local-llm
Projects tagged with local-llm on GitHub.
80 projects
local-llm
ShellEverything I know about running LLMs locally
gemma-chat
TypeScriptLocal AI chat + coding agent for Apple Silicon, powered by Gemma 4 via MLX / Supports Ollama
deltafin
RustRun full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.
vomit
GoClean up Claude's token vomit with a separate LLM. Save your tokens, Opus is hopeless
LocalAI
GoLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
CarWatch
PythonYour car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.
ollama
GoGet up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
jarvis
ShellJarvis meta-repository: shared docs, configs, and setup scripts
MTPLX
Python3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.
Lexicon
JavaScriptThe free open source offline writing assistant assist with grammar, rewriting & tone entirely on your machine.
SiliconScope
SwiftSudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking
llm-space
TypeScriptA desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.
unsloth
PythonLocal UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
deja-vu
GoSearch your past AI coding sessions — Claude Code, Codex, Cursor and 17 more. Indexes the session history they already wrote to disk, including months from before you installed it, and recalls it in any of them. No LLM, no embeddings, one local Go binary.
bindwidth
JavaScriptEvidence-aware on-prem LLM inference sizing and TCO calculator
agentacct
PythonSee what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.
Soup
PythonFine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
mdflux
PythonTurn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.
MLX-LoRA-Studio
SwiftA native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.
macos-harness
PythonThe simplest, thinnest harness that gives an LLM complete freedom to control a Mac.
waku-agent
PythonWaku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.
kimodo.cpp
C++Animate skeletons with natural language; NVIDIA's Kimodo ported to C++/GGML
nativ
SwiftLocal AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.
writer-computer
TypeScriptLocal-first desktop markdown editor
agenttrail
HTMLLocal observability map for AI coding agents. Watch Claude Code, Codex, and Cursor plans, tool calls, file changes, and progress in real time.
kiac
GoLocal Kubernetes on Apple's container framework - every node is its own lightweight VM. Metrics, storage, and LoadBalancer included.
outreachr
TypeScriptLocal-first, open-source investor fundraising CRM for founders
app-monitor
SwiftLocal-first macOS app usage, storage, cleanup, update, and uninstall monitor.
Pythia
TypeScriptOne local API call gives your agent the entire live state of the planet — every major world event at once, plus forecasts. 40+ free keyless feeds, runs entirely on Ollama. No cloud, no cost. Keyless live feeds into one global view and forecasts what’s likely next. No cloud, no keys, no cost. 1d,1w,1m,1y predictions by Mirofish.
sloptrim
PythonA local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.
Token-Saver
PythonA local Claude Desktop extension to query large PDFs with 92–98% fewer tokens. Performs local hybrid search, cites exact page numbers, and keeps your documents private on your machine
gorest-2d-animation-spritesheet-generator
TypeScriptCodex-assisted local 2D animation spritesheet generator and scene compositing workspace.
da-cli
PythonSync DeviantArt galleries to local folders — zero-dependency Python CLI with OAuth 2.1 PKCE, a SQLite index, and scheduled macOS syncs.
ds4
CDeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
maka
TypeScriptApache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorded as an append-only log.
junction
TypeScriptVS Code chat sidebar for local AI coding agents
frp
GoA fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
viseron
PythonSelf-hosted, local only NVR and AI Computer Vision software. With features such as object detection, motion detection, face recognition and more, it gives you the power to keep an eye on your home, office or any other place you want to monitor.
open-science
TypeScriptOpen Science is an open-source, local-first, model-agnostic AI research workbench for reproducible scientific research on macOS, Windows, and Linux.
OpenChatCut
TypeScriptOpen-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.
qwen-scribe
PythonPrivate, local transcription and system-wide dictation for Apple Silicon.
ownmem
JavaScriptOpen-source, Git-native memory for AI coding agents — deterministic local recall for Claude Code, Codex, Cursor, Gemini CLI, and compatible tools.
Alexandrie
Vue📚 The open-source, offline-first Notion, Obsidian & Confluence alternative. Advanced Markdown, multi-tenant teams, OIDC/SSO, and local S3 backups. Deploy in one command.
world-model-optimizer
PythonAn open source model gateway that provides one control plane across closed, open-source, local, and custom models.
understory
TypeScriptunderstory — memory that grows. Self-wiring, plain-markdown memory for AI agents (MCP + local models + a living graph).
vibepulse
CESP32-S3 AMOLED for Claude Code & Codex usage, live agent activity, and answerable NEEDS YOU alerts. Local-first macOS/Windows host; optional encrypted relays.
jit
GoFind the plaintext secrets on your Mac and move them behind Touch ID, injected just in time without breaking the tools that read them. Free and local-first.
burrow
TypeScripta whole dev machine in a browser tab - bun.wasm, shell, git, and local AI. phones home to nobody.