THIS is the wildest open-source project I’ve seen this month. We were all hyped about @karpathy
's autoresearch project automating the experiment loop a few weeks ago.
(ICYMI → https://
github.com/karpathy/autor
esearch
…) But a bunch of folks just took it ten steps further and automated the entire
OPEN SOURCE
-
Advancements in Open-Source AI Agent Automation for Research
By
–
-
Extracting Agent Skills from Open-Source Code Repositories
By
–
GitHub already has millions of repos full of procedural knowledge. The work introduces a framework for extracting agent skills directly from open-source repos. The pipeline analyzes repo structure, identifies procedural knowledge through dense retrieval, and translates it into
-
Graph Machine Learning 2nd Edition with PyTorch Geometric Advancements
By
–
2nd Edition — now at http://
amzn.to/45Y3LyI v/ @PacktDataML Graph Machine Learning — Latest advancements in Graph Data to build robust #MachineLearning algorithms 𝓚𝓮𝔂 𝓕𝓮𝓪𝓽𝓾𝓻𝓮𝓼:
Master new graph ML techniques through updated examples using PyTorch Geometric and -
OpenClaw Setup Guide: Stateful Local Memory Configuration
By
–
Detailed set-up guide: https://
byterover.dev/blog/curated-s
tateful-local-memory-for-openclaw?utm_source=sumanth&utm_campaign=openclaw_skill&utm_content=X_0326
… Byterover Skill: -
OpenClaw ByteRover Auto-Plugin Support Persistent Memory
By
–
Soon there will be auto-plugin support for OpenClaw with ByteRover. Zero manual setup for persistent memory. Support this feature → like the PR:
-
Mastering PyTorch: Create and Deploy Deep Learning Models
By
–
Mastering PyTorch: Create and deploy deep learning models from CNNs to multimodal models, LLMs, and beyond – http://amzn.to/40IFEQR via @PacktDataML #AI #ML #MachineLearning #DataScience #DataScientist #GenAI
-
Core Code Optimization and AI Plugin Architecture Advances
By
–
We made a ton of progress on that today. Lots of code gone from core. Faster, less memory use overall. Need another day or two to stabilize. Everything can be a plugin now. Also added support for Claude/Codex/Cursor plugin bundles
-
Attention Residuals: Novel Architecture for Transformer Models
By
–
Attention Residuals Paper: https://
github.com/MoonshotAI/Att
ention-Residuals/blob/master/Attention_Residuals.pdf
…
Code: https://
github.com/MoonshotAI/Att
ention-Residuals
… -
CodexBar 0.18 Release: New Providers and Performance Improvements
By
–
CodexBar 0.18 is out:
– New providers: Kilo, Ollama, OpenRouter
– Codex historical pace + risk forecasting + backfill
– merged-menu Overview tab
– fewer Claude keychain prompt annoyances – lower CPU/energy use, faster JSONL scanning
thx @RatulSarna -
Upcoming AI Model Updates: Gemma 4 and DeepSeek V4
By
–
I'll try to update it with the major ones. E.g., Gemma 4 next week (likely), and DeepSeek V4 any day now