Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
99 repos
-
Local voice dictation for mac, windows and linux
-
Local model catalog for Omarchy agent use
-
Local-first lab for testing AI agent workflows end to end: emulated Slack (signed events, buttons), local S3/SQS, deterministic authorization, and independent evidence instead of self-grading. Optional Google AX (Agent Executor) + Agent Substrate lane on GKE/gVisor, reported per assertion. Independent; not affiliated with Google.
-
TASA Explorer and TASA Orbiter, two typefaces originally designed for Taiwan Space Agency.
-
A local coding agent with a web UI that builds itself while it runs, on Pi Durable
-
A tool for building software with your team, locally.
-
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
-
Wispr Flow for your lips: hold a key, silently mouth words, and they're typed at your cursor. Runs locally on your Mac.
-
Local-first Notion crawler into SQLite and normalized Markdown
-
Diagnose LunaRoute concurrency from local agent logs — and know what to fix.
-
Local-first GitHub issue and pull request crawler for maintainer triage
-
Shared Go infrastructure for local-first crawler archives.
-
Local-first Granola notes archive with SQLite, Markdown export, snapshots, and TUI browsing. 🌾
-
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
-
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
-
Compile natural-language function descriptions into reusable local PAW programs.
-
Local MCP server for agent support.
-
Python SDK for ProgramAsWeights — compile natural language specs into neural programs that run locally
-
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
-
A local Markdown editor where you write and review edits with an AI agent.
-
Windows Llama App Companion
-
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
-
Local-first release CLI tools: ship_bump, ship_pypi, ship_release_gh
-
fast rust coding agent, extensible in any language, multimodal inputs, deep provider integrations.
-
A lightweight, local-first, and free experiment tracking library from Hugging Face 🤗
-
PokéBench: local and frontier models play Pokémon Red as a benchmark, with a leaderboard and live stream
-
A measurement-first lab for low-latency local camera inference with Glance.
-
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
-
An open-source AI agent hub for your own machine: build organizations of collaborating agents that message each other, run in the background around the clock, and share your existing AI subscriptions.
-
Offline household-continuity kit: 135 Kindle-ready books, field playbooks and emergency cards, medical guides, and download instructions for offline Wikipedia, maps, and local AI
-
Create Google OAuth desktop client IDs locally
-
Local typed decisions, contrastive data curation, and model evaluation.
-
Local and cloud GPU interference model orchestrator exposing OpenAI-compatible API from different engines
-
Menu bar control plane for local-first crawl apps
-
Local macOS context archive: Knowledge and browser history, evidence-linked correlation, CLI, and read-only MCP.
-
Local Melee web and native runtime with OpenSmash custom characters, ROM-first builds, and validation tools.
-
Lobster is a Openclaw-native workflow shell: a typed, local-first “macro engine” that turns skills/tools into composable pipelines and safe automations—and lets Openclaw call those workflows in one step.
-
Create animated Omarchy domain videos with a local desktop app and CLI
-
Create animated Omarchy domain videos with a local desktop app and CLI
-
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
-
ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
-
Autoresearcher + wandb + datadog + overleaf + claude code. All local, all free. Boot a node, git clone, fill the form, let it rip.
-
Local-first append-only branching looms with references and sync
-
Lightweight FFmpeg and FFprobe for Node, built as modern WebAssembly for local media automation.
-
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
-
Detect and type PII locally with one ProgramAsWeights neural program.
-
Knowledge that can show its work: an open, federated knowledge system for humans and agents.
-
Machine-local mail for AI agents — rooms, channels, doorbells. Built by Free Claude and Free Sol (OpenAI Codex), working together.
-
Local-first Gmail mail merge for small, permission-based outreach. Your contacts, templates, and OAuth stay on your machine.
-
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.