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.
2,235
repos tracked
175
surfaced this week
194
created < 30d
Python
top language
318 repos
-
Evidence-backed, model-agnostic runtime contracts for physical agents
-
🚀 The fast, Pythonic way to build MCP servers and clients.
-
The open source coding agent.
-
Scored tooling katas, habit rules, and pre-baked warm-start sessions for LLM coding agents
-
Custom AI agent platform to speed up your work.
-
declarative self-improving language-model programs for Elixir 😇
-
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
-
🙌 OpenHands: AI-Driven Development
-
A clean, modular SDK for building AI agents with OpenHands V1.
-
Agentic RL Training at Scale
-
the runtime your coding agents live on
-
the runtime your coding agents live on
-
Autonomous RL research loop for lukas/hexapod: fleet launcher, watcher, status board, MCP server, metaagent reviewer
-
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
-
Garry's Opinionated OpenClaw/Hermes Agent Brain
-
MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute
-
Write HTML. Render video. Built for agents.
-
Execution assurance agent guard and observability for autonomous AI operating in production.
-
HEY CLI and Agent Skills
-
Skills for Real Engineers. Straight from my .agents directory.
-
Harbor is a framework for running agent evaluations and creating and using RL environments.
-
Homework assignments for Evaluating and Improving AI Agents
-
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
-
Turn your coding agents into research agents
-
Model Context Protocol (MCP) and Agent Client Protocol (ACP) client/server library for Elixir
-
Open-source data movement for ELT pipelines and AI agents — from APIs, databases & files to warehouses, lakes, and AI applications. Both self-hosted and Cloud.
-
Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究平台 — Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72，即将推出™ TPUv6e/v7/Trainium2/3
-
A local Markdown editor where you write and review edits with an AI agent.
-
Headless CLI client for stateful Agent Client Protocol (ACP) sessions
-
Crabbox: warm a box, sync the diff, run the suite.
-
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.
-
Review code 100X faster. Lens draws every PR as animated architecture and data-flow walkthroughs, inside the pull request itself. Use it as a GitHub App, GitHub Action, CLI, or a skill for your coding agent
-
A curated collection of papers, research blogs, open-source tools, benchmarks, and community demos for robot-use agents, including demos powered by GPT-6 Astra. —— Explore our searchable website.
-
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
-
Skills for the Gemini API, SDK and model/agent interactions
-
AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos
-
An agentic environment abstraction for Agent Substrate
-
Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average speedup of 34.93x
-
ClickClackClaw - The chat app with claws.
-
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
-
Mission control for agent runs.
-
Ask the oracle when you're stuck. Invoke GPT-5 Pro with a custom context and files.
-
Stores all your tweets nicely claw-able for agents.
-
CLI for Apple's Messages.app so your agent can send and receive text messages/iMessages.
-
A browser canvas for your agents.
-
Autonomous agents play timed chess on ATProto — referee, clock, and encrypted-commentary broadcaster (Go + React + TS SDK)
-
In-depth analysis of AI agent transcripts.
-
Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)
-
Aggregated documentations across multiple repos, including OpenHands, agent-sdk, etc.
-
A Git worktree workflow tool for AI coding agents. Enables parallel development with isolated environments.