Framework
Ollama agents
399 Ollama AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
399 agents · ranked by popularity · refine in the directory →
Top 100 Ollama agents
ATENA - Enterprise AI Agent Orchestration System
Local-first AI agent for Windows/WSL/Linux. Autonomous tool chaining across 14+ providers, offline via Ollama.
Ollama embedding provider and OllamaRag convenience class for @mcp-abap-adt/llm-agent.
The local-first autonomous coding agent. Claude Code UX powered by Ollama. Zero cost, maximum privacy, fully offline.
Context-aware project scaffolding for AI coding agents (Claude Code + Ollama).
Synapse - A Multi Agent Orchestrator
Intelligent CLI tool with AI-powered model selection that analyzes your hardware and recommends optimal LLM models for your system
Bandit — a local-first AI coding agent for your terminal. Same runtime as the Bandit Stealth VS Code / Cursor extension.
Open-source agent orchestration layer — the AI company OS. Local model agent engine (GGUF/Ollama/llama-server), HuggingFace model browser, MCP integrations (Slack, Gmail, Stripe, 15+), agent scheduling (cron), business roles (CMO, CFO, EA). GUI dashboard,
minimal local-first coding agent focused on small local models
AI-powered game development CLI with local LLM, 45+ tools, autonomous agent mode, and 50+ slash commands
뇽죵이 에이전트 — AI-native autonomous agent server with MCP protocol, Obsidian memory, multi-model support, and dynamic persona system
Must-b v1.74.37 — UX & CONNECTIVITY OVERHAUL: Resolve OpenRouter 405 error, implement dependent dropdown selects for traditional brokers, design robust multi-account state structures, and harden Ollama & Binance connections.
A local-first agentic system wrapping Ollama's API, borrowing architectural patterns from the Claude Code paper
AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop
Free Agent MCP - Portable, workspace-agnostic code generation using FREE models (Ollama)
Autonomous Minecraft agent powered by Featherless AI or Ollama
Local AI agent with vision, VLA, MCP, Discord bridge, and cross-platform CLI
🪼 AI-powered CLI assistant for terminal productivity
AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop
CLI swarm agent developer tool with multi-agent orchestration
JishuShell - Multi-Agent Framework Management
Multi-agent orchestration system for pi-coding-agent with subagents, web search, and URL fetching
Local AI coding agent — LM Studio / Ollama / MLX, terminal UI, RAG, multi-agent
Open-source multi-agent coding tool for your terminal. Powered by Ollama.
The composable AI agent framework built on Effect-TS — install everything with one package
Maiar: A Composable, Plugin-Based AI Agent Framework
Yuva AI - Development agent framework with 12 agents, 20 LLM platforms, on-demand prompts, and auto-detection
A Python package for estimating sample thickness in cryo electron tomograms
Ollama tamil helps you to build ollama api but with tamil interface
Python client for the Ollama API
Python client library for function calling interactions with Ollama REST API
A package to download arXiv papers and interact with PDFs using Ollama LLM
Ollama backend adapter for the AccuralAI LLM orchestration pipeline.
Docker-like CLI for AI agents with Enhanced LLM Intelligence
Ollama integration for Microsoft Agent Framework.
🛡️ Lightweight Agent Guardrails - Make small local LLMs reliable for production agent workflows
Ultra-lightweight personal AI agent — shell, files, web, memory — powered by local or cloud LLMs
Ollama local LLM + embedding provider for AgentForge — llama / mistral / qwen / mxbai-embed on localhost
An agentic concierge that spawns ephemeral specialist teams to tackle tasks — capability-based routing, multi-pack task forces, and native tool-calling on local or cloud LLM endpoints.
LLM-powered file organizer that safely moves files into categories
AI-powered resume builder using Strands Agents and Ollama
⚛️ AgentNova - A minimal, hackable agentic framework for local LLM inference
Trust-restricting inheritance and runtime resolver for AI agent manifests. Multi-runtime: Claude, Gemini, Codex, Ollama, and more. (Import as `agentspec`.)
Airflow operator for managing Ollama and ngrok
A lightweight, extensible Python framework for building stateful AI agents with tool use, backed by local or remote LLMs.
ARIA — Autonomous Reasoning and Intelligent Agent. Your project-aware coding partner.
General-purpose open-source RAG engine with multi-LLM, hybrid retrieval, GraphRAG, and MCP support
MCP executor for Claude Code or Codex that offloads repetitive coding work to cheaper local or flat-rate models.
Persistent memory for LLM coding agents — local-first, model-agnostic, SQLite-backed
A python module
Simple yet effective command line client for chatting with big LLMs using the llm_lite wrapper or ollama models
A python module for conversational AI with ollama
A visual node-based programming system for creating and managing agent-based workflows.
OCR-first chess screenshot analyzer with optional Ollama fallback
Chroma MCP server with Ollama embedding configuration
Local backend bridge for Claude Code, Codex, and Pi.
Automatic, cheap, precise query of Claude Code session archives via SQLite FTS5 + hooks.
A minimal, typed Python interface for Ollama that simplifies the existing ollama library
Run ollama on Google Collab or Kaggle
Windows support for copilot-ollama
Local LLM Council powered by Ollama
curllm - Intelligent browser automation with local LLMs (Qwen, Llama, Mistral) for data extraction and form automation using a dynamic LLM-DSL architecture without hardcoded selectors.
Datasette enrichment for analyzing row data using a locally hosted - or remote - ollama instance
A simple script that uses the Ollama API to get the Markdown text from a PDF or image file using the DeepSeek-OCR model
A CLI tool to deploy and manage LLMs using Ollama.
A local autonomous coding agent CLI powered by Ollama.
Functions to parse Ollama options from string and get info on Ollama options.
Docling → Chroma → Ollama: Simple RAG pipeline
generate python docstrings using ollama
State-of-the-art AGI powered by NVIDIA NIM + Moonshot Kimi 2.5 — control your PC via Telegram, voice, or code. 100+ frontier models.
一个用于调用Ollama模型的Python工具包
elizaOS Ollama Plugin - Local LLM client for text and object generation
A plugin for Enthusiast that provides an Ollama connector.
A professional Python library for Ollama integration with support for multiple data sources
A lightweight Python wrapper for Ollama AI models.
Find the best local AI model for your GPU — terminal UI
Local-first AI agent framework. Built for models that aren't perfect.
AG2 agent development kit using Ollama and Firecrawl scraping.
Genie Flow Invoker Ollama
Genkit Ollama Plugin (Community)
An integration package connecting Ollama and GigaChain
AI-powered git automation tool - clone, branch, change, commit, push with intelligence
An open-source, high-transparency modular RAG framework for AI/ML applications
Django implementation for golink
Simple, reproducible red teaming pipeline for GPT-OSS via Ollama with DeepSeek-based prompt generation
基于微软GraphRAG,支持使用百度千帆、阿里通义、Ollama、字节豆包等大模型服务
The latest graphrag interface is used, using the local ollama to provide the LLM interface
A command-line interface for interacting with Ollama AI models
HAON PowerHub — miner agent: rent out idle GPU time on a decentralized compute marketplace.
Download a HuggingFace model and convert it to GGUF for Ollama.
Local LLM inference + embedding & search in one package. Run 30B on consumer hardware, RAG without ChromaDB.
Modular agentic framework - hybrid LLM (Ollama + Azure AI Foundry + GitHub Copilot) with privacy filters
MCP server for running Ollama models with async support
A Voice-Controlled Drone Agent MCP Server
A Model Control Protocol server that allows Claude Desktop to communicate with Ollama LLM server
IPython magics for running Ollama models within the shell
Tools to interact with LLM models hosted on Ollama.
Run LLMs locally. One command.