repo → https://
github.com/thedotmack/cla
ude-mem
… Shoutout to Alex Newman (
@Claude_Memory
) for building this and making it open-source for the community! Don't forget to drop a star
OPEN SOURCE
-
Claude Memory Open-Source Project by Alex Newman
By
–
-
Claude Code Mod Achieves 51k Stars With Permanent Memory
By
–
Found this awesome mod for Claude Code that gives it permanent memory It blew up to 51k stars because it fixes the biggest issues: → 95% less token consumption
→ Never hits context limits
→ Picks up exactly where you left off 1-command install. Free Repo link in ↓ -
OpenDataLoader Publishes Comprehensive Benchmark Results Online
By
–
btw @opendatalo51205 published all their benchmark results on http://
opendataloader.org -
SGLang Inference Optimization Discussion and Recommendation
By
–
SGLang is so underrated for inference optimization. Will check this out, Andrew!
-
Open-source repository showcasing Andrej Karpathy AI skills
By
–
repo:
→ https://
github.com/forrestchang/a
ndrej-karpathy-skills
… Shoutout to @jiayuan_jy for building this and making it open-source for the community! Don't forget to drop a star ! -
MiniMax Addresses M2.7 License Change Controversy Response
By
–
Just now, MiniMax responded to the controversy about the license change on the M2.7 model.
-
Netflix Open-Sources VOID Framework for Video Object Removal
By
–
/1 Netflix presents VOID, an open-source framework enabling video object removal with updated motion Netflix introduces VOID, an open-source framework that removes objects from videos and updates the physical interactions they cause. Most tools only fill in pixels behind
-
OpenClaw Routes Code Review Tasks to Hermes Agent
By
–
OpenClaw receives “review my repo and check open PRs.” It routes that to a Hermes-powered coding agent. Hermes runs the repo inspection, tests, diff review, and saved code-review workflow. It sends the result back to OpenClaw, which keeps orchestration.
-
AI as Autocomplete, Not True Intelligence
By
–
AI doesn’t understand your question. It predicts which words are statistically likely to follow it. That’s not intelligence. That’s autocomplete with a PhD-sized training set.
-
MiniMax M2.7 on 4x DGX Sparks with vLLM and OpenCode
By
–
MiniMax M2.7 at home running on 4x DGX Sparks
— Ahmad (@TheAhmadOsman) 12 avril 2026
vLLM serving full BF16 weights, 200k context
OpenCode having the model monitor its own hardware and report thermals, tokens/sec, TTFT, and other runtime stats in real time
What benchmarks / workflows / things do you wanna see next? https://t.co/iCR8UsLs8E pic.twitter.com/I04c7j6UkgMiniMax M2.7 at home running on 4x DGX Sparks vLLM serving full BF16 weights, 200k context OpenCode having the model monitor its own hardware and report thermals, tokens/sec, TTFT, and other runtime stats in real time What benchmarks / workflows / things do you wanna see next?