โ an open-source AI companion with persona distillation, an emotion engine, 11 LLM providers, and a graduation mechanism.
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
Open-source AI agent harness in native Rust โ GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.
Open memory and reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) โ by Nautilus Platform
Agentic development harness for Claude Code โ SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and ClaudeรGLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.
This project includes a long-form novel generator based on large language models like GPT, along with various novel generation prompts and tutorials. We welcome community contributions and continuously update to provide the best novel writing experience.
A list of open-source AI projects you can use to generate income easily.
Open-source AI companions, desktop pets, long-term memory & proactive chat. A comprehensive directory of open-source human-AI romance projects. Enable your local machine AI to exist independently of official platforms, equipped with memory and proactivity.
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.
E2M converts various file types (doc, docx, epub, html, htm, url, pdf, ppt, pptx, mp3, m4a) into Markdown. Itโs easy to install, with dedicated parsers and converters, supporting custom configs. E2M offers an all-in-one, flexible, and open-source solution.
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.
A Lighting Pytorch Framework for Recommendation Models, Easy-to-use and Easy-to-extend.
AI Cross-Border E-commerce Operations Agent Toolkit ยท Break down operations SOPs into 7 reusable AI Agent workflows, complete with prompts, templates, and real-world case studies
A database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonomous AI agents
The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and Windows.
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
Langtrace ๐ is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorDBs and more.. Integrate using Typescript, Python. ๐๐ป๐
Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations platform (AI SOC)
An autonomous agent that takes work, does work, gets paid, and gets better at it.
Bringing together outstanding artificial intelligence (AI) open source projects from around the world.
List of language agents based on paper "Cognitive Architectures for Language Agents"
Simple go utility to download HuggingFace Models and Datasets
Shiping: Screenshot + AI to understand anything on your screen. Code, error messages, problems, charts, and foreign-language materialsโtake a screenshot with a keyboard shortcut and get an answer. Run it in the background as a desktop tool and select any area for instant recognition. In conversation mode, it understands questions in real time and provides key points for an answer. Use it as a desktop tool, interview assistant, exam assistant, or study practice assistant.
An RSI Agent Harness for running, evaluating, and evolving agentsโwith tools, skills, MCP, stateful execution, and multi-agent workflows.
Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.