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.
Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
| Date | Stars |
|---|---|
| 2026-07-31 | 2539 |
| 2026-08-03 | 2552 |
| 2026-08-06 | 2552 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Memento: Fine-tuning LLM Agents **without** Fine-tuning LLMs
> A memory-based, continual-learning framework that helps LLM agents improve from experience **without** updating model weights.
<p align="center">
<b>Planner–Executor Architecture</b> • <b>Case-Based Reasoning</b> • <b>MCP Tooling</b> • <b>Memory-Augmented Learning</b>
</p>
---
<table>
<tr>
<td align="center" width="50%">
<img src="Figure/f1_val_test.jpg" width="90%"/>
<br/>
<sub><b>Memento vs. Baselines on GAIA validation and test sets.</b></sub>
</td>
<td align="center" width="50%">
<img src="Figure/f1_tasks.jpg" width="90%"/>
<br/>
<sub><b>Ablation study of Memento across benchmarks.</b></sub>
</td>
</tr>
<tr>
<td align="center" width="50%">
<img src="Figure/f1_iteration.jpg" width="90%"/>
<br/>
<sub><b>Continual learning curves across memory designs.</b></sub>
</td>
<td align="center" width="50%">
<img src="Figure/f1_ood.jpg" width="90%"/>
<br/>
<sub><b>Memento’s accuracy improvement on OOD datasets.</b></sub>
</td>
</tr>
</table>
## 📰 News
- [2025.10.05] We’re excited to announce that our parametric Case-Based Reasoning inference code is now officially open-sourced! 🎉
- [2025.09.05] We’ve added support to deploy a local LLM as the executor using vLLM, please see client/agent_local_server.py. 🎉
- [2025.09.03] We’ve set up a WeChat group to make it easier to collaborate and exchange ideas on this project. Welcome to join the Group to share your thoughts, ask questions, or contribute your ideas! 🔥 🔥 🔥 [Join our WeChat Group Now!](Figure/wechat.jpg)
- [2025.08.30] We’re excited to announce that our no-parametric Case-Based Reasoning inference code is now officially open-sourced! 🎉
- [2025.08.28] We’ve created a Discord server to make discussions and collaboration around this project easier. Feel free to join and share your thoughts, ask questions, or contribute ideas! 🔥 🔥 🔥 [Join our Discord!](https://discord.gg/y4FP2EDXyX)
- [2025.08.27] Thanks for your interest in our work! We’ll release our CBR code next week and our Parametric Memory code next month. We’ll keep updating on our further development.
- [2025.08.27] We add a new Crawler MCP in ```server/ai_crawler.py``` for web crawling and query-aware content compression to reduce token cost.
- [2025.08.26] We add the SerpAPI (https://serpapi.com/search-api) MCP tool to help you avoid using the search Docker and speed up development.
## 🔥 Key Features
- **No LLM weight updates.** Memento reframes continual learning as **memory-based online reinforcement learning** over a **memory-augmented MDP**. A neural **case-selection policy** guides actions; experiences are stored and reused via efficient Read/Write operations.
- **Two-stage planner–executor loop.** A CBR-driven **Planner** decomposes tasks and retrieves relevant cases; an **Executor** runs each subtask as an MCP client, orchestrating tools and writing back outcomes.
- **Comprehensive tool ecosystem.** Built-in support for web search, document processing, code execution, image/video analysis, and more through a unified MCP interface.
- **Strong benchmark performance.** Achieves competitive results across GAIA, DeepResearcher, SimpleQA, and HLE benchmarks.
---
## 🧠 Core Concept
**Learn from experiences, not gradients.** Memento logs successful & failed trajectories into a **Case Bank** and **retrieves by value** to steer planning and execution—enabling low-cost, transferable, and online continual learning.
---
## 🏗️ Architecture
### Core Components
- **Meta-Planner**: Breaks down high-level queries into executable subtasks using GPT-4.1
- **Executor**: Executes individual subtasks using o3 or other models via MCP tools
- **Case Memory**: Stores final-step tuples **(s_T, a_T, r_T)** for experience replay
- **MCP Tool Layer**: Unified interface for external tools and services
### Tool Ecosystem
- **Web Research**: Live Excerpt of 15,185 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:64f7862aa82c8ef7, desc:fine-tuning, desc:fine tuning
