gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Repository Index
81,588 visible repositories in the index
337–360 of 7,210 · Most stars
open-source agentic AI data assistant for the next generation of AI + Data products.
Unofficial Python API and agentic skill for Google Gemini Notebook. Full programmatic access to Gemini Notebook's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents like Claude Code, Codex, and OpenClaw.
- python
- sdk
- skills
- google-notebooklm
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
- agent
- artificial-intelligence
- multi-agent-systems
- task-automation
Tongyi Deep Research, the Leading Open-source Deep Research Agent
- agent
- llm
- artificial-intelligence
- information-seeking
An extremely fast Python type checker and language server, written in Rust.
High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all from your IDE. Includes VS Code extension, TypeScript/Python SDKs, and Docker deployment.
- ai
- cpp
- data-pipeline
- data-processing
Automated Nginx Reverse Proxy for Docker
- nginx
- docker
- docker-gen
- reverse-proxy
TranslatedA multi-task real-time/scheduled monitoring and intelligent analysis system for Xianyu (闲鱼), built with Playwright and AI, and equipped with a full-featured back-end management UI. It helps users find the products they like among the vast number of items on Xianyu.
Awesome list of open-source startup alternatives to well-known SaaS products 🚀
- awesome
- awesome-list
- python
- startups
Agent Zero AI framework
🕵️♂️ Offensive Google framework.
- osint
- hideandsec
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement. | Lead: Minwei Wang (https://www.minwei.wang · ORCID: 0009-0002-7976-4689 · DOI: 10.5281/zenodo.24156132)
- agency
- agent
- pua
- pip
Toolkit for linearizing PDFs for LLM datasets/training
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Train transformer language models with reinforcement learning.
Machine Learning Engineering Open Book
- pytorch
- slurm
- large-language-models
- llm
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
The best free and open-source automated time tracker. Cross-platform, extensible, privacy-focused.
- quantified-self
- activitywatch
- productivity
- time-tracking
Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.
Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!
Faker is a Python package that generates fake data for you.
The LLM Evaluation Framework
- evaluation-metrics
- evaluation-framework
- llm-evaluation
- llm-evaluation-framework