@nightona-co/pi
Pi coding agent extension that runs all tool calls inside a remote, ephemeral Nightona sandbox while the agent runs locally
6.2k listings for pi · 0 reviewed by us
323 results · page 4 of 7
Pi coding agent extension that runs all tool calls inside a remote, ephemeral Nightona sandbox while the agent runs locally
Pi extension to handle permissions using a layered approach
pi extension that sandboxes LLM coding agents inside a Gondolin micro-VM with configurable additional mounts
Confirm or block dangerous bash commands before the Pi coding agent executes them.
Observable, steerable, isolated-context subagents for pi — resume any child mid-task, flush partial results on interrupt/timeout, lean machine-facing envelope, optional model allowlist.
Hermes-style messaging gateway for pi - multi-platform agent with sessions, security, and background tasks
Agent Booster Pack for Pi: skills + Interface Design Gate runtime + proof-first runtime + whiteboarding guard + final value guard, in one install. Meta-package; depends on the four siblings.
pi coding-agent extension that runs every read/write/edit/bash op inside a per-session Linux container (Apple `container` or Docker).
Tri-state tool permission system (allow/deny/ask) for AI agent tool invocations
Pi extension — permission gate for dangerous bash commands (confirm/block with TUI dialog)
Security harness for the PI coding agent — forbids dangerous commands and gates sensitive ones behind user approval
General Agent Booster Pack skills for Pi: data, security, debugging, refactoring, and more. Runtime-owned skills ship with their matching extension packages. Renamed from pi-agent-booster-pack; old name deprecated.
Apply Divio's four-quadrant documentation system to write, audit, classify, restructure, and review technical documentation. Use when creating or improving tutorials, how-to guides, reference docs, explanations, docs...
Deterministic destructive-command guard + inviolable-constraint policy engine and deviation state machine for the Pi coding agent
Pi, enhanced — one install for nklisch's full harness: policy-gated command review, plugin marketplace, subagents, background tasks, research tools, search, model modes, and a curated UX set.
Pi Codemode plugin - TypeScript code execution with sandboxed tools, just-bash shell, and MCP integration
Unofficial Pi skill wrapper for React Doctor (by Million.co) — scans React codebases for security, performance, correctness, and architecture issues.
Pi extension for running sandboxed subagents in Freestyle cloud VMs
Pi Agent extension: inject a default bash timeout and append timeout policy guidance to the system prompt
OS-level sandbox for pi coding agent — macOS sandbox-exec / Linux bubblewrap kernel-enforced isolation
Protect your production assets from dangerous bash commands. Default no-bash mode with user approval gates and whitelist support.
Governance, RBAC, audit, and HITL for Pi-based coding agents
PRD-first SDD stack for Pi Agent with OpenSpec and strict Engram memory policy.
Cross-cutting engineering-discipline skills for pi sessions — interview-me, doubt-driven-review, code-simplification, security-hardening, performance-optimization, observability-instrumentation, systematic-debugging, node-inspect-debugger, scenario-design
Approval-gated frontend implementation for Pi, combining Implannotator design guidance with Plannotator reviews.
Pi extension that guards against content-based secret leaks and indirect script execution
Free SEO toolkit for Pi — keyword research, difficulty scoring, competitor gap, site audit. Zero dependencies. Upsells to full SEO workflow engine.
Security extension for Pi Coding Agent
Pi extension that adds a safe readonly python sandbox in the currrent directory
🧠 Persistent memory + 🔍 session search + 🛡️ secret scanning for Pi. Token-aware policy-only memory by default, SQLite FTS5 search, auto-consolidation, procedural skills. 368 tests. Ported from Hermes agent.
Block secrets and PII before they land: regex + entropy scanning for files, diffs, and AI coding agents. CLI, MCP server, Claude/Cursor skill, and pi extension.
Pi extension for VS Code diff approval workflows and editor context bridging.
Free-form, LLM-driven model switching for Pi — resolve a free-text model reference and switch mid-conversation, no approval loop, no auto-restore
Permission enforcement and quick policy commands for the Pi coding agent.
Write-ahead log for Pi tool calls: record intent before execution, reconcile results after, persist to SQLite for audit and crash recovery
pi coding-agent extension that intercepts network operations with approval flows, vulnerability scanning, and supply chain security enforcement.
Agent Tick control-plane integration for Pi: remote decisions, approvals, and session status updates
Permission enforcement extension for the Pi coding agent
Session lifecycle tools for Vera agent (ask-user, todo, check-vera, output-guard, compaction, prompt-rules, read-cap, conditional-rules, system-env, skill-catalog, time, notify-sound)
Auto-recover trapped tool calls from thinking blocks for Qwen3.6 and similar models
`executor-pi` is a first-class Pi extension for running Executor from inside Pi with native approval, elicitation, rendering, and project-aware Executor configuration.
Helps clankers keep code prim and proper with linters, formatters and security tools
Offensive security case tracker for pi and Codex — bug bounties, CTFs, security audits
Use the official Grok Build ACP agent from Pi with interactive permission bridging.
Code quality skills for pi — linting/fixing, TypeScript strict checks, production-readiness audit, multi-persona QA, and a brutal pre-prod code roast.
Standalone Auto Mode commands, permission modes, and guardrails for Pi
Claude-Code-style dynamic workflow orchestration for Pi (Baryon fork: crash-safe script errors + guarded sandbox).
Configurable allow/deny permission rules for pi tool calls — control which bash commands, file reads, writes, and edits the agent can perform.