Check posture. Gate risky actions. Prove execution.
Fits your existing agent stack.
Add posture checks, action gates, and signed receipts to the agent stack you already use.
For developers and product teams that want posture checks, action gates, and signed receipts without replacing their existing stack.
For teams that need approvals, monitoring, and verifiable evidence for high-risk agent actions.
Built for teams shipping agents into real workflows — especially when agents can touch tools, data, code, or production systems.
Give clients independent proof of what your agents did — without relying on dashboards, screenshots, or internal logs.
Check agent posture before delegation, gate risky actions, and monitor drift over time. Add coverage quickly with @avp_tracked when you’re ready.
Add posture checks, action gates, and signed receipts around sensitive agent actions — without replacing your existing stack.
Produce client-ready evidence for agent actions that can be verified independently. See Art. 9 / 12 / 13 / 14 / 50 mapping →
Technical readiness mapping only; AVP does not provide legal advice or compliance certification.
AgentVeil works in three stages: check posture before runtime, gate risky actions during execution, and verify receipts afterward.
AgentVeil is not a policy engine, MCP gateway, or sandbox runtime. It adds posture checks, runtime gates, and signed receipts around your existing identity and governance stack.
AgentVeil creates signed receipts for risky agent actions — so clients, reviewers, and partners can verify what happened independently.
curl agentveil.dev/v1/reputation/{did}/credential?format=w3c
eddsa-jcs-2022 · RFC 8785 JCS · offline-verifiable with standard VC tooling
Logs show what happened.
AgentVeil helps decide whether the action should happen — and produces signed receipts others can verify.
Add posture checks, runtime gates, and signed receipts without replacing your framework, identity provider, or observability tooling.
Frameworks
Interfaces
pip install agentveil — Python SDK.
Any language. Full documentation & guides.
pip install 'agentveil[mcp]' — Claude Desktop, Cursor, Windsurf, VS Code.
Enterprise fit
AgentVeil adds action controls and verifiable evidence around your current systems.
AVPProvider merged into Microsoft Agent Governance Toolkit (PR #1010). →
Use production endpoints for reputation signals, advisory checks, runtime gate decisions, signed receipts, and audit verification.
Start with advisory checks. Add signed runtime gates for controlled actions when you’re ready.
| Method | Endpoint | Access | Description |
|---|---|---|---|
| GET | /v1/reputation/{did} | Public | Reputation signal |
| GET | /v1/reputation/{did}/trust-check | Public | Advisory action check |
| GET | /v1/reputation/{did}/credential | Public | Signed reputation credential |
| GET | /v1/cards | Public | Agent discovery |
| GET | /v1/audit/verify | Public | Audit chain verification |
| GET | /v1/anchors/latest | Public | Latest public IPFS anchor |
| POST | /v1/attestations | Signed | Submit peer rating |
| POST | /v1/attestations/batch | Signed | Batch ratings |
| POST | /v1/agents/register | Signed | Register agent |
| POST | /v1/runtime/evaluate | Signed | Runtime Gate decision |
| POST | /v1/execute | Signed | Controlled action execution |
| GET | /v1/execution/receipts/{receipt_id} | Signed | Owner-only signed receipt lookup |
Try AgentVeil locally with a mock agent, then connect the same action workflow to production when you’re ready.
# Install the Python SDK pip install agentveil # Try instantly — no server needed from agentveil import AVPAgent agent = AVPAgent.create(mock=True, name="my_agent") agent.register(display_name="My Agent") rep = agent.get_reputation(agent.did) print(rep) # {'score': 0.75, 'confidence': 0.5, ...}
# One line to auto-register and auto-attest an agent # inside an existing workflow from agentveil import avp_tracked @avp_tracked("https://agentveil.dev", name="my_agent", to_did="did:key:z6Mk...") def review_code(pr_url: str) -> str: return analyze(pr_url)
Start free in development. Add a guided pilot around one critical action. Expand to multi-team or high-stakes environments when you need rollout support.
For developers and teams adding local posture checks and signed proof artifacts in development
can_trust()Gate one critical action and prove execution before wider rollout
Scale action gates and independently verifiable receipts across production systems