pic-standard
Active·★ 68·Apache-2.0·Updated 2026-10-21
PIC Standard is a local-first action gating protocol for AI agents. It forces agents to prove intent, provenance, and evidence before executing high-impact tool calls, and blocks the action if anything is invalid. It works 100% locally, integrates with LangGraph, MCP, OpenClaw, and Cordum, and provides evidence verification via hash and Ed25519 signatures.
#action-proposals#agentic-ai#agents#ai#artificial-intelligence#causal-gap#cli#crewai
01
Features
01Local-first action gating with zero cloud dependency
02Intent, provenance, and evidence verification before tool execution
03Evidence verification (SHA-256 hash and Ed25519 signatures)
04Extensible keyring with trust controls and strict trust mode
05Integrations with LangGraph, MCP, OpenClaw, Cordum, and HTTP bridge
02
Compatibility
Python
Native
Verified via docs
LangGraph
Supported
Verified via docs
MCP
Supported
Verified via docs
OpenClaw
Partial
Verified via docs
Cordum
Partial
Verified via docs
HTTP Bridge
Supported
Verified via docs
03
Quick start
1
$ pip install pic-standard
04
Use cases
↳Preventing prompt injections and unauthorized tool calls in AI agents
↳Enforcing provenance and evidence for high-impact actions like payments or data exports
↳Local-first action safety for production AI systems without external dependencies
05
Alternatives
ClaudeR★ 354
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automated manuscript auditing, and zero-config setup with uvx
ask-user-questions-mcp★ 147
Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI tool that allows your LLMs ask questions to you. Be the human in the human-in-the-loop!
AI-News-Briefing★ 44
📰 An automated, multi-agent research ops AI pipeline that gathers daily AI news, synthesizes it into structured briefings, and delivers them to tools like Notion, Obsidian, Slack, and Teams with zero manual effort. It also supports on-demand deep research on any topic using parallel AI agents and a modular plugin ecosystem.
BettaFish★ 42.5k
Multi-agent opinion analysis assistant. Breaks information bubbles and predicts trends.
BrowseAI-Dev★ 20
Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.
Comments
Log in to leave a comment
No comments yet. Be the first!