omp packages
-
Live elapsed time and a minimal completion timestamp for Pi's terminal UI.
-
Jev-backed tool guardrail for pi
-
Image generation tool for the pi coding agent (Codex / Grok / OpenAI Images)
-
Pi extension that scopes the providers visible in /model based on the working directory.
-
Reviewable implementation plans for the pi coding agent: the comprehensive-planning skill, the standards it routes to, and an extension that triggers, validates, and tracks the plan.
-
Coding profiles: inject a prompt file as a persistent system-prompt mode
-
Run root commands with a user-approved password prompt; audit every batch.
-
Scheduled actions for pi agents — prompts, shell checks, notifications, one-shots, and bounded polls
-
Render pi coding agent's footer with Oh My Posh — reuse your shell prompt's theme (powerline, palette, glyphs) plus pi context/model/tokens and other extensions' status chips.
-
Pi extension for spawning sub-agents via RPC for parallel task execution
-
Web search, URL fetching, GitHub repo cloning, PDF extraction, YouTube video understanding, and local video analysis for Pi coding agent. Supports OpenAI, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Crawl4AI, Jina, SE
-
Preview markdown files in Pi TUI overlay
-
pi 扩展:拦截 find 查询禁用路径、给 bash 补默认超时、守卫循环
-
Deterministic frozen-snapshot code reviews for Pi.
-
Billing engine for the serverless agency — a pi extension that meters agentic dev work like cloud compute and invoices it like a timesheet.
-
Pi coding agent extensions — security hardening, agent teams and more
-
Pi extension: switch between several Claude Pro/Max OAuth logins with /account, and use extra ChatGPT (Codex) logins as parallel openai-codex-<name> providers
-
CJK IME fix for pi: turn a leading 、 into / and switch to your English input source.
-
A pi extension for compacting and inspecting agent context.
-
pi usage ledger and local browser dashboard (tokens, CNY cost, heatmap). Zero runtime dependencies.
-
Pi compaction that reads the conversation's prompt cache instead of paying full input price
-
User-owned Markdown memory with durable maintenance, Pi integration and local stdio MCP access.
-
Pi extension wrapping the GitHub gh CLI as a single typed tool (direct CLI, not MCP).
-
Per-turn session router for Pi: Jev decides whether a prompt should continue, fork, or start a new session before it pollutes the context
-
Quality-first, concrete-model routing before every Pi model step
-
Adversarial peer review for Pi: /peer-review diff-reviews every change since the last check under an adversarial frame (task, executor's claim, real diffs, claim audit) and passes BLOCKER/RISK findings to the model as untrusted claims. Also ships the fail
-
Live tokens-per-second in pi's footer first line: sliding-window tok/s while streaming, exact last-turn average at rest.
-
Context-compression proxy that lets AI coding agents run for days — billions of tokens through one context window. Sits between any agent (Claude Code, Codex, Cursor, Aider, …) and its model API, folding consumed conversation into reversible, prefix-cache
-
Pi extension that exposes web search through the local Codex CLI
-
Pi extension for delegating work to autonomous subagents in Herdr panes
-
Synchronize new chat-model IDs from an OpenAI-compatible /models endpoint into Pi models.json
-
Markdown-first collaborative worksheets for Pi
-
Displays the sanitized friendly provider name on the native Oh My Pi statusline.
-
Project and session-aware NTFY notifications for the pi coding agent.
-
Persist the last selected model and each model's thinking level to Pi's settings.json.
-
pi and Oh My Pi extension that improves long-session context with boundary-time pruning
-
Claude Code-style working spinner for Pi — shimmer, thinking glow, token count, stall detection
-
Set and apply per-model thinking levels from Pi's native settings.
-
Show per-model prices in CNY (in/out/cacheRead/cacheWrite + tiers) inside pi's built-in /model selector
-
Pi extension: manage shared backend processes via the sharedserver CLI.
-
OpenTelemetry traces and metrics for the pi coding harness, exported via OTLP/HTTP to Grafana otel-lgtm
-
Lazy tool loading for pi-web-access.
-
/provider command for pi: add, edit and test custom providers (relays, proxies, local servers) in models.json
-
HiViz — audit and refactor standing AI-agent instructions (AGENTS.md/CLAUDE.md/skills/MCP) for prompt debt. Trace every rule before cutting it: probe-verified, safety-preserving; drift checks with MCP usage telemetry, constitution tests, blame provenance,
-
A minimal Pi loadout menu for project-local packages.
-
Pi skills and prompts for deep multi-lens code review, advisory AI-slop and driver-curation assessment, and PR/branch size analysis.
-
Dedicated-model, safety-first compaction extension for Pi Coding Agent.
-
Mnemos memory & knowledge server — Pi extension. Spawns `mnemos mcp-server` over stdio and exposes every mnemos_* tool as a native Pi tool, plus the mnemos skill pack.
-
Gives Pi a sparring partner to discuss, debate, push back, and fact-check.
-
Opinionated sub-agent router for Pi: tightly couples SKILL.md execution with the Augment Code (auggie) Context Engine.