Run 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).
Repository Index
65,264 visible repositories in the index
289–312 of 472 · Most stars
Teaching tool and debugging aid in context of references, mutable data types, and shallow and deep copy.
- python3-data-visualization-debugging-education
A Windows your apps recognize.
- cmake
- compatibility-layer
- cpp
- cpp20
pickleDB is an in memory key-value store using Python's orjson module for persistence. It can also use SQLite instead of orjson if needed.
- python
- python3
- pickledb
- database
Neo4j Bolt driver for Python
- python
- graph-database
- driver
- neo4j
TranslatedVoice AI girlfriend for DeepSeek Harness: Whisper voice input + Qwen3-TTS voice cloning + sentence-level streaming read-aloud + digital human animation window. Two modes, interrupt and queue; speaking interrupts it.
- ai-girlfriend
- companion
- deepseek-harness
- digital-human
Feature-rich single-binary file server for red teamers and developers. HTTP/S · WebDAV · FTP/SFTP · SMB · LDAP/S · NTLM hash capture · DNS/SMTP callbacks · TLS · Auth · Share links. A powerful python3 -m http.server replacement.
- golang
- http-server
- https-server
- ctf
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.
- anthropic-api
- cuda
- gemma
- gguf
Hacking Toolkit
- network-analysis
- networking
- scapy
- python3
The Swiss-Army-knife command-line tool for plotter vector graphics.
- generative-art
- pen-plotters
- svg
- vector-graphics
Python Framework to analyse Git repositories
- msr
- python3
- git
- mining-software-repositories
安卓 TV 红果短剧客户端
A Tutorial for Setting Python Development Environment with VScode and Docker
Develop inside docker containers, just like VSCode
TranslatedNot a Q&A bot, but a digital twin that can actually get work done. Agents and project context are shared, so all project members can work together. At the same time, agents, like people, abstract and summarize experience from materials or work into the project context.
- agent
- agent-framework
- agent-orchestration
- agent-skill
A standalone SIGMA-based detection tool for EVTX, Auditd and Sysmon for Linux logs
- sigma
- python3
- evtx
- sigma-rules
🤖 An open source chat-ops bot framework
- bot-framework
- opsdroid
- botkit
- python3
Implementing LLM architectures from scratch in PyTorch
- gemma3
- llama4
- llm
- moe
A simple, direct, ultra-thin CLR library for high-performance Win32 Native Interop
- dotnet
- dotnetcore
- winapi
- directx
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.
Cloud Native Presentation Slides with Jupyter Notebook + Reveal.js
- jupyter-notebook
- nbconvert
- reveal-slide-decks
- reveal-js
SDK for building cross-platform desktop apps in ANSI-C
- c
- cross-platform
- win32
- cocoa
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
- avx2
- c
- cpu-inference
- gguf
Python live trade execution library with zipline interface.
- python3
- python
- algorithmic-trading
- quant