ollama

Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.

A local-first agent harness for running 2–9B models on laptops with Ollama. The project focuses on finishing real tasks, includes an offline mode, benchmarks, and a large public test suite.

Hillnote is a local-first writing workspace for notes, documents, databases, and plans, with AI features that run on-device and optional cloud models. It supports markdown files on disk, sync across devices, and direct use by agents through MCP and CLI access.

A minimalist, terminal-native coding agent written in C. It runs as a single native binary, supports local models through llama.cpp and Ollama, and can also connect to OpenAI, Anthropic, OpenRouter, and Codex.

A drop-in proxy for Ollama that automatically tunes local LLM requests to reduce RAM use and speed up first-token latency. The page shows install steps, benchmark results, a live dashboard, and a local-only admin UI.

Local-first AI memory layer for LLM apps with persistent knowledge graph storage, entity extraction, semantic retrieval, and API endpoints for ingesting and retrieving context.

An open-source, local-first canvas for editing LLM context as a graph. It lets users branch, prune, merge, and inspect the exact context sent to a model, with a desktop app, web demo, and support for Ollama and OpenAI-compatible endpoints.

Self-hosted multi-tenant AI agent platform built on Claude Code and Codex, with a dashboard, sandboxed execution, shared/personal workspaces, scheduling, webhooks, and support for API keys and local models.

SmolSignal is an AI signal copilot for Flipper Zero files. It explains common capture formats, classifies safety risk, supports local and cloud model backends, and can generate safe consumer IR files.

Open-source Python framework for building multi-agent LLM apps that can run on local models through Ollama or on hosted APIs like OpenAI, Anthropic, and OpenRouter. The repo highlights built-in plugins, workflow orchestration, agent serving over HTTP, and guardrails for tool use.

A hands-on kit for authorized red teaming of locally run LLMs, with jailbreak techniques, prompt-injection scenarios, streaming attack visualization, and support for OpenAI-compatible local model servers.

AI-powered code review tool that analyzes git diffs and produces structured review reports, with support for GitHub Action workflows and multiple model providers.

A local-first macOS desktop app for tracking manga and book libraries and turning chapters into narrated recap videos using local vision models, TTS, and swappable video backends.

A lightweight CLI for running RAG over local documents, with hybrid vector + BM25 retrieval, OCR for scans and images, and support for local or API-based LLMs.

Open-source local AI coworker system that routes Claude Code and Codex work to local models on your own hardware, with durable task handling, multi-machine cooking, and MCP/CLI support.

Local-first private planning and decision workspace that turns messy documents into structured plans, grounded outputs, and traceable decisions with citations and audit trails.

A lightweight Flask-based LLM proxy that forwards Ollama, OpenAI, and llama.cpp-style requests to NVIDIA’s OpenAI-compatible API, with streaming support, retries, caching, auth, and usage stats.

An open-source CLI for inspecting live LLM inference processes on NVIDIA GPUs. It breaks down VRAM usage by component, shows runtime and model details, and projects memory savings from quantization strategies.

A framework-free Unix-style AI agent stack built from small shell commands. It uses bash, curl, and jq to run a REPL-like agent loop with append-only JSONL history, tool dispatch, and piping-friendly components.

A local-first AI memory engine for asking questions over selected files on your computer using Ollama, embeddings, and a custom vector database.

Open-sourced local multi-agent OS that runs three agents on consumer hardware, lets them form goals from environmental pressure, and supports self-modifying workflows through tool creation and change requests.

Open-source LLM routing and cascade engine that sends prompts from local Ollama models to cloud and frontier models based on task complexity, cache hits, and quality gates.

A text-first, hands-on guide to agentic AI for practicing engineers, with runnable local-first code samples and a module-based structure covering LLM basics, tool calling, RAG, memory, multi-agent patterns, evaluation, safety, and enterprise topics.

A local coding-agent setup that turns Ollama models into a private, verified team of specialist agents for coding workflows. It includes hardware-aware model selection, role assignment, permission-restricted workflows, and validation probes.