Search

Powerlevel10k-style prompt for pi — reuses your ~/.p10k.zsh colors, icons, and git formatting

Real-time voice agent engine: turn taking, barge-in, voice activity detection and call screening, independent of any telephony or AI vendor. Pairs with @nolag/voice so the call can reach a larger orchestrator for knowledge and tools.

Chatbase Voice SDK for the browser — real-time voice sessions with your Chatbase agent

Microsoft MarkItDown as a DeepSeek Harness tool: convert PDF, Word, Excel, PowerPoint, HTML, CSV, EPUB, or a URL into Markdown the model can read.

Pi skill + subagent: three parallel code-review channels (OCR / Standards / Spec) reviewing the same diff bound under one scope, then an oracle deduplicates, resolves conflicts and re-grades them into a single adjudicated report (00-adjudication.md). Pure

Unofficial standalone Scrypted Tuya plugin with maximum advertised camera quality selection and Smart Life P2P bridge integration.

Read your agent CLI session logs, score sessions for cost and friction, and turn expensive patterns into reusable skills, sub-agents, hooks, and instruction files.

Autonomous DevOps & Infrastructure Orchestrator powered by Ray and Brain

Pure JSON operations engine for Karzoun automations (browser + Node safe)

A developer-friendly spaced repetition engine for vocabulary building

Extension for the pi coding agent: enforce a context token budget (defaulting to the model's configured context window; 200k when unknown) by forcing compaction, including mid-turn during long tool loops, instead of riding long-context models up to their

pstack for Pi. Poteto's rigorous engineering workflow ported to the Pi Agent Harness: 50 skills and 2 agents, plus an extension that wires the mode into Pi settings, sessions, compaction, and the context window.

Ollama (local + Ollama Cloud) and LM Studio providers for the pi coding agent - live model discovery with real capabilities (tools/vision/thinking) and context windows.

Raise Node's HTTP timeouts for the whole DeepSeek Harness process so slow local models are not cut off at 5 minutes

Run ComfyUI workflows with GPU execution; use AI image models and AI video models including FLUX 2, Seedance 2.5, Wan 3.0, LTX 2.5 and Seedream 5.0; track LoRA training.

SID: generator, parser, formatter, and checksum verifier

Perceptual colour utilities: CIEDE2000 distance, WCAG contrast, OKLCH lightness scales, and nearest-named-colour.

React bindings for the 1mn SDK — embedded product analytics, session replay, error tracking, user management, and customer feedback (PostHog/Sentry-like). Self-contained: npm install + <OnemnProvider>, no snippet.

web3-think

Migrate an email account to MillionSend: contacts, segments, topics, templates, webhooks, domains and suppressions — read from the source provider, written to your MillionSend instance, re-run safe