~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
- academia
- arxiv
- brave
- deep-research
Repository Index
77,353 visible repositories in the index
49–72 of 293 · Most stars
Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.
- knowledge-graph
- large-language-model
- logical-reasoning
- multi-hop-question-answering
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
- evaluation
- benchmark
- large-language-model
- llm
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
AI agent to evaluate and score resumes.
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.
Framework for evaluating and improving agents
- evals
- rl-environments
- terminal-bench
An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.
- claude-code
- geoguessr
- geolocation
- osint
Modeling, training, eval, and inference code for OLMo
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
- ai-agent
- agent-os
- llm-orchestration
- agentic-ai
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
- adk
- agent-development-kit
- agents
- coding-agent
Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
- metric-learning
- deep-learning
- computer-vision
- machine-learning
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
- python
- attack
- adversarial-machine-learning
- poisoning
A curated list of bugbounty writeups (Bug type wise) , inspired from https://github.com/ngalongc/bug-bounty-reference
- bugbounty
- bugbountytips
- bughunting
- bugbounty-writeups
Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox.
- gpt-35-turbo
- whisper-ai
- windows
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
🐢 Open-Source Evaluation & Testing library for LLM Agents
- mlops
- ml-validation
- ml-testing
- ai-testing
A treasure chest for visual classification and recognition powered by PaddlePaddle
- image-classification
- knowledge-distillation
- autoaugment
- randaugment
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.