PIC (Provenance & Intent Contracts) serves as an action firewall for agentic AI.
Lightweight, it adds machine-verifiable contracts to agent calls and actions and it is particularly efective at shielding the agent from propmpt-injection.

Before any high-impact tool call, the agent must submit an Action Proposal (schema + verifier):

- explicit intent
- impact classification (read / write / money / irreversible / privacy / etc.)
- provenance sources with trust levels (untrusted → trusted via verification)
- claims backed by verifiable evidence (SHA-256 file hashes or Ed25519 signatures)

If trust/evidence is insufficient, it fails closed and blocks the action.

Current version features:
- Deterministic Hash Evidence verification (SHA-256)
- Signature evidence (Ed25519)
- Keyring expiry + revocation
- CLI keys
- MCP and LangGraph integrations
- Comprehensive tests, examples, and documentation

Features

  • Structured Action Proposal (PIC/1.0 JSON)
  • Fail-Closed Verifier
  • Deterministic Hash Evidence Verification (type="hash")
  • Ed25519 Signature Evidence (type="sig" – v0.4 highlight)
  • Trusted Keyring with Lifecycle Controls
  • Key Status & Diagnostic Helpers
  • LangGraph Integration (PICToolNode)
  • MCP (Model Context Protocol) Guarding
  • Privacy Gating & Hardening
  • CLI Tooling Suite

Project Activity

See All Activity >

License

Apache License V2.0

Follow pic-standard

pic-standard Web Site

Other Useful Business Software
Gemini 3 and 200+ AI Models on One Platform Icon
Gemini 3 and 200+ AI Models on One Platform

Access Google's best plus Claude, Llama, and Gemma. Fine-tune and deploy from one console.

Build generative AI apps with Vertex AI. Switch between models without switching platforms.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of pic-standard!

Additional Project Details

Registered

2026-02-04
Report inappropriate content