Hackernews posts about Qwen3 Coder

Every Hardware Deserves a Coder: Devstral Small 2 24B and Qwen3 Coder 30B (byteshape.com)

2 points by dajonker 20 days ago | discuss
Show HN: oMLX – coding agents on local LLMs without the painful reprefill (github.com)

3 points by jundot 25 days ago | discuss
Show HN: LiberClaw, deploy AI agents that run 24/7 on their own VMs

2 points by moshemalawach 16 days ago | 1 comments
Show HN: Luna Agent – Custom AI agent in ~2300 lines of Python, no frameworks (nonatofabio.github.io)

1 points by nonatofabio 13 days ago | discuss
Show HN: Triplecheck – Review your code free with local LLMs (github.com)

1 points by raullen 15 days ago | discuss
Show HN: An experiment in giving coding agents long-term memory

1 points by yacc2 6 days ago | 2 comments
Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training (github.com)

252 points by xlayn 2 days ago | 82 comments
Show HN: ZSE – Open-source LLM inference engine with 3.9s cold starts (github.com)

58 points by zyoralabs 23 days ago | 9 comments
Giving local LLMs read-only institutional memory before task execution

2 points by LavaDMan 12 days ago | discuss
Show HN: VerdictMail – IMAP daemon that uses LLM reasoning to catch phishing (github.com)

2 points by ascarola 26 days ago | discuss
Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs (dnhkng.github.io)

491 points by dnhkng 11 days ago | 125 comments
Launch HN: IonRouter (YC W26) – High-throughput, low-cost inference (ionrouter.io)

71 points by vshah1016 8 days ago | 37 comments
Show HN: On-device meeting transcription for your Mac

6 points by paynedigital 3 days ago | discuss
Show HN: LLMadness – March Madness Model Evals (llmadness.com)

5 points by rjkeck2 2 days ago | 2 comments
My AI didn't misread a receipt – it fabricated one from scratch

4 points by Raywob 3 days ago | discuss
Show HN: Open-Jet – self-hosted Agentic TUI for air-gapped Jetsons (www.openjet.dev)

2 points by lforster 19 days ago | 2 comments
Sumi – Open-source voice-to-text with local AI polishing

2 points by alkd 12 days ago | discuss
Show HN: I wrote an LLM inference engine in pure Go – 48 tok/s zero dependencies (github.com)

2 points by computerex 14 days ago | discuss
Show HN: PLAI.chat – Multi-model AI chat that doesn't store your conversations (plai.chat)

2 points by coderai 19 days ago | discuss
Show HN: Voxlert – SHODAN and the StarCraft Adjutant narrate my agent sessions (github.com)

1 points by settinghead 5 days ago | discuss
Show HN: OpenJet – An offline agent harness for memory-constrained edge hardware (github.com)

1 points by lforster 6 days ago | discuss
Show HN: Agentic Metric – top for your AI coding agents (token, cost tracking) (github.com)

2 points by MrQianjinsi 12 days ago | discuss
Demo of an indie AI collaboration app – beyond Codex and Claude Code desktop

1 points by seeksky 23 days ago | 1 comments
AI Code Review Gets Better When I Ask Models to Debate: Claude, Gemini, Codex (milvus.io)

23 points by Fendy 22 days ago | 3 comments
Looking for Feedback on a Computer Agent

2 points by alphabetnerd 15 days ago | discuss
Replacing Anthropic's API with 2x 3090s. Claude Code on a local 80B Qwen model (twitter.com)

1 points by ianlpaterson 25 days ago | discuss
Show HN: Claude-consensus – Multi-model code review plugin for Claude Code (github.com)

1 points by k_git 14 days ago | discuss
Show HN: Hydra – Real-time ops dashboard for developers running AI agents (github.com)

1 points by marinerk9 14 days ago | 2 comments
Show HN: AgentArmor – open-source 8-layer security framework for AI agents (github.com)

10 points by AgastyaTodi 7 days ago | 6 comments
Show HN: Omni-Glass – Rust app that turns screen pixels into MCP tool calls (github.com)

3 points by goshtasb 27 days ago | 1 comments