AI Dev Impact Lab JA
← Topics ranking · 2026-08
GITHUB TOPIC

#local-first

GitHub repositories that have self-applied the topic "local-first" — a creator-tagged metadata that surfaces how AI projects describe themselves.

178
tagged repos
92,761
top 40 stars
24
with tool sigs
40
shown

REPOS Repos for #local-first (top 40 by stars)

nexu-io/open-design

🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK.

TypeScript 88,193 AI 70 2 sig live ↗
Intuition-Lab/personal-model

Build your HUMAN.md.

Python 1,310 AI 45 2 sig live ↗
Javis603/token-monitor

Local-first desktop widget for tracking token usage, costs, and limits across 28+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, and OpenClaw—with multi-device sync.

JavaScript 1,119 AI 70 Solo 2 sig live ↗
mereyabdenbekuly-ctrl/clodex-ide

Local-first, zero-trust agentic IDE for verifiable autonomous software development.

TypeScript 862 AI 45 Solo 1 sig live ↗
myICOR/myPKA

AI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain markdown. Any LLM. Yours forever.

TypeScript 282 AI 70 2 sig live ↗
Patdolitse/piia-engram

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Python 157 AI 70 Solo live ↗
fancyboi999/open-tag

Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub Copilot, and more) work as teammates in channels, threads, DMs, and shared tasks. Your data stays on your machines.

TypeScript 149 AI 60 2 sig live ↗
EliasOulkadi/shokunin

職人 Shokunin 62 AI agent skills for OpenCode, Claude Code, Cursor, Windsurf. ChromaDB memory, MCP servers, declarative self-updates. Multi-model, open source, zero cost.

HTML 110 AI 70 Solo live ↗
tristan666666/agent-island

Open-source status companion for Claude Code and Codex on macOS and Windows. See live session state, get your-turn alerts, and download with no account or telemetry.

C# 92 AI 100 Solo 1 sig live ↗
ofekron/better-agent

Local web workspace for coding agents — Claude, Codex, Gemini, and more in one inspectable, LAN-ready hub.

Python 52 AI 100 Solo 2 sig live ↗
100yenadmin/Lossless-Codex-Orchestrator-LCO

Index, search, summarize, and approval-gate local Codex sessions through OpenClaw/MCP. Agent-first recall and dry-run orchestration for Codex-heavy work.

TypeScript 38 AI 100 1 sig
ddsyasas/llm-wiki

Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.

TypeScript 37 AI 100 Solo 1 sig live ↗
amajorai/ryu

The fully self-hostable, open composable platform for agent orchestration and human collaboration. With tools, security, memory, cost saving, and routing all built in.

Rust 35 AI 70 live ↗
Perseus-Computing-LLC/perseus

Live context engine for AI agents: resolve verified workspace state before the context window opens. Pairs with Perseus Vault for persistent encrypted memory. Local-first, MIT. pip install perseus-ctx

Python 35 AI 60 2 sig live ↗
oomkapwn/enquire-mcp

The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.

TypeScript 30 AI 70 Solo 2 sig live ↗
fru-dev3/prevail-desktop

Private, local-first AI "life OS": any model per life-domain over a markdown vault on your machine. Council mode, open source (GPL-3.0).

TypeScript 25 AI 100 Solo live ↗
EasyCode-Obsidian/Stone

Personal, local-first desktop AI gateway for Windows, macOS, and Linux. Connect Claude Code, Codex, and Gemini CLI to OpenAI, Anthropic, Gemini, and compatible providers with protocol conversion, model-aware routing, quota visibility, and OS-protected credentials.

TypeScript 21 AI 50 Solo live ↗
korovin-aa97/talkthrough-mcp

Don't write a bug report — record it. Local MCP: screen recording → transcript, frames, OCR, wall-clock evidence for coding agents.

Python 21 AI 45 2 sig
burakgon/roamcode

Self-hosted mission control for real Claude Code and Codex sessions — persistent terminals, automations, and browser/mobile control.

TypeScript 20 AI 70 Solo 1 sig live ↗
whyiyhw/seek

Not just an agent demo — a local coding-agent platform: plan mode, sub-agent teams, cron, memory, MCP. Single Go binary, DeepSeek-native, MIT.

Go 19 AI 60 Solo 2 sig live ↗
bluejacketblackhawk/saysomething

Free, local voice dictation for Windows. Hold a key, speak, your words appear at the cursor. On-device Whisper, no cloud, no account, no telemetry.

JavaScript 18 AI 70 Solo live ↗
vladar107/claudescope

A scope for your Ai coding-agent sessions

TypeScript 14 AI 70 2 sig
unn-Known1/clickyX

Cross-platform AI companion port of OpenClicky for Windows, Linux, and macOS.

Rust 13 AI 70 1 sig
ChampionGPT/readpilot

Local-first AI reading workspace for EPUBs, notes, Claude Code chat, and interactive companion pages.

TypeScript 10 AI 70
russeell/jobfindsme

本地优先的 AI 求职 MCP Server:一句话搜索 BOSS直聘、猎聘、智联、前程无忧,按简历排序并追踪新增与已投岗位。

Python 10 AI 70 1 sig
omarelkhal/aftertone

Hear a short spoken summary after your coding agent answers. Free to install - no API keys, no subscription, no cloud TTS.

Python 9 AI 70 Solo 3 sig live ↗
JPSchloss/Job-Scouts-Public

Local-first, multi-agent job-search assistant: finds close-match roles and tailors your résumé + cover letter to the ones you choose. You review and send — never an auto-applier. Runs on your own Claude subscription.

TypeScript 9 AI 70
boggspa/TaskWraith

Local-first desktop control room for coding agents. Run Codex, Claude Code, Cursor, Grok, Mistral, Pi, and local models together — each with its own role, permission posture, and receipts. Multi-agent ensembles in one thread, diff review, on-device history. macOS, Windows, Linux.

TypeScript 8 AI 100 2 sig
ding7015869-alt/agent-meeting-studio

🏛️ Multi-Agent Debate & Brainstorm Studio | 本地多Agent辩论&头脑风暴 — run Hermes/Codex/Ollama on your machine

JavaScript 7 AI 100
Feed-Scription/openovel

Local-first AI interactive fiction app — a self-hosted narrative engine with an async multi-agent brain that keeps story state in plain files.

JavaScript 6 AI 70
wolbarg/wolbarg

Wolbarg — modular, provider-agnostic semantic memory SDK for AI agents

TypeScript 6 AI 70 live ↗
maxbaluev/accreted-intelligence

AccInt - local-first MCP Work Model for coding agents that learns from real outcomes.

Shell 6 AI 45 Solo live ↗
SuvenSeo/ai-coding-usage-tracker

Local-first AI coding usage dashboard for Codex, Claude Code, and Cursor — tokens, credits, USD estimates, native GUI, and WakaTime sync.

Python 5 AI 100 Solo live ↗
SidCorp-co/forge

Self-hosted lifecycle platform for software powered by Claude Code. Configurable pipelines, devices you control, no credentials on the server. Apache-2.0.

TypeScript 5 AI 70 1 sig
legostin/learn-almost-anything

Local desktop AI tutor: designs personalized courses on any topic with articles, interactive widgets, comprehension tests, homework review, and TTS lectures. Free — uses your Claude Pro/Max or ChatGPT Plus/Pro subscription. Tauri + React + Claude Agent SDK / Codex SDK.

TypeScript 5 AI 70 Solo 2 sig live ↗
LeahyCC/kungfu-kanban

Local-first kanban board where Claude Code agents work your cards — dependency chains with merge gates, an AI manager that reviews real diffs and merges green PRs, group lanes, CI-gated. One runtime dependency.

JavaScript 5 AI 70 Solo 1 sig live ↗
wl1650918245/douyin-creator-distill

Local-first creator intelligence agent: directory capture, dual transcription, viral analysis, topic generation and reusable creator personas.

JavaScript 5 AI 70
Yomiracle/trinity-lite

Local AgentOps for cross-vendor CLI coding agents: route work, recover state, and accept only with evidence.

Python 5 AI 45 Solo live ↗
wesleysimplicio/simplicio-agent

Local-first autonomous agent: Hermes speed plus Rust determinism, gated actions, checkpoints, evidence receipts, MCP, skills, and multi-model freedom.

Python 4 AI 100 2 sig
aaronlab/browsertrace

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

Python 4 AI 70 Solo live ↗

RELATED Other topics · full topics ranking →

#claude-code

1,564

#ai-agents

1,160

#llm

1,071

#claude

943

#python

806

#ai

741

#developer-tools

728

#mcp

727

#codex

521

Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology