✨ Reverse-engineered Python API for Google Gemini web app
Repository Index
95,842 visible repositories in the index
49–72 of 162 · Most stars
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints
Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents
- generative-ai
- hallucinations
- llm
Comet: agent skill harness for turning ideas into evaluated workflows
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
DeepTeam is a framework to red team LLMs and AI agents.
- llm-guardrails
- llm-red-teaming
- llm-safety
- python
Community maintained hardware plugin for vLLM on Huawei Ascend
Advanced CLI tool that scans your hardware and tells you exactly which LLM or sLLM models you can run locally, with full Ollama integration.
Lucebox inference engine for heterogeneous hardware & consumer GPUs
Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.
A general fine-tuning kit geared toward image/video/audio diffusion models.
- diffusers
- diffusion-models
- fine-tuning
- flux-dev
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
- proof-assistant
- lean4
- ai-agents
- ai-for-math
Switch between Claude accounts, Gemini, Copilot, OpenRouter (300+ models) via CLIProxyAPI OAuth proxy. Visual dashboard, remote proxy support, WebSearch fallback. Zero-config to production-ready.
- claude
- claude-code
- cli-tool
- multi-account
✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
- large-multimodal-models
- multimodal-large-language-models
- omni-language-model
- omni-modal-video-understanding
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and model-agnostic. Currently shipping Qwen3.8-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1×/2×/4x/8x cards.
A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
- nlp
- text-classification
- text-matching
- information-extraction
A unified cross-platform AI client supporting seamless transitions between standard cloud APIs and on-device, offline execution of custom and uncensored language models.
I made my AI think harder by making it argue with itself repeatedly. It works stupidly well.
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
- ai-gateway
- observability
- simulation
- ai-agents
Local-first AI token usage & cost tracker for 31 coding tools incl. Claude Code, Codex, Cursor, Gemini & DeepSeek Harness—with native apps. Never reads prompts.
- claude-code
- cli
- codex-cli
- cost-tracker
Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.
Run a 1-billion parameter LLM on a $10 board with 256MB RAM