Author

Agent Native

@agentnativedev

articles: 28
total claps: 5,543
top claps: 1,973
avg read: 9.6 min
paywalled: 28
active: 2024-08-24 → 2026-07-08

Wiki topics

LLM · Large Language Models · 22 AGT · AI Agents · 18 💻 · Programming · 9 🔓 · Open Source · 8 MM · Multimodal & Generative Media · 4 OPS · LLMOps & Inference · 4 EVAL · Evaluation & Benchmarks · 3 AI · AI · General · 2

Top tags

#agentic-ai ·10 #ai-agent ·8 #claude-opus ·4 #qwen ·3 #local-llm ·3 #gpt-5 ·3 #coding ·3 #claude-code ·3 #deepseek-v3 ·2 #deepseek ·2

AI TCH

AG Agent Native

Local LLMs That Can Replace Claude Code

Editor’s note: While hardware tiers remain valuable context for this article, we’ve published an updated list for the models themselves:

Jan 20, 2026 · 6 min read · 1,973 claps paywalled #minimax-m2 #qwen3-coder #deepseek-v3

AI TCH SPT

AG Agent Native

Qwen 3.5 35B-A3B: Why Your $800 GPU Just Became a Frontier Class AI Workstation

I have been running local models for a while now, and I thought I had a pretty good sense of where the ceiling was for consumer hardware.

Mar 01, 2026 · 10 min read · 1,134 claps paywalled #qwen-3 #claude-opus #claude-sonnet

Qwen 3.5 35B-A3B: Why Your $800 GPU Just Became a Frontier Class AI Workstation

AI TCH

AG Agent Native

Stop Asking What Model to Run. You Only Have 2 Options

When developers say “model X is dumb,” they often mean:

Jul 02, 2026 · 9 min read · 250 claps paywalled #open-source #qwen #kimi

Stop Asking What Model to Run. You Only Have 2 Options

AI TCH SOC

AG Agent Native

KubeClaw: OpenClaw for Adults

Secure defaults, pinned images, predictable upgrades, observability, and reliability for OpenClaw agents.

Mar 24, 2026 · 9 min read · 212 claps paywalled #openclaw #kubernetes #ai-agent

AI TCH

AG Agent Native

LLM Fine-Tuning Strategy: 4 Open Source Toolkits That You Should Know

With everything at our fingertips today, fine-tuning large language models (LLMs) can get overwhelming fast.

Jun 06, 2025 · 8 min read · 191 claps paywalled #fine-tuning #axolotl #unsloth

LLM Fine-Tuning Strategy: 4 Open Source Toolkits That You Should Know

MDA

AG Agent Native

GOT-OCR2.0 in Action: Optical Character Recognition Applications and Code Examples

I’ve been diving into GOT-OCR2.0 lately, and it’s pretty impressive.

Oct 31, 2024 · 7 min read · 184 claps paywalled #ocr-software #ocr #text-extraction

GOT-OCR2.0 in Action: Optical Character Recognition Applications and Code Examples

AI ART TCH

AG Agent Native

Open Source Perplexity: Perplexica is Self-Hosted AI Search With Citations

Perplexica is an open-source, AI-powered search engine inspired by Perplexity-style UX.

Jan 28, 2026 · 6 min read · 177 claps paywalled #perplexity #perplexity-ai #perplexity-deep-research

Open Source Perplexity: Perplexica is Self-Hosted AI Search With Citations

TCH AI

AG Agent Native

Latest Vision, Image and Language Models: Pangea, Ferret, OmniParser, Granite, Pixtral, Aya, SD 3.5

Recently, an influx of new model releases from all angles has felt like the floodgates of innovation bursting open.

Oct 29, 2024 · 16 min read · 173 claps paywalled #omniparser #pangea #ferret

Latest Vision, Image and Language Models: Pangea, Ferret, OmniParser, Granite, Pixtral, Aya, SD 3.5

AI TCH

AG Agent Native

Tiny Phi 3 Models Deliver GPT Power on Your Phone: Open Source and Ready for Production

You’ve been watching these language models get bigger and bigger, thinking, “How the hell am I supposed to run a language model on anything…

Aug 24, 2024 · 11 min read · 154 claps paywalled #small-language-model #phi-3-mini #gpt-4

Tiny Phi 3 Models Deliver GPT Power on Your Phone: Open Source and Ready for Production

AG Agent Native

10 AutoResearch Agents You Should Absolutely Know About

The next wave of AI agents will improve themselves against measurable goals.

May 07, 2026 · 9 min read · 152 claps paywalled #autoresearch #self-evolving-agent #agentic-ai

10 AutoResearch Agents You Should Absolutely Know About

AI TCH

AG Agent Native

LinkedIn’s Liger: The GPU Kernel Suite that Andrej Karpathy, Jeremy Howard, and Thomas Wolf Use for…

LinkedIn just open-sourced a collection of Triton-based kernels that are specifically designed for Large Language Model (LLM) training.

Aug 25, 2024 · 6 min read · 152 claps paywalled #linkedin #llm-finetuning #cuda

LinkedIn’s Liger: The GPU Kernel Suite that Andrej Karpathy, Jeremy Howard, and Thomas Wolf Use for…

AI SOC

AG Agent Native

ClawRouter: Anthropic charged me $4,660 — How I cut it 70% with smart LLM routing

Last month I opened my credit‑card statement and almost threw up. Anthropic charged me $4,660.87, just for AI APIs.

Feb 06, 2026 · 9 min read · 149 claps paywalled #openclaw #clawdbot #openclaw-bot

ClawRouter: Anthropic charged me $4,660 — How I cut it 70% with smart LLM routing

AI SPT MDA TCH

AG Agent Native

Outperforming Claude Code and Codex for Local LLM Workflows

Orchestrating a codebase on 5GB VRAM using a local Qwen3.5–35B-A3B (~25–30 tokens/sec through llama.cpp, 65k context, remaining layers…

Apr 18, 2026 · 11 min read · 131 claps paywalled #claude-code #xcode #gemma-4

Outperforming Claude Code and Codex for Local LLM Workflows

AG Agent Native

“This PDF hates OCR” — DeepSeek OCR 2 Reads Documents Like A Human

Your customer forwards an invoice PDF with the subject line: “why is this invoice scrambled?”

Feb 02, 2026 · 9 min read · 91 claps paywalled #deepseek #ocr #gemini-3-pro

“This PDF hates OCR” — DeepSeek OCR 2 Reads Documents Like A Human

AI TCH

AG Agent Native

GLM-4.7-Flash on 24GB GPU (llama.ccp, vLLM, SGLang, Transformers)

GLM-4.7-Flash is one of those rare open-weights releases that changes what “local-first” can realistically mean for coding + agentic…

Jan 22, 2026 · 6 min read · 89 claps paywalled #llama-cpp #vllm #sglang

GLM-4.7-Flash on 24GB GPU (llama.ccp, vLLM, SGLang, Transformers)

AI TCH

AG Agent Native

DeepSWE: Both Claude Opus 4.6 and 4.7 registered CHEATED on more than 12% of reviewed SWE-Bench Pro

For months, on public coding leaderboards, the frontier models looked close enough that engineering leaders could justify almost any…

May 27, 2026 · 8 min read · 66 claps paywalled #ai-agent #claude-code #openai-codex

DeepSWE: Both Claude Opus 4.6 and 4.7 registered CHEATED on more than 12% of reviewed SWE-Bench Pro

AI TCH

AG Agent Native

M5 Max 128GB, RTX 4090 or 2x 3090 for Local LLMs?

A single RTX 4090 or M5 MBP can already handle a serious amount of coding work with the right open model, the right quantization…

Apr 19, 2026 · 10 min read · 51 claps paywalled #m5-max #rtx-4090 #rtx-3090

M5 Max 128GB, RTX 4090 or 2x 3090 for Local LLMs?

AI ECO

AG Agent Native

Founder’s Open-Model Stack: GLM-4.7, Qwen3-VL, DeepSeek-V3.2, Kimi-K2, FLUX.2

If you’re building an AI product as a solo founder or a small team, you don’t need one “best” model.

Jan 23, 2026 · 7 min read · 47 claps paywalled #deepseek-v3 #deepseek #qwen

Founder’s Open-Model Stack: GLM-4.7, Qwen3-VL, DeepSeek-V3.2, Kimi-K2, FLUX.2

AI TCH

AG Agent Native

I’m Done Watching Agents Pretend to Understand Repos, Here’s the Fix

Understanding a codebase for agents is a search problem pretending to be reasoning.

Jul 05, 2026 · 8 min read · 45 claps paywalled #agentic-ai #coding #ai-coding-agent

I’m Done Watching Agents Pretend to Understand Repos, Here’s the Fix

AI TCH

AG Agent Native

Nemotron 3 Ultra Is Agent Factory

NVIDIA’s Nemotron 3 Ultra announcement is easy to misread.

Jun 01, 2026 · 17 min read · 28 claps paywalled #nvidia-nemotron #nvidia-llm #agentic-ai

AI MDA

AG Agent Native

60–95% Fewer Tokens with Claude Code and Codex

If you ever open the billing dashboard and you feel something cold, this article is exactly written for you.

Jun 20, 2026 · 18 min read · 20 claps paywalled #ai-agent #llm-caching #token-compression

60–95% Fewer Tokens with Claude Code and Codex

AI TCH

AG Agent Native

GLM-5V-Turbo Beats Opus 4.6 on Multimodal Benchmarks

GLM-5V-Turbo is Z.AI’s first multimodal coding foundation model, built for vision-based coding tasks.

Apr 02, 2026 · 12 min read · 20 claps paywalled #glm #claude-opus #claude-opus-4-6

GLM-5V-Turbo Beats Opus 4.6 on Multimodal Benchmarks

AI HUM LIF

AG Agent Native

Fable 5 Is COMPLETELY Wasted on Most Developer Workflows

A self-improving agent system gets better because everything around the model gets better, i.e., the environment compounds.

Jul 08, 2026 · 9 min read · 20 claps paywalled #claude-fable-5 #agent-harness #harness-engineering

Fable 5 Is COMPLETELY Wasted on Most Developer Workflows

AI MDA TCH

AG Agent Native

48GB VRAM: Local Coding Agents

Most developers asking about local AI hardware still frame the question in model-size terms.

May 21, 2026 · 8 min read · 19 claps paywalled #local-ai-deployment #local-agent #local-llm

AI ECO HUM TCH

AG Agent Native

He writes 94% less code, 20% cheaper and 27% faster.. and it works!

This month, a single-author repo called ponytail collected tens of thousands of GitHub stars in a couple of weeks on one promise: install a…

Jun 24, 2026 · 11 min read · 9 claps paywalled #ai-agent #tokenomics #token-economy