llm

Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST API and MCP support for AI clients.

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.

Rank LLMs, RAG systems, and prompts using automated head-to-head evaluation

An experiment that applies Google Research's `ReasoningBank` technique to Small Language Models. This experiment hopes to show that the same gains from the ReasoningBank paper also applies to much smaller, less capable models.

A high-performance AI Gateway written in Rust — call 100+ LLM APIs using OpenAI format

Self-hosted RAG platform for AI document search across GitHub, Notion, Google Drive, local files, and web sources with citations.

A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

Beginner-friendly repository for launching your first LLM API with Python, LangChain and FastAPI, using local models or the OpenAI API.

A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summaries and suggestions based on user queries. Features data ingestion with Airflow, real-time monitoring with Grafana, and a Streamlit interface.

Mistral + Haystack: build RAG pipelines that rock 🤘

(Windows/Linux/MacOS) Local WebUI with neural network models (Text, Image, Video, 3D, Audio) on python (Gradio interface). Translated on 3 languages

Open-source, self-hosted multi-agent AI infrastructure for teams and apps with support for cloud and local models, tool integrations, workflows, and automation across business systems including Slack, ERPNext, Discord & Gmail.

The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLLM/SGLang — 0.76 µs per request, no I/O on the request path, cache-affinity routing, RBAC, budgets and a 13-screen UI in the binary.

Efficient LLM inference on Slurm clusters.

Self-hosted RAG search engine — 34 formats, BM25+hybrid search, multi-LLM (Gemini/OpenAI/Claude/Ollama), FastAPI + Docker, production-ready in 3 min

Ask several AI models one question — they answer in parallel, critique each other blind, and you decide. Native macOS, bring-your-own-keys.

Commanding robots using only Language Models' prompts

Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.

A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-device. MLX-native, Ollama/OpenAI API compatible, zero API keys.