6.2k listings for pi
323 results · page 5 of 7
🧠 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.
PRD-first SDD stack for Pi Agent with OpenSpec and strict Engram memory policy.
A proper sandbox extension for pi, using the Anthropic Sandbox Runtime
Layered permission control extension for pi-coding-agent (no sound)
Multi-agent red teaming system for Pi - 10 specialized security agents for vulnerability assessment and penetration testing
Interactive menus & input for pi — proactive multi-question tabs, option search filter, single/multi select, typed input (text/secret/number/date/path), configurable emoji
Four approval modes + command-level security restrictions for the Pi coding agent. Act / Auto / Ask / Plan mode switching, rule engine, subagent auto-approval.
Permission enforcement and quick policy commands for the Pi coding agent.
Claude Code-style permission modes for pi. Controls approval for file writes, edits, and bash commands with four modes: default, acceptEdits, fullAuto, and bypassPermissions.
Agent Booster Pack helps Pi produce code that is well-organized, low in complexity and side effects, and is secure and high-performing.
Authenticated-session manager for Pi Agent — store and resolve cookie, OAuth client-credentials, and mTLS auth for authorized pentest targets
Context-aware Bash permissions for Pi with automated guardian review.
Configurable allow/deny permission rules for pi tool calls — control which bash commands, file reads, writes, and edits the agent can perform.
Security harness for the PI coding agent — forbids dangerous commands and gates sensitive ones behind user approval
Permission enforcement extension for Pi/OMP
A lightweight OS-level guard for Pi: agents stay useful, sensitive paths stay blocked, and writes stay inside the workspace you allow. No container overhead. No workflow drama.
Agents should invoke this skill for code security reviews, leaked secret checks, dependency risk, unsafe shell/Python/TypeScript/Rust patterns, auth/input-validation flaws, SAST-style audits, or supply-chain concerns in repositories.
Pi extension that detects and prevents LLM loops in tool calls and reasoning
Track LLM spending per task and pause when a configurable threshold is reached — continue, refine the prompt, or stop. Pi extension by agentoom.com.
Extensión de Pi para administrar sandboxes de Apple `container` (micro-VMs Linux): un comando /container y una herramienta container_sandbox invocable por el modelo (status/list/create/run/stop/remove).
Helps clankers keep code prim and proper with linters, formatters and security tools
Security extension for Pi Coding Agent
Security scanning: nmap wrapper, vulnerability checks
A pi coding-agent extension that reviews every tool call and tool output with an LLM reviewer, hard-denies secret access, and gates risky actions behind user approval.
Allowlist-only zsh script runner extension for pi coding agents.
Pi extension for running sandboxed subagents in Freestyle cloud VMs
Deterministic tool-call guard for pi: path preflight, schema/repair, content rules, error enrichment, and destructive-bash blocking (interactive confirm + headless subagent hard-block)
Deep research harness for pi — tier-adaptive 16-step pipeline with adversarial audit, source provenance, and a persistent searchable vault. Wraps the hyperresearch Python CLI.
Bash command allowlist system for pi — grouped trust policies with glob matching, recursive parsing, and an interactive TUI manager
a pi extension for safely running allow-listed, read-only commands on remote hosts over SSH
High-performance secret firewall for pi — secrets usable as shell vars, never visible to models
Native Pi extension: give a Pi coding agent a real, routable Whisper IPv6 /128 identity - keyless verify/RDAP; the full control plane, /128 egress, and the whisper.security graph (Cypher + 29 recipes) with a key.
`executor-pi` is a first-class Pi extension for running Executor from inside Pi with native approval, elicitation, rendering, and project-aware Executor configuration.
Blocking, user-approved sudo tasks in a dedicated Herdr pane
Configurable auto-reviewer Pi extension for parsed, structural command policy
Secret detection and pi-share-hf integration for pi-coding-agent. Scans projects, sessions, and environment for secrets, syncs to pi-share-hf workspace, and manages the collection/upload pipeline.
Asqav extension for the pi coding agent - sign and gate tool calls before they execute
OS-level sandboxing for pi with interactive permission prompts (fork)
Gondolin micro-VM sandbox for clankie — runs agent tools inside an isolated VM with network policies, secret injection, and filesystem isolation
Governance, RBAC, audit, and HITL for Pi-based coding agents
Dynamic full-permission bypass toggle for pi-permission-system with backup/restore of policy files.
macOS Seatbelt sandbox extension package for pi bash and file-tool access controls.
Defense-in-depth protection for Pi coding agent. Blocks dangerous commands and protects sensitive files — fork of Serhioromano/pi-defender with defaultMode support.
Named profiles for pi: bundle model, thinking level, tools, and system-prompt instructions, with a soft model-allowlist guard for separating contexts like a personal OpenRouter budget from a work Vertex AI project.
Agent Tick control-plane integration for Pi: remote decisions, approvals, and session status updates
Pi extension that lets agents request temporary sudo-backed root access with explicit user approval.
pi extension that redacts PII/secrets before sending to the LLM and restores them in responses
Pi safety bundle: safe command runners, damage prevention, and secret redaction.