pi-sandbox
OS-level sandboxing for pi with interactive permission prompts
6.2k listings for pi
445 results · page 3 of 10
OS-level sandboxing for pi with interactive permission prompts
Pi extension for attachment processing — classifies, parses, and renders file attachments into LLM-visible prompt context
Pi extension providing persistent curated memory (MEMORY.md + USER.md) injected into the system prompt as a frozen snapshot.
Numbered approval options and Tab-to-comment for Pi's extension select dialogs, including pi-auto-permissions command approval prompts.
Reusable Pi agent platform, project adapters, MCP/tool policy, and coding workflow harness.
Pi coding-agent extension that summarizes completed tool-call batches, replaces raw outputs with short stubs, compresses closed tool-call chains, and recovers any original on demand via context_tree_query.
Goal mode extension for pi: persistent long-running objectives, /goal-set drafting, Sisyphus prompt style, autoContinue, and an above-editor status overlay. Fork of @capyup/pi-goal.
Invisible session continuation for pi — resume the agentic loop without sending ANY prompt the LLM can see
A Pi extension that decorates user prompts and replaces the default "Working..." loader with a shimmering, randomized activity word, live elapsed timer, and output-token activity meter
Pi extension — system-prompt injection (SOP.md + repo directives)
YAML hook automation for the Pi and OMP coding agents: tool guards, session hooks, prompts, notifications, and bash actions.
JHP's Pi extension suite for team coding workflows
Advisory ghost-text prompt suggestions for the pi coding agent
SuPi Cache — prompt cache health monitoring and cross-session forensics
SuPi extras — command aliases, skill shorthand, tab spinner, /supi-stash prompt stash with TUI overlay, and other small utilities
Pi extension: model + thinking + tools + system-prompt presets, with a UI on top.
Pi's Heartbeat - A pi extension for scheduling recurring and one-shot main agent or background prompts with cron-like functionality
Toggle skill visibility in pi's system prompt — flip disable-model-invocation on skills via an interactive TUI
Cognitive-driven multi-agent orchestration for society.db, prompt-vault, and agent-kernel
pi extension that registers Kimi, MiniMax, Xiaomi MiMo, and CrofAI providers with cache fix, Anthropic OAuth adapter, and native web search with provider-override support. Search backends include ZAI MCP, Google, OpenAI, xAI, Anthropic, Claude Code, and C
Safer, cheaper edits by verifying prior reads in the harness instead of the prompt. Lets the harness verify the model already read the latest text it wants to edit, avoiding old-text replay and hash-decorated reads.
Compact Pi extension for recording turnlog provenance with low prompt overhead.
Pi extension for prompt stack and agent profile management.
Codebase-aware prompt enhancer for the Pi coding agent — rewrites rough prompts into precise ones, with project tree, git context, and referenced file contents, before they reach the model.
Skip the startup trust prompt in pi — auto-decline project trust so you're immediately interactive, then /trust + /reload when ready
Global, cross-session TODO for pi — persists across all sessions and is auto-injected into every prompt. The disk-backed counterpart to branch-scoped pi todo extensions.
Footer widget with costs, cache, turns, ctx window tracking etc. Detailed usage reports, Isolated SSH, Self learning & injecting issues & solutions, various skills, 3 themes, prompt repeater, shortcuts and more.
Pi extension for structured multi-tab inline questions and bridge-driven replies.
Translate Chinese Pi editor drafts to English on demand before submission.
Pi quality-of-life extension: compact statusline/π prompt, reliable multiline input, styled pasted-image chips, session naming/search/context import, scheduled prompts, handoff, permission prompts, notifications, custom compaction, and a collapsed-thinkin
Builds a behavioral portrait from your session history — learns your corrections and injects them into the system prompt so the agent anticipates them before responding.
Deterministic, reversible in-session context compaction for the Pi coding agent — folds stale tool output out of the model's view, never out of the session.
Memory for pi — Claude-Code-compatible cwd-keyed memory, auto-injected into every prompt. One-command CC→Pi import. The cross-tool on-ramp from Claude Code to pi.
Kimi K3 prefix-cache optimizer extension for pi-agent (dual-channel, zero-fork)
A pi extension that prompts before session changes when the current git repo has uncommitted changes.
A pi extension that expands inline bash commands in user prompts.
Subagent tool and direct agent runs for pi — isolated agents, parallel scouts, manager workflows, and bundled prompts
Captures user decisions and re-injects them into the system prompt after compaction and into subagents, so the agent never forgets a decision you made.
Reusable prompts and skills for CLI LLM tools, with native pi package support.
Ghost completion for prompt history in pi's TUI
Prompt workflow extension for Pi coding agent
Scheduled actions for pi agents — prompts, shell checks, notifications, one-shots, and bounded polls
Gemini ACP chat, prompt, search, and research provider for Pi.
Sage Protocol MCP integration for pi coding agent
ProjectOps — 완전 자동화 GitHub 프로젝트 관리 템플릿 통합 CLI
Give Pi coding agents a clock: schedule reminders, shell commands, and self-waking prompts for CI polling and autonomous follow-ups.
Aggressive automatic todo progress widget for multi-goal prompts in Pi.
Official Octocode Pi package: system prompt, skills, harness docs, and setup commands for coding agents.