From ec6da06702eec747bdcc144d6a78f05d29b19a34 Mon Sep 17 00:00:00 2001
From: Anton Razzhigaev <47871264+razzant@users.noreply.github.com>
Date: Fri, 2 Oct 2026 23:16:07 +0300
Subject: [PATCH] Refresh existing Ouroboros description and evidence

---
 README.md          |  2 +-
 data/projects.json | 11 ++++++-----
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/README.md b/README.md
index 1c3720e..8a38077 100644
--- a/README.md
+++ b/README.md
@@ -52,7 +52,7 @@ Projects focused on enabling AI agents to evolve, learn, and improve autonomousl
 - [**SIA**](https://github.com/hexo-ai/sia#readme) - Self-improving AI framework that autonomously optimizes the performance of any AI system through iterative evaluation and refinement. by [@hexo-ai](https://github.com/hexo-ai) (2,151 stars)
 - [**Reef**](https://github.com/Human-Agent-Society/reef#readme) - Continual learning infra for self-improving agents. Serves agent traffic, turns matched feedback into model-weight or harness updates, and publishes accepted updates as versioned artifacts. by [@Human-Agent-Society](https://github.com/Human-Agent-Society) (2,004 stars)
 - [**Orkas**](https://github.com/Orkas-AI/Orkas#readme) - Local-first multi-agent desktop application whose specialist agents improve through reflection and crystallize successful approaches into private reusable skills. by [@Orkas-AI](https://github.com/Orkas-AI) (1,998 stars)
-- [**Ouroboros**](https://github.com/razzant/ouroboros#readme) - Self-creating AI agent that writes its own code and evolves autonomously. Completed 30+ evolution cycles in first 24 hours with zero human intervention. by [@razzant](https://github.com/razzant) (1,328 stars)
+- [**Ouroboros**](https://github.com/razzant/ouroboros#readme) - Self-developing general-purpose agent with persistent identity and memory, reviewed changes to its own implementation, and desktop and headless interfaces. by [@razzant](https://github.com/razzant) (1,402 stars)
 - [**Agent0**](https://github.com/aiming-lab/Agent0#readme) - Self-evolving agent framework from UNC/Salesforce/Stanford. Improves without human-curated datasets via curriculum and executor agent competition. by [@aiming-lab](https://github.com/aiming-lab) (1,261 stars)
 - [**agent-qa**](https://github.com/vostride/agent-qa#readme) - Self-improving QA agent for natural-language web and mobile tests, using persistent run memory to adapt to UI changes and catch regressions. Source-available under FSL-1.1-ALv2: use is permitted except to provide a competing commercial product or service, and each release converts to Apache-2.0 after two years. by [@vostride](https://github.com/vostride) (911 stars)
 - [**A-Evolve**](https://github.com/A-EVO-Lab/a-evolve#readme) - The PyTorch for Agentic AI. Open-source infrastructure that evolves any agent across any domain with zero human intervention. #1 on MCP-Atlas (79.4%). by [@A-EVO-Lab](https://github.com/A-EVO-Lab) (790 stars)
diff --git a/data/projects.json b/data/projects.json
index af787a7..3572a8b 100644
--- a/data/projects.json
+++ b/data/projects.json
@@ -120,15 +120,16 @@
   {
     "name": "Ouroboros",
     "repo": "razzant/ouroboros",
-    "description": "Self-creating AI agent that writes its own code and evolves autonomously. Completed 30+ evolution cycles in first 24 hours with zero human intervention.",
+    "description": "Self-developing general-purpose agent with persistent identity and memory, reviewed changes to its own implementation, and desktop and headless interfaces.",
     "category": "evolution",
     "maintainer": "razzant",
     "tags": [
-      "self-creating",
-      "autonomous-evolution",
-      "self-modifying"
+      "autonomous",
+      "self-evolving",
+      "open-source"
     ],
-    "stars": 1328
+    "stars": 1402,
+    "paper": "https://arxiv.org/abs/2608.08311"
   },
   {
     "name": "A-Evolve",