// 1,359 open-source projects indexed

$ Discover the best projects built with Ollama

A hand-curated, daily-updated gallery of open-source projects. Browse the ecosystem, ranked by GitHub stars.

>

sort --stars ▾

#all#aiml1262#devtools82#docs4#dashboards3#apis2

// 1359 results

Debug your RAG pipeline without leaving the terminal. Real-time chunking visualization, batch testing, quality metrics, and one-click export to LangChain/LlamaIndex. Maintained by rasinmuhammed on GitHub, where it has earned 21 stars from the community.

@rasinmuhammed4mo ago

Chat with an LLM. Maintained by ariya on GitHub, where it has earned 20 stars from the community.

A self-hosted knowledge broker for homelabs. Routes and fuses queries across Kiwix, FreshRSS, Open-Meteo, SearXNG, Uptime Kuma, and Home Assistant — and tracks what changed over time. REST API and MCP server, integrates natively with Open WebUI and Home Assistant. Maintained by immortalbob on GitHub, where it has earned 20 stars from the community.

@immortalbob3mo ago

Agent OS in Rust — one binary, 37 agents, 26 LLM providers, 37 channels (Telegram/Discord/Slack...), MCP server, A2A protocol, 120+ API endpoints, web dashboard. Maintained by ginkida on GitHub, where it has earned 20 stars from the community.

Self-hosted autonomous AI agent for Linux — multi-LLM, real desktop control (VNC), WhatsApp, RAG knowledge base, sandboxed security layer, OpenClaw skills. Maintained by dev-core-busy on GitHub, where it has earned 20 stars from the community.

@dev-core-busy8w ago

A command line tool for journaling daily accomplishments and summarizing them to create a bragging document. Maintained by bovem on GitHub, where it has earned 20 stars from the community.

Rag (Retreival Augmented Generation) Python solution with LLama3, LangChain, Ollama and ChromaDB in a Flask API based solution. Maintained by OmJavia on GitHub, where it has earned 20 stars from the community.

Embedded long-term memory database for AI agents & LLM apps. Six-layer cognitive architecture, knowledge graph, hybrid BM25 + vector search, sleep-time memory consolidation. One.meh file, zero infrastructure, pure Go. Maintained by qyiun666 on GitHub, where it has earned 20 stars from the community.

@qyiun6668w ago

LLM proxy with built-in DLP and regulatory compliance. Redacts secrets before they reach the API. EU AI Act, GDPR, HDS/PCI DSS ready. Multi-provider failover, live TUI, virtual keys, fan-out. 6 MB, zero deps. Rust. Maintained by azerozero on GitHub, where it has earned 20 stars from the community.

@azerozero2mo ago

Das Bloomberg Terminal für r/wallstreetbetsGER. Maintained by bsommerfeld on GitHub, where it has earned 20 stars from the community.

@bsommerfeld2mo ago

Self-extending AI agent system running on local Ollama - creates its own capabilities autonomously. Maintained by ArneJanning on GitHub, where it has earned 20 stars from the community.

@ArneJanning11mo ago

Ollama Optivus is a video processing AI that extracts meaningful insights from videos using AI technologies like YOLO for object detection, EasyOCR for text extraction, and Whisper for speech-to-text. Integrated with Ollama LLM, it provides detailed summaries and event analysis, supporting various advanced AI model prompting. Maintained by TarikSeyceri on GitHub, where it has earned 20 stars from the community.

@TarikSeyceri5mo ago

Real-time global intelligence dashboard 54-country CII, AI Agent (Ollama/Groq/OpenRouter), 35+ data layers, Tauri desktop (Win/macOS/Linux). Maintained by sjkncs on GitHub, where it has earned 20 stars from the community.

Universal Unity games automatic local AI translation and communtity sharing and improvments. Maintained by djethino on GitHub, where it has earned 20 stars from the community.

@djethino8w ago

A Markdown editor powered by your LLM. Like GitHub Copilot, but local and free. Maintained by szilarddoro on GitHub, where it has earned 20 stars from the community.

@szilarddoro7mo ago

A real-time, offline voice assistant for Linux and Raspberry Pi. Uses local LLMs (via Ollama), speech-to-text (Vosk), and text-to-speech (Piper) for fast, wake-free voice interaction. No cloud. No APIs. Just Python, a mic, and your voice. Maintained by m15-ai on GitHub, where it has earned 20 stars from the community.

Chat with PDF locally: An advanced chatbot using Ollama / Sambanova LLMs to interactively extract information from PDFs, Using Streamlit & Ollama / Sambanova API and langchain. Maintained by drisskhattabi6 on GitHub, where it has earned 20 stars from the community.

@drisskhattabi61y ago

Run multiple open source large language models concurrently powered by Ollama. Maintained by ahmetkca on GitHub, where it has earned 20 stars from the community.

@ahmetkca2y ago

Advanced AI functionalities, including tool usage, context aware similarity with Ollama models. Maintained by bigsk1 on GitHub, where it has earned 20 stars from the community.

A Material You themed JVM based agentic browser made in JCEF (Java Chromium Embedded Framework), Swing, and JavaFX. Maintained by ingStudiosOfficial on GitHub, where it has earned 20 stars from the community.

@ingStudiosOfficial8w ago

This project demonstrates function-calling with Python and Ollama, utilizing the Africa's Talking API to send airtime and messages to phone numbers using natural language prompts. Ollama + LLM w/ functions + Natural language = User Interface for non-coders. Maintained by Shuyib on GitHub, where it has earned 20 stars from the community.

Autonomous multi-agent coding system on local LLMs. No frameworks, no API costs. Plan → Build → Test → Fix with Qwen 80B + 7B on your own GPUs. Maintained by TenchiNeko on GitHub, where it has earned 20 stars from the community.

@TenchiNeko8mo ago

Free & Open Source AI Agent — Self-Hosted, Self-Learning, No Vendor API. Qwen2.5-7B + LoRA. 35 tools. Built on Islamic Epistemology (IHOS). Maintained by fahmiwol on GitHub, where it has earned 20 stars from the community.

@fahmiwol3mo ago

Spring AI framework for Java that plans, executes, and improves itself — agents detect capability gaps at runtime and generate validated skills on the fly. Maintained by intelliswarm-ai on GitHub, where it has earned 20 stars from the community.

@intelliswarm-ai3mo ago

AI-powered CLI for file reorganization. Runs fully locally — no data leaves your machine. Maintained by PerminovEugene on GitHub, where it has earned 20 stars from the community.

@PerminovEugene1y ago

PowerShell script simulates a team of AI Agents working together on a user provided PowerShell project. It utilizes Retrieval-Augmented Generation (RAG). The project leverages Azure OpenAI, Ollama, and LM Studio. Maintained by voytas75 on GitHub, where it has earned 20 stars from the community.

@voytas756mo ago

Examples of how to monitor the OpenAI SDK calls using Langfuse. Maintained by ErickWendel on GitHub, where it has earned 20 stars from the community.

@ErickWendel1y ago

A simple yet fast mind map editor written in C++. You can also call LLM to get some inspiration (if you run LLM locally with Ollama). Maintained by azula1A89 on GitHub, where it has earned 20 stars from the community.

@azula1A8910mo ago

A CLI utility for working with and moving the Ollama cache. Maintained by sealad886 on GitHub, where it has earned 20 stars from the community.

@sealad8861y ago

A project worth exploring. Maintained by bopalvelut-prog on GitHub, where it has earned 20 stars from the community.

@bopalvelut-prog6mo ago

A Go CLI tool to benchmark local LLMs via Ollama, measuring Time To First Token (TTFT) and throughput on your specific hardware. Maintained by rohanelukurthy on GitHub, where it has earned 20 stars from the community.

@rohanelukurthy7mo ago

Local-first knowledge graph for developers. Watches your files, builds a knowledge graph with LLMs, lets you query across projects. Maintained by gzoonet on GitHub, where it has earned 20 stars from the community.

@gzoonet2mo ago

Docker-based multi-agent AI team. One config file. Unlimited agents. Always on. Maintained by Mone-Industries on GitHub, where it has earned 20 stars from the community.

@Mone-Industries7mo ago

A demonstration of integrating FastAPI with Ollama, featuring streaming, formatted, and complete JSON responses from AI models. Learn how to set up and use FastAPI with Ollama for building AI-driven applications. Maintained by darcyg32 on GitHub, where it has earned 20 stars from the community.

@darcyg322y ago

llama3,finetune,Meta-llama3。. Maintained by user-wu on GitHub, where it has earned 20 stars from the community.

Community-driven benchmark suite for MLX inference engines on Apple Silicon. Maintained by igurss on GitHub, where it has earned 20 stars from the community.

This repository features a Next.js (React 19) frontend and FastAPI backend, integrating Ollama and DeepSeek-R1 for AI-driven functionality. Designed for efficiency and scalability, it supports real-time updates through event streaming, enabling high-performance AI interactions. Maintained by rabbicse on GitHub, where it has earned 20 stars from the community.

@rabbicse12mo ago

Your AI company, in your device. Local-first AI platform: chat, agent crew, memory, and a model store sized to your hardware - from 4GB laptops to big GPUs. One-click setup, fully private. Maintained by Yashwanth-pilli on GitHub, where it has earned 20 stars from the community.

@Yashwanth-pilli3mo ago

Production-grade RAG toolkit - ingest PDFs, DOCX, XLSX into Qdrant with LLM metadata extraction, hybrid search, and SHA256 deduplication. Maintained by laxmimerit on GitHub, where it has earned 20 stars from the community.

@laxmimerit2mo ago

From the blog

Latest Ollama guides & deep-dives

All articles →

OllamaTutorialOllama + Fastify — On‑Prem LLM API Stack Guide

A practical stack guide showing how to combine Ollama (local/model runtime) with Fastify (Node.js API) to run an on‑prem inference API. Includes architecture, flow, deployment topology, observability, security boundaries, and a staged rollout plan.

MMadeWithWhat Editorial Team · Jul 24, 2026 · 12 min

LlamaIndexGuideLlamaIndex vs Ollama: choosing for LLM projects

A practical comparison between LlamaIndex (a Python data/agent framework) and Ollama (a local/model runtime and manager). Includes decision matrices, workload fit, migration notes, and recommended pairings for four project types.

AAndrea Lunelio · Jul 8, 2026 · 15 min

Video archive

Ollama talks, tutorials & deep-dives

Run Your Own Agentic AI? Full Ollama Setup + Hermes Workflow

Run Your Own Agentic AI? Full Ollama Setup + Hermes Workflow

WWanderloots · 224K views · Jun 25, 2026

Hermes Agent + Ollama = 100% Private OS

Hermes Agent + Ollama = 100% Private OS

JJack Roberts · 204K views · Jun 5, 2026

FREE UNLIMITED Claude Code (No NVIDIA NIM, No Ollama!) - Fastest Responses [2026]

FREE UNLIMITED Claude Code (No NVIDIA NIM, No Ollama!) - Fastest Responses [2026]

DDanish Sofi · 164K views · May 10, 2026