Starred repositories
Control your Pi coding agent from your phone. Pair with a one-time QR code and chat with your local agent — even when you're away from your computer.
A local AI coding workspace for Claude Code, Codex, Cursor, OpenCode, Amp, Factory Droid, Pi, and OpenAI/Anthropic-compatible models.
PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
Desktop app to manage markdown knowledge bases
Low-level unprivileged sandboxing tool used by Flatpak and similar projects
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms
Speculative prefill for LLM inference: draft model fills KV cache, verifier accepts or rejects. Benchmarked on Llama-3-8B/70B.
Real-time terminal UI dashboard for monitoring vLLM
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
A GPU cluster manager that configures and orchestrates inference engines like vLLM and SGLang for high-performance AI model deployment.
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
Unified API for running OpenCode, Claude Code, Codex agents
The design language that makes your AI harness better at design.
A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.
MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenario…
Pi package that automatically routes each prompt to a configured model and thinking level.
Profile manager for pi coding agent — switch between curated sets of packages, skills, and extensions
Hallucination-prevention RAG system with verbatim span extraction. Ensures all generated content is grounded in source documents with exact citations.
Q&A system based on papers in the ACL Anthology and the VerbatimRAG system
Identify and evaluate hallucinations in LLM outputs using retrieval-augmented verification and semantic entropy scoring.
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…