|
1 | | -<a href="https://kayba.ai"><img src="assets/kayba-banner.png" alt="Kayba - Make your agents self-improve from experience" width="1080"/></a> |
| 1 | +<a href="https://kayba.ai"><img src="assets/kayba-banner.png" alt="Kayba - Stop fixing agents by hand" width="1080"/></a> |
2 | 2 |
|
3 | 3 | # Agentic Context Engine (ACE) |
4 | 4 |
|
5 | | - |
| 5 | +[](https://github.com/kayba-ai/agentic-context-engine/stargazers) |
6 | 6 | [](https://kayba.ai) |
7 | 7 | [](https://discord.gg/mqCqH7sTyK) |
8 | 8 | [](https://twitter.com/kaybaai) |
9 | 9 | [](https://kayba-ai.github.io/agentic-context-engine/latest/) |
10 | 10 |
|
11 | 11 | > [!TIP] |
12 | | -> ### Try our hosted solution for free at [kayba.ai](https://kayba.ai): automated agent self-improvement from your terminal. CLI + dashboard that analyzes traces, surfaces failures, and ships improvements directly from Claude Code, Codex, and more. |
13 | | -> [](https://kayba.ai) |
| 12 | +> ### Want this fully managed? [Kayba](https://kayba.ai) automates the loop: it connects to your error sources, investigates agent failures from traces, and ships fixes as pull requests, with impact tracking after deploy. |
| 13 | +> [](https://kayba.ai) |
14 | 14 |
|
15 | 15 | --- |
16 | 16 |
|
17 | | -**AI agents don't learn from experience.** They repeat the same mistakes every session, forget what worked, and ignore what failed. ACE adds a persistent learning loop that makes them better over time. |
| 17 | +**AI agents don't learn from experience.** They repeat the same mistakes every session, forget what worked, and ignore what failed. ACE is the open-source engine that adds a persistent learning loop. It also powers [Kayba](https://kayba.ai), the managed service that does this for your production agents automatically. |
18 | 18 |
|
19 | 19 | <img src="examples/seahorse-emoji-ace.gif" alt="ACE learns from mistakes in real time" width="70%"/> |
20 | 20 |
|
|
0 commit comments