LLM & Chat
Self-hosted large language model servers and chat interfaces.
Open WebUI
User-friendly WebUI for LLMs (Ollama, OpenAI API)
AxonHub
Open-source AI Gateway — use any SDK to call 100+ LLMs with built-in failover, load balancing, and cost control.
EvalScope
Streamlined and customizable framework for efficient large model (LLM, VLM, AI agent) evaluation and performance benchmarking.
Rig
Build modular and scalable LLM Applications in Rust
H2O LLM Studio
A no-code GUI framework for fine-tuning Large Language Models, with an intuitive dashboard and experiment tracking
WindsurfAPI
Self-Hosted AI Model Gateway for 100+ Models
DEEIX Chat
Enterprise AI workspace with model routing, multimodal chat, files, tools, and billing management
DeepClaude
High-performance LLM inference API combining DeepSeek R1 reasoning with Claude's creative power
CoAI
Next-gen multi-tenant AI platform with enterprise LLM gateway, built-in billing, and support for 200+ AI models
AI as Workspace
Elegant AI chat client with multi-workspace support, plugin system, MCP integration, and real-time cloud sync
Evidently
Open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline with 100+ metrics.
MLflow
Open source AI engineering platform for agents, LLMs, and ML models. Debug, evaluate, monitor, and optimize production-quality AI applications.
OmniRoute
Free AI gateway: one endpoint, 231+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini. RTK+Caveman compression saves 15-95% tokens.
Manifest
The open source LLM router that connects your AI agents and harnesses to any provider in seconds. Subscriptions, pay-per-token, local models, and custom providers.
FastChat
Open-source platform for training, serving, and evaluating large language models — from the makers of Vicuna and Chatbot Arena
FastAgency
The fastest way to bring multi-agent workflows to production
SillyTavern
LLM Frontend for Power Users - roleplay, chat, and AI interactions
Lemonade
Run optimized LLMs locally on your own GPU or NPU — a fast, OpenAI-compatible server for private AI apps.
OpenMed
Local-first healthcare AI for clinical NER and HIPAA PII de-identification, running 100% on your own hardware.
Giskard
Open-source evaluation & testing library for LLM agents
RLLM
Agentic RL on any harness, with any backend, on any benchmark
Soup
Fine-tune LLMs from one YAML file. Layer streaming trains an 8B model on a 4 GB laptop GPU.
ODS
Turn your PC, Mac, or Linux box into a full AI server — LLM inference, chat UI, voice, agents, RAG, and workflows.
vLLM Omni
A framework for efficient model inference with omni-modality models, built on vLLM.
DS4
Local inference engine for DeepSeek 4 Flash and PRO — run on Metal, CUDA and ROCm
Colibri
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model.
Chainlit
Build Conversational AI chatbots in minutes with Python
GPUStack
Manage GPU clusters, serve AI models with vLLM and SGLang, and get SSH-accessible GPU instances on demand.
vLLM Ascend
High-throughput LLM serving on Huawei Ascend NPUs. Community-maintained hardware plugin for vLLM.
Mesh LLM
Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.
Bifrost
Fastest enterprise AI gateway — 50x faster than LiteLLM with adaptive load balancing, cluster mode, guardrails, and 1000+ model support.
BentoML
The easiest way to serve AI apps and models — build inference APIs, job queues, LLM apps, and multi-model pipelines.
SeekDB
The AI-Native Search Database. Unifies vector, full-text, and scalar search in one engine — the best storage for AI agents.
OpenMetadata
The open platform for trusted data context and business semantics for humans, AI assistants, and agents.
FauxPilot
Open-source alternative to Copilot using Triton Inference Server
Xinference
Run open-source LLMs, embeddings, and multimodal models with one line of code
Text Generation Inference
Hugging Face's high-performance LLM serving with Rust/Python for production
TabbyAPI
Lightweight OpenAI-compatible ExLlamaV2 API server
Aphrodite Engine
High-performance LLM inference engine for roleplay and chatbots
Llamafile
Distribute and run LLMs as single-file executables — no installation needed
LMDeploy
Efficient LLM deployment with TurboMind/PyTorch engines
SGLang
High-performance serving framework for LLMs with RadixAttention
Intel transformers
Intel extension for transformers and LLM serving
text-generation-webui
Run local LLMs with a powerful web interface — text, vision, tool-calling, and OpenAI-compatible API
aisuite
Simple, unified interface to multiple generative AI providers
Open WebUI Pipelines
Connection framework for Open WebUI — add custom filters, function routing, and pipelines to any LLM
LiteLLM
Open-source AI gateway to call 100+ LLM providers in OpenAI format — self-hosted, enterprise-ready
LocalAI
Open-source AI engine — run any model (LLM, vision, voice, image, video) on any hardware, no GPU required
Jan
Open-source ChatGPT replacement — run LLMs locally with full control and privacy
LibreChat
Self-hosted AI chat platform unifying all major LLM providers in one privacy-focused UI
Phoenix
AI observability & evaluation: LLM tracing, evaluation, and RAG troubleshooting
Streamlit
Build and share data apps in pure Python — fast
OpenVINO
Intel's open-source toolkit for optimizing and deploying AI inference across hardware platforms
Lobe Chat
Extensible, open-source ChatGPT alternative with plugins, knowledge base, and multi-LLM support
llama-cpp-python
Python bindings for llama.cpp with OpenAI-compatible server and multi-model support
Langfuse
Open source AI engineering platform for LLM observability, evals, and prompt management
Bionic GPT
On-premise replacement for ChatGPT with enterprise data confidentiality
LangServe
Deploy LangChain runnables and chains as production-ready REST APIs
DSPy
The framework for programming—not prompting—language models
NextChat
Cross-platform ChatGPT web UI with multi-model support for Ollama, Claude, Gemini, and more
Helicone
Open-source LLM observability platform for monitoring, evaluating, and improving your AI applications
HuggingChat
Open-source chat interface powering HuggingChat, built by Hugging Face
Big-AGI
The Expert's AI Workspace — multi-model reasoning, personas, and advanced agent controls
Open Assistant
Open-source chat-based assistant that understands tasks and interacts with third-party systems
Chatbot UI Lite
Extremely lightweight ChatGPT-style chat interface built with Next.js, TypeScript and Tailwind CSS
Gradio
Build and share delightful machine learning apps in Python
Chatbot UI
The open-source AI chat app for everyone — chat with 80+ AI models