Search
test-fortress
avi770
Test Fortress — 23-agent multi-agent testing orchestration framework
ochead
ryanskidmore
Enterprise-grade OpenCode plugin with micro-plugin architecture and multi-agent orchestration
drex-core
r3ap3redit
Autonomous multi-agent AI coding engine with RAG+Grep and execution verification.
insight-ai
piyush-666
AI-powered codebase analysis in your terminal
delta-prune
karesansui
LLM context contradiction detector and pruner — give your AI a sleep cycle
@praesidia/neurogent
praesidiadev
Run a team of AI experts in your terminal. Build and deploy production-ready A2A agents.
smriti-cache
Semantic and exact caching for LLM calls — cut costs by catching duplicate and similar prompts.
@delta1035/ccs-cli
delta1035
AI CLI Tool Manager - Switch between Claude, Codex, Gemini, and more
@o-lang/agent-memory
blackgenius007
Unified agent memory resolver for O-Lang. Combines short-term chat memory and long-term facts with deduplication and scoring.
...moregopherbase
sankhyahrick
The official JavaScript/TypeScript client for GopherBase.
@gsep/adapters-llm-ollama
luisvelmarketing
Ollama adapter for GSEP — use local LLMs with GSEP
@dugleelabs/copair
sharma02gaurav
Model-agnostic AI coding agent for the terminal
meowcube
cons0leweb
MeowCube AI — coding assistant for the terminal. Every model, one command.
onlinellm-claw
xlvlxn
OpenClaw plugin — routes all LLM calls through OpenRouter (supports Grok, Claude, Gemini, GPT, DeepSeek, etc.)
@launch11/srgical
paul.e.gradie
A polished local-first CLI for planning and executing long AI-driven delivery sequences.
claude-mobile-bridge
uladluch
Lightweight bridge between Claude Code CLI and your mobile app via Supabase
@openteams-lab/openteams-web
caleb196x
OpenTeams - Run agents as one team, multiply your efficiency in the AI era.
demo-composer
andrewshawcare
Generate narrated demo videos from Cucumber BDD tests using Playwright and Gemini AI
@saltcorn/bootstrap-prompt-theme
christianhugoch
Bootstrap 5 layout plugin with LLM-generated CSS overlay
arbis-llmwrap
Decorator to wrap LLM calls for production use with flexible prompt binding.