Ollama agents

Find the breaking point of your local LLM hardware.

Add your description here

Chain small language models to outperform large ones — runs locally on 8GB RAM

Distributed Parallel AI Agent Orchestration with Intelligent Load Balancing - integrates with FlockParser for RAG and SOLLOL for distributed inference

RAG library

TAPM v2 hook for ollama (migrated to tapm.hook.ollama namespace)

OpenTelemetry Ollama instrumentation

A bridge that allows Ollama to join Telegram chats as a bot

CLI for Productive.io time tracking with calendar sync, team hours review, and local LLM support

AI-powered Python code generation tool - creates containerized Python applications from TODO.md descriptions

OpenTelemetry instrumentation for Ollama - local LLM runner

Multilingual Parallel Translation Platform with Reflection-based Improvement using Local LLMs

Modular GGUF patching tool for Ollama multimodal monoliths

Complete RAG with built-in Ollama + FastAPI + Swagger - Zero Config!

Universal Document Agent for extracting and analyzing various documents with Ollama support.

RAG tool with local FAISS and remote S3 Vectors backends, using Ollama embeddings

Ollama-style daemon and CLI over vllm-mlx on Apple Silicon

A lightweight client for local LLM APIs like Ollama or OpenWebUI

Semantic code search tool for local repositories using ChromaDB and Ollama embeddings

Youtube Autonomous Docker Ollama Module

Youtube Autonomous FastAPI Docker Ollama Module

Python SDK for zag — a unified CLI for AI coding agents

基于 ZIM 文件和本地大模型的 RAG 知识库问答系统

Terminal-native autonomous coding agent powered by free AI models

Local AI coding agent — Ollama + any model

Ollama-based embedding + retrieval pipeline backed by skeg.

Offline Expert Agent — local RAG, agent mode, plugins, privacy-first

Purpose-scoped ADK agents for SDC4 data operations — SMB Edition (local LLM via Ollama)

Ollama AI agent provider for VibeControls Agent (CLI + SDK, Cloud + self-hosted)

Terminal-native local AI assistant — offline, GPU-accelerated, agentic. Runs any GGUF model locally with full tool use.

Ollama

A local-first CLI coding agent that brings the power of agentic coding tools like Claude Code and Gemini CLI to local models or controlled APIs like OpenRouter

Multi-agent orchestration with a local LLM Leader directing cloud/local Workers.

Proactive cognitive AI assistant — learns your interests, pushes insights, evolves skills autonomously

Multi-agent AI assistant with local LLM inference

Multi-LLM orchestration framework with agentic execution, memory/RAG, and training data generation

A control layer for LLM-in-the-loop reliability: wrap an unreliable generator in a verify-and-refuse feedback loop with a pluggable controller (deterministic checks, a model critic, or compositions) and composable 'circuits'. Keep one exact element in the loop and outputs are checked, corrected, or honestly refused. Zero runtime dependencies; runs with no model at all.

Production helpers for running Ollama under concurrent load across local and remote endpoints.

AI Infrastructure OS — same engine, four facades (CLI, REST, web, MCP). Reduce 80-95% of AI spend by routing tasks to the right model.

Python bindings for newt-agent — agentic coder runtime (newt-core, newt-tools, newt-coder, newt-eval, newt-inference, newt-acp-worker, newt-mcp-server submodules)

Minimal Ollama agent executor runtime

Transparent context reduction for LLMs

Python routing library for local LLM agent loops: score prompts, map tiers to model names, embed in your runner.

htop for AI agents — liveness, CPU/mem/GPU usage, and a kill switch for headless agents (openclaw, hermes, ollama, vllm, claude-code).

AIAR — local retrieval-augmented generation with LLM-judge grounding loop

Search and filter Ollama models by size, context, input type and more.

Splash — Autonomous Agent Platform: CLI + multi-provider agent loop + TUI dashboard + platform bots

An Anytype-native LLM wiki combining Karpathy's pattern with Anytype's typed knowledge graph (Objects, Types, Relations).

Core reasoning and planning engine for Bandit Agent Framework.

Provider integration adapters for Bandit Agent Framework.

Node.js adapter for the Bandit Agent Framework.

UI primitives for the Bandit Agent Framework.

GitHub Actions adapter for the Bandit Agent Framework.

A framework-free agent runtime you can read, run, and leave. Own the loop, not the framework. Runs local on Ollama at $0 — or any frontier model.

Lightweight local AI coding agent — zero external dependencies, single process startup, with intelligent model routing (Claude > Qwen > Ollama).

Respan instrumentation plugin for Ollama

VS Code adapter for the Bandit Agent Framework.

Web adapter for the Bandit Agent Framework.

Doraemon Cyber Team — Multi-server Ollama agent

The embeddable woollama model-management core (Rust) — start of the v1.0 port.

own your fleet — connect any device, dispatch real work. Part of Own Your Stack.

Local Ollama text-generation skill for NeuroCore

Terminal-based AI assistant powered by local Ollama with Exa search and Robinhood tools

MCP stdio server exposing Ollama's hosted web search and web fetch APIs as tools for any MCP client.

Run Claude Code (and other LLM CLIs) inside a Docker sandbox, against a switchable local or remote LLM endpoint.

Pair-wise ELO evaluation arena for local LLMs.

A desktop GUI application for text classification using LLMs (Ollama, vLLM, SGLang, llama.cpp)

Local AI compute control plane for Claude Code and coding agents. Route subagents across your Macs, GPUs, and Ollama nodes — with real-time fleet health, role-based routing, model warmup, and execution tracing.

First-Class Hermes Tool Agent — Offline ReAct agent with dual memory (episodic + semantic), skill learning, and daemon mode

High-performance terminal UI for planning and running agentic coding workflows

Multi-agent repo boilerplate generator — scaffolds conventions, repo-namespaced skills, settings, and hooks for Claude Code, Gemini CLI, Cursor, Codex, Copilot, Google Antigravity, Cline, Aider (Ollama), opencode, and Kimi Code CLI

Multi-agent orchestrator for OpenCode. Provider-agnostic — uses whatever model is configured per agent. Automatic mission mode with per-project plan/todo scoping.

QUANT CLI 3.0 — Local AI Coding Agent with streaming, 12 tools, 6 modes

Find the best LLMs for your hardware specs

Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),

Local-first AI coding CLI with embedded model router, multi-agent orchestration, and codebase indexing

Local-first Goal Loop OS for long-term AI work across terminal, web, desktop, mobile app, and messengers.

Local-first LLM router: keep sensitive data and bulk text labor on your own models, call the cloud only for the hard part. Privacy-routing (fail-closed) + manager-worker delegation + allowlist guard, MCP-native.

Local-first, multi-agent AI security scanner. Finds vulnerabilities. Writes the patches. Free forever.

Host-agnostic building blocks for the Bandit agent framework — memory files, hooks, mentions, and the extra tool set (todo_write, web_fetch).

基于 Ollama + RAG 的智能问答系统

An MCP server that offloads cheap work from your cloud LLM agent to a local Ollama model.

Simple ollama ai agent base for allowing a ai to run python functions

Tool-use agent with optional LLM brain via Ollama. Pure Python stdlib.

Terminal benchmark runner with automatic discovery of local LLM servers

OBLIVION - Terminal AI coding agent with voice, RAG, and multi-model support. Powered by Meera.

Reference TickTick adapter for Agentic Task System. Wraps TickTick OpenAPI v1 + qdrant + ollama (nomic-embed) into the ATS adapter contract.

Privacy-first, SQLite-first observability for local Ollama agents.

Local AI coding agent for your terminal — an open-source, offline alternative to Claude Code, Cursor, and GitHub Copilot, powered by Ollama. Private by default, free forever.

Framework-agnostic multi-agent scaffold for Claude Code — install once, run cls init on any project

Drop-in open-source agent SDK. Multi-model, streaming, MCP, sub-agents.

Yumi — open-source self-hosted AI agent framework: cross-language tool edges + Telegram/LINE/Discord chat

Autonomous AI agent orchestrator — Claude, GPT, Codex, and local models (Ollama/LMStudio/llama.cpp)

Document conversion agent that watches folders, converts files with marker-pdf, and routes Markdown outputs.

htop for Ollama — curses-based TUI monitor for models, GPU, and Docker containers

Ollama Target adapter for Waken — routes waken Events to a local/self-hosted Ollama daemon.

Local-first LLM instance framework: deploy, specialize, and chat with grounded, cited model instances.

Claw coder is a local first AI agent that turns local coding small LLMs into powerful AI agents that actually work

Multi-LLM MCP server for Claude Code & Codex — route AI agent work across 20+ low-cost provider buckets with round-robin dispatch and quota-aware fallback.

Agent-Nuvira: Multi-agent AI coding CLI — plan, write, review, test, and publish code with local models (Ollama) or cloud APIs (Groq, NVIDIA NIM, Google Gemini, OpenRouter)