MIDREAL

Hot on Hacker News

updated 63 minutes ago

Category: All Coding agents MCP AI video Local AI Developer tools Self-hosted Models Skills

Sort: Default order Stars gained, 7d Stars gained, 24h HN points

More filters

Language: All C++ Python TypeScript

Topic: All ai-agent ai-coding-assistant anthropic aws claude-code cli codex coding-agent command-line computer-vision devtools glm harness hermes inference llm llm-serving mcp megakernels neuron nki ollama openai openai-api productivity shell terminal trainium tui typescript

# Project Verdict Hype Reality Gap Stars gained, 7d Stars gainedStars gained over the window named in the column header. 24h is the change since our reading from at least 24 hours ago, 7d the change since our reading from at least 7 days ago. Blowing up and Hot on Hacker News show 7d, New to our radar shows 24h. More on the methodology page and HN points HN pointsHacker News points added up across posts that mention the project, published in the last 7 days. Signal SignalOne label per project that states a measured fact. It is not a verdict. The first rule that matches wins, and a missing number never triggers a rule. Archived: The repo is archived by its owner. Gone quiet: No commits in more than 90 days. Surging: At least 1,000 stars gained in 7 days, or at least 300 in 24 hours. Accelerating: This week's star gain is at least 3x the project's usual weekly gain (average of the 4 weeks before), and at least 50 stars. Slipping: The star count fell over 7 days, or gained nothing in a week when it usually gains. Cooling off: Usual weekly gain is at least 50 stars and this week's is under 40% of it. More talk than stars: At least 150 Hacker News points in 7 days and fewer than 200 stars gained in 7 days. Quiet climber: At least 300 stars gained in 7 days and no Hacker News points. Being talked about: At least 50 Hacker News points in 7 days. Watching: None of the above. Nothing stands out yet. More on the methodology page
1 lookatmyquant

A quantization compiler that delivers 12× lower KL than Q4_K_M at the same file size

TOO EARLY 99 39 +29 to +71 - 440 pts Being talked about
2 tamserve

Live, multi-camera object tracking with SAM3, SAM 2 and EdgeTAM, on one GPU or many. One m...

OVERHYPED 100 47 +53 - 123 pts Being talked about
3 trnrt

The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-...

OVERHYPED 97 49 +48 - 54 pts Being talked about
4 agav

Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run t...

REAL 96 83 +14 - 27 pts Watching
5 Tiny-2.1

Language model for DOS that fits on a floppy disk

TOO EARLY 96 28 - 4 pts Watching
6 samir-vllm

small LLM inference engine from scratch, w/ 6+ hours of youtube tutorials & 85+ pages of h...

TOO EARLY 92 20 +21 1 pts Watching