snap-stanford/POPPER
quality grade F, 33 out of 100Automated Hypothesis Testing with Agentic Sequential Falsifications
- stars
- 289
- stars gained this week
- —this week
- forks, open issues and contributors
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Released model weights, reference implementations and architecture research.
Signals: large-language-models, llm, foundation-models, transformer, gpt, llama, mistral, qwen
1,455 results
Automated Hypothesis Testing with Agentic Sequential Falsifications
⚡ Stream browser logs to terminal, zero setup, perfect for Ai Agents
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
Integrated AI environment in the terminal. Build, test and instruct agents.
❓Curie: Automated and Rigorous Scientific Experimentation with AI Agents
Odyssey: Empowering Minecraft Agents with Open-World Skills
Task tracking for Agents
Repository-level Repair Agent Based on SWE-Bench—JoyCode Agent
Live-SWE-agent: live, runtime self-evolving software engineering agent
Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency
A program synthesis agent that autonomously fixes its output by running tests!
No code AI agents
The first AI Agent Server, Eidolon is a pluggable Agent SDK and enterprise ready, deployment server for Agentic applications
Extracted artifacts from Kimi OK-Computer (and other agents) system for AI studies in agentic architecture.
[EMNLP2025] "GraphAgent: Agentic Graph Language Assistant"
Reflexion: an autonomous agent with dynamic memory and self-reflection
AG2 Visualized - Build Multi-Agentic Apps with Drag-and-Drop.
IDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation into a unified desktop experience.
AI agent skill for Jetpack Compose & Compose Multiplatform (KMP/CMP). MVI architecture, Navigation 3, Koin/Hilt, Ktor, Room, DataStore, Paging 3, Coil, coroutines/Flow, animations, performance, accessibility, testing, and cross-platform patterns. Works with Codex, Cursor, Claude Code.
Host-agnostic bridge connecting Claude Code SDK to IM platforms (Telegram, Discord, Feishu)
23 Components of the Claude Code Architecture
Autocomplete your obsidian notes with AI, including ChatGPT, through a copilot-like interface.
“百聆”是一个基于LLaMA的语言对齐增强的英语/中文大语言模型,具有优越的英语/中文能力,在多语言和通用任务等多项测试中取得ChatGPT 90%的性能。BayLing is an English/Chinese LLM equipped with advanced language alignment, showing superior capability in English/Chinese generation, instruction following and multi-turn interaction.⚠️ This project has been moved to: https://github.com/BayLing-Models/BayLing
An efficient API documentation management tool that fully adheres to the OpenAPI specification and incorporates advanced LLM technology. This tool can automate the generation of API documentation, data models, and test cases, greatly enhancing development efficiency and documentation quality.
24,540 repositories in the index in total.