Launches on August 27, 2026
Repositories created on this date, ranked by GitHub stars. They launched the same day, so their stars compare directly.
- 185
Evidence-first search for AI agents / Claude Code & Codex & Pi & OMP & kimi & mcp
- 255
Give an agent real hands and eyes: undetectable, DOM-independent GUI automation. A $4 USB-HID microcontroller for hands, a vision grounding model for eyes, any LLM for a brain.
- 33
Personal agent companions built on the pi SDK — chat over Telegram, per-agent plugins, memory, calendar, scheduling heartbeat, self-evolution
- 43
AI-assisted systematic literature reviews with traceable evidence.
- 52
Local-first chat agent that runs comfortably with small-context local LLMs (from 2B) without losing the original goal of a long conversation. Multi-window context with rollovers, SKILL.state runtime, memory carry-over, three-tier auto web search, and a stalled-session detector. Next.js + FastAPI + SQLite + LanceDB, packaged for Docker Compose.
- 61
A software factory for coding agents. One command, /bulma, picks the next piece of work and walks it through delivery, review, and QA.
- 70
agent patterns lab
- 80
AI 에이전트와 웹 UI로 즐기는 노리밋 텍사스 홀덤
- 90
Autonomous Multi-Agent AI Crypto Trading Bot powered by Google Gemini Vision, NVIDIA NIM, and OpenAI with TradingView chart integration and paper trading engine.
- 100
知识库
- 110
A job and contract search you run as a loop: an AI-assistant skill plus a dependency-free local dashboard. Guided intake, honest 0-100 scoring, live-link verification, and a five-lens adversarial resume review per role. Never auto-applies.
- 120
Multiharness-Core is a central orchestration framework driven by an agentic workflow.Codex acts as the lead Planner to design architecture and delegate tasks, while Opencode serves as the Executor to implement the codebase according to Codex's blueprints.
- 130
Landing page for Shelve — tryshelve.com
- 140
TokenLab native-protocol model provider, multimodal tools, and async tasks for DeepSeek Harness
- 150
把「最终做对了」的长 Agent Trace 剪成精华版:训练能用,人也能看懂。
- 160
Transcrição local de notas de voz do WhatsApp Web com Whisper e backend localhost