DBDelve
Dive deep into your data. A fast, native, multi-engine database client written in Rust. Free and open source, no telemetry.
llama-modchip
Social buzz #21Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
Translation pending
Developer toolsGitHub @synchopateSelf-installOwner unconfirmed
Open GitHub repository
Paste into Claude or ChatGPT for installation instructions suited to your environment.
View prompt
Have you tried it? One tap is enough. No sign-in needed.
Buzzing on social · #21 now · 2 sources
Hacker News · 483 points · 207 comments
HN 483 points · 207 commentsLlama-modchip: 284B DeepSeek on 64GB RAM, no GPUNov 8 · Shared by someone elseDiscussion ↗
Checked Nov 13, 22:16 · Scores are copied from each platform at the last check. We don’t copy post bodies or comments, and deleted posts disappear here too.
- Access
- Self-install
- Runs in your environment
- Listed on nomorevibe
- Nov 13
Repository information has not been collected yet.
Updates0 updates
AllNo updates detected yet. GitHub releases will appear here.
Trending in Developer tools
GitHub star growth between the latest completed 8-hour observations
Motty
原生桌面 SSH 工作台：终端、SFTP/SCP、端口转发、VNC 与 RDP 远程桌面、AI 助手都在一个窗口里。Go 编写，没有 Electron，空闲时保持安静。免费开源，支持 macOS、Windows 和 Linux。
Translation pending
BigMoeOnEdge
Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behin
Translation pending
Free, open tools for AI safety
Sandbox AI agents, watch what they do with a hidden Observer, and measure it with evals. Open source, local, with evidence anyone can check.
oh-my-agent
The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.