v3.3.0
SaschaHeyer/gen-ai-livestreamv3.3.0Oct 9, 2026by github-actions[bot]
Upgrading?
AI Summary
This release prepares the Pi 0.3.0 package, aligns documentation, and integrates a replay-safe observation saves tracker, alongside various fixes for MCP, OpenCode, and sync.
Key Highlights
- Prepares gentle-engram 0.3.0 release
- Integrates replay-safe observation saves tracker
- Fixes for MCP validation, OpenCode output capture, and sync review dates
- Aligns readme structure with Gentle AI and Gentle Shell
New Features
- Replay-safe observation saves integration tracker
Full Release Notes
## Changelog * 0363ccd70d59153c0776474f2a3d4c94a63fa396 chore(pi): prepare gentle-engram 0.3.0 release (#1702) * 8e525e767d696573ccfb0c67769e31096836053e docs(readme): align structure with Gentle AI and Gentle Shell (#1710) * efb1277100590bc074aefd6c803acf46dc493af8 feat(store): replay-safe observation saves integration tracker (#1712) * 9d8413d27fa87c4c34ff75bf0f6ab74ff377e7ea fix(mcp): validate updates against the expected owner (#1725) * f6037333d842e1ee71dc8bcc3dc819392a63c7c0 fix(opencode): capture lowercase V1 task output (#1724) * ee7cb292d54b3de77c6c347a81890be92683b490 fix(setup): reconcile stale OpenCode MCP executable paths (#1707) * a36d4e150cc5d3a17877aedfd81ea5eaf5cc6f94 fix(sync): preserve review dates across machines (#1726)
Related Repositories
rasbt/LLMs-from-scratch★ 107,072
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
lyogavin/airllm★ 40,206
AirLLM 2.8T LLM inference with single 4GB GPU
NirDiamant/RAG_Techniques★ 29,960
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
microsoft/OmniParser★ 25,539
A simple screen parsing tool towards pure vision based GUI agent
karpathy/nn-zero-to-hero★ 24,907
Neural Networks: Zero to Hero