Emerging AI agents repos

An agent that moves into your Android phone and becomes its soul — not an assistant, not a tool. Any app, no integrations, on-device, one APK.

after quiet weeks

Autonomous AI sales agent powered by Claude Code or Codex. Finds prospects, writes cold emails, sends campaigns, handles replies, books meetings. No API keys needed — runs on your Claude or Codex subscriptions.

Breakout week (~6 a week)

Local-first AI teammate workspace. Bring your own models and keep project conversations, tool approvals, and results together.

after quiet weeks

Scenario for Blender: AI images, video, 3D and PBR materials in the viewport, plus a local MCP server for agents. Blender 5.0+ extension, GPL-3.0-or-later.

Breakout week (~2 a week)

Context is yours. Agents are replaceable.

51× its usual pace (~12 a week)

The operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent 的运维超集——完整继承 Pi 的核心能力，并进一步扩展可观测性、治理、故障恢复、评估和多 Agent 编排。

50× its usual pace (~16 a week)

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

45× its usual pace (~16 a week)

SEO skills for Claude Code, Cursor and Codex: SEO autopilot, title tags, blog refreshes, backlinks, customer journeys, video transcripts and copywriting.

after quiet weeks

Harness Engineering 101 — building AI agents from first principles. The LLM is the brain; the harness is the body.

after quiet weeks

Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.

37× its usual pace (~9 a week)

The open-source Grok Bot alternative: message Claude Code, Codex, Cursor, Gemini and 40+ AI agents as bots on your own computer, from iPhone, Mac, Windows, Linux or terminal. Free. Also a Muse and Dots alternative. Built in Rust.

after quiet weeks

mission control for agent skills

65× its usual pace (~4 a week)

YouTube transcript skills for Claude Code, Cursor and Codex. Agent Skills to get transcripts, search YouTube, read channels and playlists, and bulk export.

after quiet weeks

Computer-Use SDK for E2E QA Testing

Breakout week (~1 a week)

Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy

23× its usual pace (~14 a week)

AI multi-agent tool that turns research papers into cited commercialization and tech-transfer assessments: TRL, patent landscape, market and risks. CrewAI + FastAPI, with a reproducible benchmark.

24× its usual pace (~9 a week)

Deep Skill Finder – Real Tests Real Reviews find skills that Real Work

52× its usual pace (~4 a week)

Autonomous GitHub Project build → QA → review loop for Claude Code. One-line install.

Breakout week (~1 a week)

24 open-source agent skills that turn taste into instructions — ten genre identities, each proven by a same-brief before/after demo

after quiet weeks

中国 A 股数据基础设施。55个日更数据集：股票行情、基本面、期货数据、资金面、公告事件、指数行业、宏观与风险。行级溯源、PIT 语义、复权与历史成分内置，MCP 原生。自托管，零注册、零 API Token

17× its usual pace (~23 a week)

ASPIRE: Agentic /Skills Discovery for Robotics

17× its usual pace (~28 a week)

DSH × Blender 直连实时插件：15 个模型工具让 AI 驱动 GUI Blender；v2.5 活动状态置顶并可一键暂停 AI，原生选中/集合/子元素直送 DSH，随包建模 skill，支持 WSL / Windows / macOS。

17× its usual pace (~42 a week)

AI Agent Identity and Access Management and Inference Firewall

after quiet weeks

Programmable git infrastructure on top of object storage. Think turbopuffer for git. Open source alternative to Pierre (code.storage) and Cloudflare Artifacts.

16× its usual pace (~12 a week)

Operant Beta：以多模型分工、按需通信、分层审批和经验复用为核心设计，在本机组织可追溯的 Agent 协作，并通过模块化架构扩展能力。

Breakout week (~1 a week)

Vibe code with pi in a lightweight, real IDE that customises itself around the way you work — The Vibe You Need

15× its usual pace (~29 a week)

Free, open-source MCP server that gives AI coding agents (Claude Code, Codex, Cursor, OpenCode, ZCode…) design inspiration from award-winning websites — search with real screenshots, pull design DNA, capture and record live sites. A Mobbin alternative. No API key.

19× its usual pace (~8 a week)

Unofficial Claude Skill derived from the book Refactoring UI — a design rulebook and diagnostic layer for web UI. 151 tracked rules, design token generation, and Tailwind mappings.

after quiet weeks

AI agent skills for production grade applications

Breakout week (~1 a week)

Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.

13× its usual pace (~36 a week)

一个会总结你习惯的私人 AI agent

after quiet weeks

An evaluation harness for medical/health AI agents — reproduce and cover multiple benchmarks under one scoring discipline

25× its usual pace (~5 a week)

An AI Skill Runtime for knowledge-intensive work which makes everything under your control.

Breakout week (~1 a week)

Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.

12× its usual pace (~11 a week)

Agentic hardware development with lawful, deterministic KiCad/STEP viewers, written in Bend

11× its usual pace (~20 a week)

PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.

Breakout week (~1 a week)

A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.

11× its usual pace (~84 a week)

响应快 省Token， Let AI agents (Claude Code, Codex, any MCP client) drive a real iPhone · 让 AI agent 操作真实 iPhone：读屏、点击、输入、滑动，USB 或 Wi-Fi，自有 XCTest runner，可回放的 App flow。Open source, self-hosted on macOS.

22× its usual pace (~5 a week)

Auditable AI-assisted scientific research: evidence-gated hypothesis routing, isolated computation, independent replication, and anomaly-sensitive representation repair.

after quiet weeks

Hardware as fast as software.

10× its usual pace (~25 a week)

Pi — A cross-platform AI coding agent, bringing the Claude Code experience to your desktop. No environment setup, no terminal commands. Download and start coding right away.

10× its usual pace (~31 a week)

Open-source, self-hostable Rust runtime that runs Claude Code, Codex, and Pi in the cloud.

10× its usual pace (~61 a week)

Cosmonapse is an open-source event-driven runtime for distributed AI agents. Build agent systems around typed signals, asynchronous messaging, and independent services instead of a centralized orchestrator.

after quiet weeks

Standalone SearXNG CLI for coding agents

after quiet weeks

Claude Code skill for Dribbble-level product launch videos from code. One shape that never cuts, springs, a cursor that drives every change, beat-synced SFX, 60 fps motion blur. v2: use with Claude Opus 5.5.

22× its usual pace (~4 a week)

High-performance native SSH client in Rust, GPU-rendered with GPUI: host manager, terminal, WinSCP-style SFTP and port forwarding. Rust 编写、GPU 渲染的原生 SSH 客户端。

after quiet weeks

An elegant, information-rich status, menu, and side bar for Pi Agent.

17× its usual pace (~5 a week)

⭐️⭐️⭐️ Open-source, self-hosted alternative to Linear and Plane. Project management and issue tracking where teams and AI agents work side by side to plan and ship products.

8× its usual pace (~76 a week)

从 Vibe Coding 到 Vibe World：AI原生的可编程三维世界，面向元宇宙、Science、世界模型的开源底座

after quiet weeks

Git-backed shared memory for AI agent fleets: searchable knowledge base, incident and task tracking, every write versioned and attributed. CLI, HTTP API and MCP server.

after quiet weeks

Autonomous backend platform. Your coding agent builds it over MCP, Backenly keeps it running: Postgres, REST APIs, auth, storage, realtime, and functions, with every change governed, verified, and reversible.

35× its usual pace (~2 a week)

The phone is your last API. Give your agent a voice to call any US business - reservations, inquiries, quotes. Verified outcome + transcript. First 250 calls free.

23× its usual pace (~3 a week)

Senior-level UX and design-system knowledge, packaged so your AI agent applies it automatically.

16× its usual pace (~4 a week)

Run the DeepSeek Harness AI agent natively on Android — no root, no Termux, extension center included | 手机本地运行 DeepSeek Agent，免 Root 免 Termux

13× its usual pace (~5 a week)

Open-source, self-hostable alternative to ChatGPT and NotebookLM — agents, skills, MCP, and cited knowledge in one AI workstation. Your models, your infrastructure. Free to use GPT 6: https://SourceWeft.com/

21× its usual pace (~3 a week)

The self-hosted AI SRE agent. You don't have to monitor your systems alone. Versus Incident will keep track of your services, applications, and systems, detect new or unexpected problems, and provide your team with the evidence needed to investigate.

6× its usual pace (~9 a week)