Top AI Repos — open-source AI, indexed and scored
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.
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.
Multi-agent demo platform for Titans (arXiv:2501.00663) — neural networks that learn to memorize at test time. 7 AI agents, native desktop UI.
| Date | Stars |
|---|---|
| 2026-07-24 | 361 |
| 2026-07-25 | 361 |
| 2026-07-28 | 361 |
| 2026-07-30 | 361 |
| 2026-07-31 | 358 |
| 2026-08-05 | 339 |
| 2026-08-06 | 339 |
Today
— stars today
This week
-22 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> # 🧠 Titans: Learning to Memorize at Test Time [](https://github.com/ai-in-pm/Titans---Learning-to-Memorize-at-Test-Time/stargazers) [](https://github.com/ai-in-pm/Titans---Learning-to-Memorize-at-Test-Time/network/members) [](LICENSE) [](https://python.org) [](https://arxiv.org/abs/2501.00663) **An interactive multi-agent demonstration platform for the landmark *Titans* architecture — the first neural network to learn how to memorize at test time.** <img src="https://github.com/user-attachments/assets/a1207510-6c37-4a2a-93d3-a6dab0139184" width="900" alt="Titans Demonstration Platform" /> </div> --- ## ✨ What Makes This Special The [Titans paper](https://arxiv.org/abs/2501.00663) introduces a groundbreaking memory architecture that **learns what to remember during inference** — no more fixed context windows. This repository brings those ideas to life with: - **7 specialized AI agents**, each embodying a different perspective on the Titans architecture - **Native desktop UI** with real-time telemetry, interactive charts, and live visualization - **Side-by-side agent collaboration** — watch how GPT-4, Claude, Mistral, Groq, Gemini, Cohere, and Emergence reason about the same memory problem - **Zero-friction setup** — runs with a single command, even if only one API key is configured --- ## 🚀 Quick Start ```bash # 1. Clone the repo git clone https://github.com/ai-in-pm/Titans---Learning-to-Memorize-at-Test-Time.git cd Titans---Learning-to-Memorize-at-Test-Time # 2. Install dependencies pip install -r requirements.txt # 3. Configure API keys cp .env.sample .env # Edit .env and add your API keys (only the providers you want to use) # 4. Launch python main.py ``` > **Windows users:** Run `titans.bat` (handles path setup automatically) or launch `titans.exe` for a bundled, dependency-free experience. --- ## 🤖 The Seven Agents Each agent explores a distinct component of the Titans architecture through a different LLM lens: | # | Agent | Provider | Titans Role | |---|-------|----------|-------------| | 1 | **Neural Memory Module** | OpenAI (GPT-4) | Core long-term memory model | | 2 | **Memory as Context** | Anthropic (Claude) | Attention-based context memory | | 3 | **Memory as Gate** | Mistral | Gating mechanism for memory flow | | 4 | **Memory as Layer** | Groq | Per-layer memory integration | | 5 | **Experimental Validation** | Google Gemini | Benchmarking & ablation analysis | | 6 | **Innovations** | Cohere | Novel extensions & improvements | | 7 | **Analysis** | Emergence | Cross-agent synthesis & insights | --- ## 🖥️ Desktop Features The native Tkinter interface provides a rich interactive environment: - **Agent selector panel** — choose which agents participate in each run - **Live demonstration console** — real-time streamed output from each agent - **Runtime telemetry** — per-agent timing and token usage metrics displayed live - **Numeric-series chart** — automatically extracted from agent output, with play/scrub interaction - **Collaborative insights view** — synthesized cross-agent analysis panel - **Adjustable split-pane layout** with remembered position across sessions --- ## 🔑 API Key Configuration Copy `.env.sample` to `.env` and add the keys for any providers you want to use: ```env OPENAI_API_KEY=sk-... ANTHROPIC_API_KEY=sk-ant-... MISTRAL_API_KEY=... GROQ_API_KEY=... GOOGLE_API_KEY=... COHERE_API_KEY=... EMERGENCE_API_KEY=... `
Excerpt of 7,262 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:cddab9bb5bdc2a69, topic:ai-agent, desc:ai agents, readme:ai agents
matched fp:cddab9bb5bdc2a69, topic:deep-learning
matched fp:cddab9bb5bdc2a69, topic:llm, topic:transformer