LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and medical agentic benchmarks.
Repository Index
88,573 visible repositories in the index
361–384 of 926 · Most stars
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.
Comet: agent skill harness for turning ideas into evaluated workflows
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
- embeddings
- openai
- rag
- retrieval
🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.
OneTrainer is a one-stop solution for all your Diffusion training needs.
- fine-tuning
- lora
- training
- image-model-training
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
- agent
- artificial-intelligence
- benchmark
- multimodal
Full description can be found here: https://discuss.huggingface.co/t/pretrain-gpt-neo-for-open-source-github-copilot-model/7678?u=ncoop57
🌊 AChat - An open-source/self-hosted/local-first AI platform, designed for enterprises and teams, perfectly combining powerful local processing capabilities with seamless remote synchronization.
Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs
- ai-agents
- ai-workflow
- beginner-friendly
- mvp-development
A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.
- agent-skills
- agentic-workflows
- ai-agents
- automation
Specialised AI models for logo design — a brand-analysis model turns a business into constraints, typography and symbol models construct the mark, and a composition engine produces real lockups and clear-space rules. Early access open.
- brand-identity
- cloudflare-workers
- design-systems
- generative-ai
LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.
- ai
- auto-completion
- developer-tools
- ide
InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统)
Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown
Add a real-time analytics node to your operational database. Spice is a portable, accelerated SQL query, search, and LLM-inference engine in Rust for data-grounded AI apps and agents.
- artificial-intelligence
- developers
- machine-learning
- data
Improved file parsing for LLM’s
- document-structure
- table-detection
- document-parser
- layout-parsing
Let ChatGPT teach your own chatbot in hours with a single GPU!
Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor. 把 Windsurf/Devin 云端 100+ 模型变成三套兼容 API。
- openai-compatible
- windsurf
- anthropic-compatible
- claude-code
QuantMind is an open source agent-native knowledge extraction and retrieval framework for quantitative finance.
- quantitative-finance
- quantitative-research
- data
- knowledge
Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
- bert
- pre-training
- fine-tuning
- gpt
RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.
- ai
- containers
- cuda
- hip