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
70 repos
-
Call commands safely by checking them rigorously against an allow-list
-
A tool for building software with your team, locally.
-
Official repository for BrickWright, a framework that enables LLM agents to create physically feasible LEGO® builds from text or image prompts.
-
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
-
Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.
-
Wispr Flow for your lips: hold a key, silently mouth words, and they're typed at your cursor. Runs locally on your Mac.
-
Script to automatically add trackers from a list to all torrents in Transmission
-
Tools for managing BibTeX bibliographies: automatically update preprints to published versions and filter to only cited references.
-
A conda-smithy repository for pyjuliacall.
-
Python and Julia in harmony.
-
Python SDK for ProgramAsWeights — compile natural language specs into neural programs that run locally
-
Fast, flexible, elastically deterministic data loading for foundation model training
-
Official implementation of FlowHMR, a generative model for physically plausible motion capture from monocular video.
-
Your always-on AI coworkers that move between text, calls, and Slack.
-
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
-
Minimal Jupyter protocol commons: wire-format sessions and kernel-client call conventions
-
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
-
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
-
Cache your API calls with a single line of code. No mocks, no fixtures. Just faster, cleaner code.
-
Interactive signal aliasing visualization with analytically correct sampling and reconstruction.
-
Create Google OAuth desktop client IDs locally
-
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
-
Add a decorator for dspy Signatures that automatically uses TypeSafe where relevant
-
A catalog of unexpected AI behaviors, discovered automatically.
-
Monkey patch, test, and trace Python by attaching bindings to call sites, without modifying the code being observed. Built on wrapt.
-
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.
-
A small readable MCP library for serving Python functions as tools and calling MCP servers
-
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.
-
Automatically rotate ChatGPT & Claude accounts based on remaining usage
-
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.
-
Speculative programmatic tool calling (sPTC) for harnesses like RLM, CodeAct, etc.
-
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.
-
AI-powered video frame extraction tool that automatically identifies and extracts high-quality frames containing people, with intelligent pose categorization (standing/sitting/squatting), head orientation detection, and shot type classification. Features GPU acceleration, resumable processing, and extensive configuration options.
-
structured outputs for llms
-
The procedural generation voxel engine
-
🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dangerous until you say go. From your desk or your phone.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
★ 233 OpenHands/agent-canvasOpenHands Agent Canvas is a Open Source AI coding platform. Start locally, connect your tools, and automate workflows.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
OpenHands Agent Canvas is a Open Source AI coding platform. Start locally, connect your tools, and automate workflows.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Apple Silicon (Metal) backend for Triton: write standard @triton.jit kernels on your Mac GPU. The same source runs bit-identical on NVIDIA and AMD, so you develop kernel logic locally and rent a datacenter GPU only for the perf pass.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.