#llm

alibaba/open-code-review

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

Tencent/WeKnora

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

tashfeenahmed/freellmapi

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

Why do LLM pelicans look like this?

Linus Torvalds's first LLM-assisted patch series

lyogavin/airllm

AirLLM 2.8T LLM inference with single 4GB GPU

microsoft/BitNet

Official inference framework for 1-bit LLMs

Launch HN: Consus (YC F24) – LLM gateway for companies handling sensitive data

Show HN: Jevcrawl – A web crawler for AI agents with no LLM in the crawl loop

Jev handed our LLM the wrong page a tenth as often as our embeddings

Janas: Run LLMs larger than RAM by streaming experts from SSD

The gap in shared understanding of LLM capability is widening

Show HN: LLMxRay an open-source observability tool for LLMs

multica-ai/andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

alibaba/open-code-review

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

BerriAI/litellm

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

open-slopware – Alternatives to FOSS projects choosing to use LLMs/AI

Port of the TypeScript compiler, checker and lsp to Rust, by LLM

Sub-1-Bit LLM Compression via Latent Factorization

We have LLMs now. Why are the docs still wrong?

Write Like It's 1866: LLMs Relearn Telegraphese

I'm not paying $20 for ChatGPT or Claude because a free local LLM does

LLMs and Data Poisoning Are Weaponized to Manufacture Consensus

LLMs may have helped my RSI

[分享创造] 测了 1000 个中文大站的 llms.txt，只有 30 个放了真正的文件

[分享创造] 给已有网站做了个 llms.txt 生成器，欢迎试用

earendil-works/pi

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

From the creator of Redis; run LLM locally with ds4

Greg Kroah-Hartman – Security in the LLM Age [video]

Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers

Rai: CPU-only LLM inference engine in pure Rust

jingyaogong/minimind

🧠 Train a 64M-parameter LLM from scratch in just 2h!

Kcc, a C compiler built solo with an LLM on $100/month boot Linux kernel

Show HN: Strata – an expressive semantic layer that can say no to your LLM

ahujasid/mcp-for-blender

Community plugin to control Blender 3D with any LLM of your choice

MicroLLM Lab – Try 7 tiny LLM's in the browser

2026 in LLMs (So Far)

2026 in LLMs (So Far)

"As a Language Model": Chat Template Switches LLM Self-Referential Voice

DoorDash 借助多 Agent LLM 系统清理 6 万个 Feature Flag

MakazhanAlpamys/Soup

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

NVIDIA/Model-Optimizer

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

How to keep enjoying programming in a world of LLMs

A single function Jev-like wrapper for LLMs, including vision models

Generate fonts where every LLM token is the same width

shy3130/tick-stock-panel

TSP自托管、零运维的 A 股「选股 + 监控 + 回测」量化工作台 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源

Best LLM for every budget, updated daily

Using LLMs to trace alchemical knowledge and decode 17th century letters

Mercury 2.5 LLM hits 770 tokens per second

给Codex配上Jev，直接起飞。

在 Codex 中安装 Jev 判断模型实测，Agent 决策比 LLM 快 40-200 倍，便宜 40-400 倍，输出 Token 免费

Jev vs. LLMs on 770 "Am I the Asshole?" posts

Jev introduces a new shape of LLM

Ask HN: When is fine-tuning a small LLM worth it?

纯 LLM 做 NL2SQL 总不准？金融场景为什么必须做本体工程

You can use any LLM just like JEV

“只剩一群用 LLM 的菜鸟”：顶级黑客怒退 PS5 Linux 项目，几个月心血全打水漂

Pirate Face Rescues LLM Models from Deletion

Show HN: jevals – replacing LLM judges with typed Jev decisions

Stepfun Step 5 Preview (LLM): On AA Pareto frontier

The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It

Grab 智能体框架 LLM-Kit 加速 AI 智能体生产部署

How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip

Cache-to-Cache: Direct Semantic Communication Between LLMs (2025)

The Implications of Linguistic Illegibility for LLM Security

My Thoughts on AI and LLMs

Tencent/WeKnora

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

How to Write with an LLM

I Don't Like LLMs

Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data

LLM Classification Is Feature Engineering

PS5 Linux lead quits: "a bunch of noobs using LLMs" that "they don't understand"

Learning Programming in an Age of LLMs

Breaking the 1.58-bit Barrier for Ternary LLMs

Why I'm still bearish on LLMs after Navier-Stokes

[分享发现] 能用的免费白嫖的 ai llm 越来越少

How much of F-Droid is LLM generated?

Learning to solve hard problems in RL for LLMs by never giving up

GRP-Obliteration: Unaligning LLMs with a Single Unlabeled Prompt

Building your first LLM API call in Python (step by step)

Show HN: Let agent read files with secrets while redacting values for LLM contex

不下班的经营者：把 LLM-as-Judge 做成会自我校准的评估闭环｜QCon上海

TauricResearch/TradingAgents

TradingAgents: Multi-Agents LLM Financial Trading Framework

[奇思妙想] 如果 LLM 冲刺 AGI 失败了，以后哪里还会有高质量的代码、文本和其他数据？

OpenArch – PyTorch implementations of modern LLM architectures

When LLM judges agree, should we believe them?

LLMs are real, AI is fake

1. 从零开始搭建一个 AI Agent —— LangChain + TypeScript 实战手记

从零开始搭建一个 AI Agent —— LangChain + TypeScript 实战手记 目录 项目初始化：先把骨架搭起来 理解 Agent：它和普通 LLM 调用有什么不同？