🏆 BNBChain GoodVibes Hackathon Winner
Open beta  ·  2,000 free checks

A circuit breaker
for AI agents

One check before every action. ProceedGate detects loops, enforces budgets, and returns a signed token as proof.

POST /v1/check → 200 allowed
// request { "agent_id": "scraper-prod-1", "action": "http_request", "task_hash": "aHR0cHM6Ly9leGFtcGxlLmNvbS9wcm9kdWN0cy8x" } // response { "decision": "allow", "proceed_token": "eyJhbGciOiJFUzI1NiJ9.eyJkZWNpc2lvbiI6ImFsbG93In0...", "zone": "safe", "iteration_count": 2, "credits_remaining": 1847 }

In action

Every agent decision, governed

One call before each action — loop detection, budget enforcement, signed proof, and five SDK integrations.

loading…
agent
POST /check
safe · ≤5
gray · 6–10
storm · >10
iter ProceedGate
0safegraystorm10+
≤5 iterations — allowed immediately 6–10 — friction charge applies >10 — hard block, 429 returned
session · active
crypto-scraperACTIVE
session_8f3a2c · 18 requests processed
Budget spent $1.24 / $2.50
$0 alert at $2.00 $2.50 cap
web_scrape+$0.042✓ allowed
search_api+$0.031✓ allowed
model_call+$0.018⚡ friction
web_scrape✕ cap reached
Per-agent session budgets with hard USD caps Webhook alerts before cap is hit Zero overspend — blocked at exactly $2.50
ES256 · proceed_token issued
Request
action:"tool_call"
agent_id:"scraper-1"
task_hash:"sha256:aHR…"
attempt:3
ProceedGate
evaluates
✓ allowed · token issued
eyJhbGciOiJFUzI1NiJ9.eyJzdWIi…
sub:"scraper-1"
task:"sha256:aHR…"
step:"tool_call"
exp:45s TTL
alg:ES256 ✓
JWKS endpoint → verifiable by any service, offline, no round-trip
ES256 signed — cannot be forged 45s TTL — tight anti-replay window JWKS verifiable — any downstream service
5 integrations · drop-in
@proceedgate/node
TypeScript · any framework
@proceedgate/langchain
Callback · Tool · Executor
@proceedgate/vercel-ai
Middleware · gatedTool
ProceedGate
proceedgate-crewai
Python · BudgetAwareCrew
@proceedgate/mcp-server
Claude Code · Cursor
TypeScript + Python covered Drop-in — no agent rewrite needed MCP: works inside Claude Code natively

How it works

Three zones. One decision.

Every check is evaluated in under 50ms at the edge. Your agent gets a signed token or a hard block — decided before the API call is made.

01

Agent calls /check

Before every action — model call, HTTP request, tool use — send the action type and a hash of what the agent is about to do.

02

Pattern is evaluated

≤ 5 repeats → auto-allow.
6–10 repeats → AI decides (Llama 3.1 8B).
> 10 repeats → hard block, 429.

03

Token or block

Allowed: a signed proceed_token (ES256, 45s TTL). Blocked: a loop_detected reason with retry-after and loop data.

The check endpoint

Designed to stay out of your way

One POST. Works with any agent framework, language, or orchestrator. If the check passes, attach the token to your downstream call as proof of governance.

If the check fails with 429, the loop is stopped before it touches your API quota.

ES256 signed TTL 45s P-256 keypair <50ms edge JWKS endpoint
loop blocked — 429
// iteration_count: 11 · zone: storm { "decision": "block", "reason": "loop_detected", "zone": "storm", "iteration_count": 11, "human_reason": "Repeated 11× in 60s. Stopping.", "retry_after": 60 }

Features

What's actually built

No vaporware. Everything below is live in the free tier today.

Loop detection

SHA-256 hash of action + task_hash + step_hash, tracked in a 60s sliding window per workspace. Three zones: safe, gray (AI), storm. Zero config.

Signed proceed tokens

Every allowed action returns a JWT signed ES256 (P-256). 45s TTL. Verify downstream at /.well-known/jwks. Cryptographic proof the action was governed.

Per-agent budgets

Credits-based hard cap per workspace. When credits hit zero, checks return 402 — the agent can't spend past the limit even if it ignores the response.

Agent reputation

Each workspace accumulates a trust score 0–100. Trusted agents get looser thresholds. Untrusted agents face tighter gates. Updates automatically from behavior.

MPP payments

Machine Payments Protocol (Stripe + Tempo). Agents pay per-check via HTTP 402 with TIP-20 tokens. All payments recorded in a CostLedger Durable Object, queryable via GET /costs/:agentId.

Webhook alerts

POST to Slack or Discord when a loop is blocked or credits fall below threshold. Configure per workspace. No polling required to know when something went wrong.

Payments

Agents pay. No human needed.

When an action requires friction, ProceedGate returns HTTP 402 with a payment challenge. The agent settles onchain — autonomously, in seconds.

Agent
sends check request
POST /check
ProceedGate
loop detected
HTTP 402
Agent Wallet
pays 0.004 USDC
tx_hash
proceed_token
ES256 · 45s TTL
BSC Mainnet · USDC · ~3s settlement · <$0.01 gas
$0.004
per friction event
x402
HTTP-native protocol
0
humans required
CostLedger
onchain audit trail
Everyone else
  • Human tops up credits manually
  • Agent gets blocked, waits for human
  • Stripe / bank transfer
  • Off-chain, auditable only by vendor
ProceedGate
  • Agent wallet pays automatically
  • Agent receives proceed_token, continues
  • USDC on BSC — HTTP 402 native
  • Every payment on-chain, public, verifiable

Integration

Works with your stack

Drop-in SDKs for every major agent framework. No rewrites — add one wrapper and governance is live.

@proceedgate/node Full docs →
// npm i @proceedgate/node
import { createProceedGateClient, requireGateStepOk } from '@proceedgate/node';

const client = createProceedGateClient({
  apiKey: process.env.PG_KEY,
  actor:  { id: 'my-agent', project: 'my-workspace' },
});

// Before each agent action:
await requireGateStepOk(client, {
  policyId: 'retry_friction_v1',
  action:   'tool_call',
  context:  { attempt_in_window: 3, tool: 'web_scrape' },
});
// ✅ Throws ProceedGateFrictionError if blocked
@proceedgate/node TypeScript · any framework
@proceedgate/vercel-ai Middleware · gatedTool
@proceedgate/langchain Callback · Executor
proceedgate-crewai Python · BudgetAwareCrew
@proceedgate/mcp-server Claude Code · Cursor

Pricing

Simple, usage-based tiers

All plans include the full API. No feature gating on loop detection or proceed tokens.

Free
$0
2,000 checks · 14-day trial

  • 2,000 checks included
  • 1 workspace
  • Loop detection
  • Proceed tokens
  • 3-day log retention
Start free →
Most common
Starter
$19
per month

  • 25k checks / month
  • 3 workspaces
  • Webhook alerts
  • Agent reputation
  • 30-day log retention
Get started →
Pro
$49
per month

  • 1M checks / month
  • 5 workspaces
  • Custom policies
  • MPP payments
  • CostLedger audit trail
  • 90-day log retention
Get started →