01
LLM & models
deepseek-ai/DeepInfer
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
★ 14.7K▲ first snapshot
Spotted on HN @ggcr
Category
LLM & models
Models, inference servers, fine-tunes, and the libraries people use to run them locally or in production.
18 repos
AllAgents & orchestrationMCP serversLLM & modelsDev toolsVibe codingUI & componentsDesignGames & funOther
- 02Agents & orchestrationLLM & models
ayghri/i-have-adhd
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
★ 58.1K▲ first snapshot
Spotted on HN @domhudson
- SponsoredSlot 1
Your brand here
Show a dev tool, agent, or design product to people deciding what to try this week, plus a line in the Monday email.
Sponsor this spot2 featured spots a week · Open
- 03LLM & modelsDev tools
antirez/h3.c
MiniMax H3 inference engine for Mac computers
★ 2,935▲ first snapshot
Spotted on HN @swyx
- 04LLM & models
angelos-p/llm-from-scratch
Train Your Own LLM From Scratch A hands-on workshop where you write every piece of a GPT training pipeline yourself, understanding what each component does…
★ 3,432▲ first snapshot
Spotted on HN @iamnotarobotman · HN @kristianpaul
- 05LLM & models
marcelroed/gigatoken
Language model tokenization at GB/s
★ 4,134▲ first snapshot
Spotted on HN @syrusakbary
- 06LLM & modelsAgents & orchestration
Trystan-SA/claude-design-system-prompt
Reverse-engineered system prompt and skill library that turns an LLM into an opinionated, accessibility-aware, AI-slop-resistant design collaborator.
★ 2,005▲ first snapshot
Spotted on HN @handfuloflight
- SponsoredSlot 2
Your brand here
Show a dev tool, agent, or design product to people deciding what to try this week, plus a line in the Monday email.
Sponsor this spot2 featured spots a week · Open
- 07Agents & orchestrationVibe coding
weave-os/router
Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.
★ 5,596▲ first snapshot
Spotted on HN @adchurch
- 08LLM & modelsAgents & orchestration
stanford-cs336/assignment1-basics
Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch
★ 3,052▲ first snapshot
Spotted on HN @prakashqwerty
- 09Agents & orchestrationLLM & models
antoinezambelli/forge
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows
★ 2,260▲ first snapshot
Spotted on HN @zambelli
- 10MCP serversAgents & orchestration
MinishLab/semble
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
★ 6,254▲ first snapshot
Spotted on HN @Bibabomas
- 11LLM & modelsAgents & orchestration
antirez/ds4
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
★ 24K▲ first snapshot
Spotted on HN @tamnd
- 12Agents & orchestrationVibe coding
aattaran/deepclaude
Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper.
★ 2,273▲ first snapshot
Spotted on HN @alattaran
- 13LLM & models
arman-bd/guppylm
A ~9M parameter LLM that talks like a small fish.
★ 3,894▲ first snapshot
Spotted on HN @armanified
- 14Games & funLLM & models
love2d/love
LÖVE is an awesome 2D game framework for Lua.
★ 8,850▲ first snapshot
Spotted on HN @cl3misch
- 15LLM & models
haykgrigo3/TimeCapsuleLLM
A LLM trained only on data from certain time periods to reduce modern bias
★ 1,996▲ first snapshot
Spotted on HN @admp
- 16LLM & models
DGoettlich/history-llms
Information hub for our project training the largest possible historical LLMs.
★ 1,805▲ first snapshot
Spotted on HN @iamwil
- 17Games & funLLM & models
borndotcom/react-native-godot
React Native Godot - Embed Godot Engine in React Native apps
★ 2,694▲ first snapshot
Spotted on HN @Noghartt
- 18MCP serversAgents & orchestration
Aherontas/Pycon_Greece_2025_Presentation_Agents
Tech Trends Agent 🚀 **A robust, scalable AI-powered web service combining FastAPI, Pydantic-AI, and MCP servers** This project demonstrates how to build a…
★ 94▲ first snapshot
Spotted on HN @Aherontas