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.
Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and version control agents across compatible frameworks.
| Date | Stars |
|---|---|
| 2026-07-31 | 1193 |
| 2026-08-01 | 1192 |
| 2026-08-06 | 1192 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<a href="https://docs.letta.com/">
<img alt="Agent File (.af): An open standard file format for stateful agents." src="/assets/agentfile.png">
</a>
<p align="center">
<br /><b>Agent File (.af): An open file format for stateful agents</b>.
</p>
<div align="center">
[](https://discord.gg/letta)
[](LICENSE)
</div>
<div align="center">
[ [View .af Schema](#what-state-does-af-include) ] [ [Download .af Examples](#-download-example-agents) ] [ [Contributing](#-contributing) ]
</div>
---
**Agent File (`.af`)** is an open standard file format for serializing [stateful AI agents](https://www.letta.com/blog/stateful-agents). Originally designed for the [Letta](https://letta.com) framework, Agent File provides a portable way to share agents with persistent memory and behavior.
Agent Files package all components of a stateful agent: system prompts, editable memory (personality and user information), tool configurations (code and schemas), and LLM settings. By standardizing these elements in a single format, Agent File enables seamless transfer between compatible frameworks, while allowing for easy checkpointing and version control of agent state.
## Browsing Agents
Each agent in this directory has been trained and tuned for specific purposes. You can explore them at:
```text
agents/
└── @{owner}/
└── {agent-name}/
├── {agent-name}.af # The agent file
└── {agent-name}.webp # Avatar image
```
### Featured Agents
| Agent | Author | Description |
|-------|--------|-------------|
| [Loop](agents/@letta-ai/loop/) | @letta-ai | A ChatGPT alternative focused on memory. Direct, dry, remembers everything. |
## Deploying an Agent
You can deploy any agent file to your own Letta server using the ADE, REST API, or SDK.
### Using the Agent Development Environment (ADE)
1. Download the `.af` file from this repository
2. Open [Letta ADE](https://app.letta.com)
3. Click "Import Agent" and select the file
### Using the Python SDK
```python
# Install SDK with `pip install letta-client>=1.0.0`
from letta_client import Letta
# Assuming a Letta Server is running at http://localhost:8283
client = Letta(base_url="http://localhost:8283")
# Import your .af file from any location
agent_state = client.agents.import_file(file=open("/path/to/agent/file.af", "rb"))
print(f"Imported agent: {agent_state.id}")
```
### Using the TypeScript SDK
```typescript
// Install SDK with `npm install @letta-ai/letta-client@^1.0.0`
import { LettaClient } from '@letta-ai/letta-client'
import { readFileSync } from 'fs';
import { Blob } from 'buffer';
// Assuming a Letta Server is running at http://localhost:8283
const client = new LettaClient({ baseUrl: "http://localhost:8283" });
// Import your .af file from any location
const file = new Blob([readFileSync('/path/to/agent/file.af')])
const agentState = await client.agents.importFile(file, {})
console.log(`Imported agent: ${agentState.id}`);
```
### Using cURL
```sh
# Assuming a Letta Server is running at http://localhost:8283
curl -X POST "http://localhost:8283/v1/agents/import" -F "file=/path/to/agent/file.af"
```
## Contributing an Agent
Have an agent you've trained and want to share? We'd love to include it.
### Quick Start
1. **Fork this repository**
2. **Create your agent directory:**
```
agents/@{your-github-handle}/{agent-name}/
```
3. **Export your agent** from Letta using the ADE or via the API (see [Exporting Agents](#exporting-agents) below)
4. **Add required files:**
- `{agent-name}.af` — Your exported agent file
- `{agent-name}.webp` — Square avatar image
5. **Submit a pull request**
See [agents/CONTRIBUTING.md](agents/CONTRIBUTING.md) for detailed guidelines.
### ExportinExcerpt of 9,075 characters
Read on GitHub
Sarah Wooders · Letta · United States
69
Charles Packer · @letta-ai · United States
45
Cameron · @letta-ai · United States
21
Shubham Naik · @letta-ai
14
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2a9be97c0bc919ba, desc:ai agents