Run LLMs locally in Node.js with an OpenAI-compatible API
Local-LLM-first agentic coding assistant
Local LLM provider plugin for Antseed
Local LLM routing server with OpenAI compatibility
Ollama adapter for TanStack AI local LLM chat, tool calling, and structured outputs.
Multi-agent AI assistant with local LLM inference
Universal local LLM lifecycle CLI
OpenClaw plugin for UncommonRoute, the local LLM router that cuts premium-model spend
TUI for managing local LLM inference with llama.cpp
Core inference backend — llamafile wrapper for local LLM inference
Four-layer local memory system plugin for OpenClaw — auto-captures, structures, and profiles conversational knowledge using local LLM + SQLite vector search (L0→L1→L2→L3 pipeline)
Standardized local LLM inference benchmarks.
Self-hosted code-hygiene engine for TypeScript / JavaScript codebases. Deterministic detectors + local LLM verdicts + dashboard.
Pi package for frontier-designed, local-LLM implementation loops with frontier final gates.
Polls GoNext cloud API for async local LLM jobs and runs them against Ollama/OpenAI-compatible servers on this Mac
Clipal CLI installer for the local LLM API gateway
Shared core runtime and native contract for local-llm packages
Clipal CLI installer for the local LLM API gateway
Cloud and local LLM provider discovery and management
SharkCraft local LLM provider abstraction: Ollama (HTTP) + llama.cpp (in-process) + multi-pass enhancement pipeline.
AI coding agent powered by local LLM via Onde Inference.
Ollama engine adapter for auggy — local LLM runner, no API key required.
Local LLM integrator for OpenClaw — localhost UI, model proxying, and defense-in-depth security.
Local policy-enforcing proxy for AI agents — sandboxes local LLM file access with Undisk's policy engine
Orchestrate a swarm of Claude Code agents with a local-LLM brain that learns from you.
A dead-simple Ollama wrapper – auto-installs Ollama & models, then lets you prompt in two lines of code.
Privacy-first, air-gapped AI coding agent and personal assistant that drives one local model (LM Studio or Ollama). Single-binary Rust CLI + TUI.
Senior SysAdmin, Network Admin, Data Analyst, and Software Engineer living in your terminal. A high-precision local AI agent harness for LM Studio, Ollama, and other local OpenAI-compatible runtimes that runs 100% on your own silicon. Reads repos, edits files, runs builds, inspects full network state and workstation telemetry, and runs real Python/JS for data analysis.
Ollama local model provider for neuron-turn
Ollama local model provider for skg-turn
An open-source local-LLM terminal coding agent (Ollama / llama.cpp / LM Studio / vLLM).
Local-LLM token-saving router for Claude Code (vinitokx)
A calm Twitter/X CLI with a local-LLM rage filter
Ghost Librarian — ultra-lightweight local-LLM RAG engine with Context Distillation
[experimental] Lightweight Smart ToolAgent for code investigation
Layer 3 reasoning — plan/output parsers + provider-agnostic local-inference scorers (router, complexity, relevance, retrieval, strategy, summariser, validator, entity enhancer) for the Brainwires Agent Framework
local_llm is a lightweight Ruby gem that lets you interact with locally installed Ollama LLMs such as LLaMA, Mistral, CodeLLaMA, Qwen, and more. It supports configurable default models, configurable Ollama API endpoints, real-time streaming or non-streaming responses, and both one-shot and multi-turn chat—while keeping all inference fully local, private, and offline.
Ruby bindings for Llama.cpp to run local LLMs in Ruby applications.
Create changes for a local repository with chatgpt / openai / local llm
Auto fix all rubocop warnings with chatgpt / openai / local llm
A RubyLLM plugin that enables local LLM execution using the Red Candle gem. Run quantized GGUF models directly in Ruby without external API calls. Supports streaming, structured output, and multiple model architectures including Gemma, Llama, Qwen, Mistral, and Phi.
A Ruby gem for interacting with Ollama's API that allows you to run open source AI LLMs (Large Language Models) locally.
Ruby gem for running state-of-the-art language models locally. Access LLMs, embeddings, rerankers, and NER models directly from Ruby using Rust-powered Candle with Metal/CUDA acceleration.
Connects LegionIO to Ollama local LLM server
zen-and-musashi is a Ruby CLI that gives local, structured terminal wisdom in two modes: calm Zen-style reflection and fierce Musashi-style critique. It works without an API key by default, and can optionally use an LLM when explicitly enabled.
LLM inference gateway: metering over RabbitMQ, fleet RPC dispatch, local disk spool
Connects LegionIO to Apple MLX local LLM server
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.