#llm
93 条相关内容
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
TencentCloud/TencentDB-Agent-Memory
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
KotlinLLM
Show HN: Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO)
LLMs can't trade and higher reasoning doesn't help
Everyone is building LLM routers, we deprecated ours
Predictive Speculative KV Replication for Bursty LLM Inference
alibaba/open-code-review
Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Go LLM SDK for streaming, tool-calling AI backends (plus frontend React lib)
An LLM-assisted security review of GlobaLeaks: 41 findings for $3,140
LLM Honeypot
GCC to Decline Any Significant Contributions Made via AI/LLMs – Except for Tests
My Local LLM Scored 6/6. It Was Wrong Every Time
Now is the time to give LLMs access to the ACM digital library
Don't ask an LLM for a confidence score
"Uncensored" open LLMs are measurably more optimistic than their base models
OpenReviewer: A Specialized LLM for Generating Critical Scientific Paper Reviews
Show HN: Writekin – fine-tune a local LLM on your own writing, on your Mac
ASD-STE100 Simplified Technical English for LLMs
Running a 28.9M parameter LLM on an $8 microcontroller
LLM Usage in Debian: Three Proposals
2x, not 10x: coding with LLMs in 2026
Becoming a Research Engineer at a Big LLM Lab
Hetzner is working on LLM Inference
Debian launches competing General Resolutions on LLM usage in Debian code
GR: Ban LLM Contributions from Debian
A production-grade OCR pipeline on Kubernetes with vLLM and Rust
Protecting our FLOSS commons from LLMs
Petals: Run LLMs at home, BitTorrent-style
AstrBotDevs/AstrBot
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
AlexsJones/llmfit
Hundreds of models & providers. One command to find what runs on your hardware.
Can a MUD evaluate LLMs? A $99 proof of concept
Anthropomorphism in Children's Interactions with LLM Chatbots
Show HN: Millwright – Rust-based, self-hosted LLM router
Proxy for OpenAI Codex and Claude Code, use any LLM with those apps
LLMs Will Cheese Your Types: Fighting Back in Haskell
kvcache-ai/ktransformers
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
DoorDash 如何打造了一款不完全依赖大型语言模型（LLM）的 AI 购物助手
LLM-Based Hierarchical Topic Modeling Tool
Controlling Reasoning Effort in LLMs
WAIC五位首席科学家交锋：多模态是LLM的“外挂”，还是下一代智能的“灵魂”？
LLM-Integrated Multivariable Calculus Course
In-House LLM Serving at Netflix
The Economic Mirage of Local LLMs
Show HN: ride-recap, teaching a LLM my taste to automate cycling highlights
Shubhamsaboo/awesome-llm-apps
100+ AI Agent & RAG apps you can actually run — clone, customize, ship.
The LLM Critics Are Right. I Use LLMs Anyway
Detecting LLM-Generated Texts with “Classical” Machine Learning
1-Bit LLM in the Browser
Can LLMs Perform Deep Technical Comprehension of Computer Architecture Papers
Ask HN: Who gets credits on big math questions solved by LLMs?
DSLs Enable Reliable Use of LLMs
LLM Networking with MikroTik
面向 Agentic 负载的下一代 LLM 推理引擎设计实践｜AICon深圳
Guardian Angels: LLM Personalization for Productivity and Security
Building Food Metadata with LLM Juries
Show HN: Low-latency local LLM runner via OpenJDK Panama FFM (Java 22)
DSLs Enable Reliable Use of LLMs
Show HN: MemStitch – Zero-copy context bridging for vLLM (25x TTFT speedup)
I love LLMs, I hate hype
Mechanistic interpretability researchers applying causality theory to LLMs
Ask HN: How do you use LLMs for private discussions?
Mesh LLM: distributed AI computing on iroh
Stop Telling Me to Ask an LLM
unclecode/crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
ZhuLinsen/daily_stock_analysis
LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.
vLLM 针对多模态模型的推理优化实践｜AICon深圳
I think I have LLM burnout
LLMs for technical editing: The good, the bad, and the ugly
Target 推出基于 LLM 的语义匹配系统，提升营销预测流程效率
Show HN: Onboard-CLI, a LLM powered and AST-based tool to visualize codebase
Agentic test processes, LLM benchmarks, and other notes on agentic coding fr
Show HN: Foreman, a self-hosted LLM gateway for cost aware model routing
Show HN: Frugon – Find which LLM calls a cheaper model could handle (local, MIT)
Reinforcement Learning with Metacognitive Feedback Elicits Uncertainty in LLMs
CoplayDev/unity-mcp
Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Show HN: LLM Thought Visualization
Show HN: Otari: your open-source LLM control plane
Show HN: Sidenote – comment on your rendered blog, an LLM writes the Git diff
harry0703/MoneyPrinterTurbo
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.