Search
vibetime-cli
iamnotstatic
Track what you ship in AI coding sessions
proxy-acpx-x
clonn
ACP adapters for Claude Code, Codex, and Gemini CLI — proxy-acpx-x where x is the CLI name
@xinsd/cli-notice
xinsd
npx installer for CLI Notice Codex, Gemini, and Qwen voice reminder integrations.
sourceloop
lteawoo
NotebookLM-centered research orchestration pipeline
@rafaelsene01/contextual
rafaelsene
Generate context-aware prompts from your codebase using semantic embeddings — works with LM Studio, Ollama, OpenAI, Google, Mistral and more.
...morecommand-gpt
sukhwinder-i0
A CLI tool that converts plain English into shell commands using AI
opencode-local-provider
goniz
OpenCode plugin that adds a 'local' provider with auto-detection for Ollama, LMStudio, llama.cpp, vLLM, and Exo
sigmagen
SigmaGen Contributors
AI-powered Sigma rule generator using MITRE ATT&CK and RAG
@ollamaduct/gateway
decimozs
A lightweight, local-first AI gateway for Ollama with workspaces, cost tracking, and privacy controls.
yyr-skills
Yeshwanth's Claude Code skills
todocs
Static-analysis documentation generator for project portfolios — WordPress-ready markdown articles without LLM
ModelStash
BytePengwin
A Python wrapper for OpenAI-compatible APIs with cost tracking and async/sync support
@strav/brain
strav
AI module for the Strav framework
local-llm-wrapper
Local LLM wrapper (import local_llm_wrapper) with a stable text-in text-out API.
django-pragmatic
Pragmatic Mates
Pragmatic tools and utilities for Django projects
splunk-otel-instrumentation-crewai
OpenTelemetry CrewAI instrumentation
ragcheck
Lightweight, reference-free RAG evaluation. No ground truth needed.
zerokv-neo
ZeroKV-Neo: Adaptive Polar + QJL KV cache compression for Large Language Models — production-ready with vLLM, CLI, and Docker
...morespectral-kv
Hkshoonya
Up to 28x KV cache compression for LLMs via spectral SVD projection
clauthing
Wrapper to launch Claude Code in a dedicated kitty terminal with tmux