-
engraft-ngram Public
ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, verified on llama.cpp GGUF (Qwen3.8-Flash-Next).
-
ds4 Public
Forked from antirez/ds4DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
C MIT License UpdatedSep 18, 2026 -
llama.cpp Public
llama.cpp fork with the fork-ple branch: PLE n-gram table overlay (.pleo) and llama-ple-lens for ENGRAFT (github.com/fulvian/engraft-ngram)
C++ MIT License UpdatedSep 8, 2026 -
pi-com Public
Minimal Pi-to-Pi communication for independent coding-agent sessions over a private NATS JetStream bus
TypeScript MIT License UpdatedAug 24, 2026 -
gemma4 Public
Resolve Gemma4 loading issues with LM Studio or find alternative solutions with llama.cpp Vulkan/ROCm support for optimal inference performance
Python UpdatedAug 24, 2026 -
jai Public
Journeys with AI - Unified Me4BrAIn + PersAn monorepo. Hybrid routing LLM engine + conversational AI frontend.
Python UpdatedAug 24, 2026 -
wifi-switch Public
WiFi auto-switch daemon for Linux — monitors internet connectivity and switches between known networks based on HTTP reachability
Python UpdatedJul 2, 2026 -
github-discovery Public
MCP-native agentic discovery engine that finds high-quality GitHub repositories independent of popularity. Tiered scoring pipeline: discovery → screening → deep LLM assessment → anti-star bias rank…
-
ollama-bridge Public
Transparent Python proxy that routes Claude Code API calls to Ollama cloud when Anthropic token budgets exceed configurable thresholds
Python UpdatedMay 11, 2026 -
kiloclaw Public
Kiloclaw - AI assistant fork da KiloCode con memory 4-layer, multi-agency orchestration e policy-first execution
TypeScript MIT License UpdatedApr 15, 2026 -
turboquant-local Public
TurboQuant KV-cache optimization for AMD Radeon 890M (gfx1150) with Vulkan backend - work in progress
-
llama-cpp-turboquant Public
Forked from TheTom/llama-cpp-turboquantLLM inference in C/C++
C++ MIT License UpdatedApr 8, 2026 -
verbalizer Public
Automatic audio recording, transcription, and documentation for Google Meet and Microsoft Teams calls
HTML UpdatedMar 27, 2026 -
llm-training-mx250 Public
LLM training scripts optimized for MX250 2GB GPU with 4-bit quantization and LoRA
Python UpdatedMar 23, 2026 -
9router Public
Forked from decolua/9routerUniversal AI Proxy for Claude Code, Codex, Cursor | OpenAI, Claude, Gemini, Copilot
JavaScript UpdatedMar 14, 2026 -
freqtrade-trading-bot Public
Professional algorithmic trading bot built with Freqtrade - Multi-strategy, multi-timeframe cryptocurrency trading system with comprehensive backtesting capabilities
-
nba-predictor-streamlit Public
Advanced NBA Game Prediction System with ML
-
devstream Public
Claude Code proactive framework: task-forced workflow + semantic memory + AI agent team
-
exc-to-pdf Public
Excel to PDF converter with advanced features and CLI interface
-
devflow Public
Sistema intelligente di gestione della memoria e dei task di agenti di coding AI
TypeScript UpdatedSep 27, 2025 -
-
-
-




