Get an audit

Head to head · Onchain wallets · October 2026 research run

Openfort vs Turnkey Agentic Wallets

Turnkey Agentic Wallets scores 76 (BB) on agent readiness against Openfort's 70.1 (BB), and leads in 3 of 7 scored categories. Openfort leads on reliability and schema & documentation. Both do onchain wallets.

Best agent wallets and spending controls · All 23 wallets comparisons

OpenfortOpenfort (Alamas Labs Inc.) · HTTP API BB70.1/100#163 of 950 Turnkey Agentic WalletsTurnkey Global, Inc. · HTTP API BB76/100#39 of 950

Which one, for what

Openfort BB

Good for A team that wants server-held wallets for agents on EVM chains and Solana with enclave signing, a free start and a CLI an agent can drive.

Ahead on

  • Reliability, 88 against 75
  • Schema & documentation, 89 against 79

Also in its favour

  • Runs on your own machine

Watch for

An EVM backend send is evaluated only as signEvmHash, so address, value and calldata rules do not block it unless the caller pre-flights

Turnkey Agentic Wallets BB

Good for A company that wants agents to sign from its own wallets under rules checked in an enclave, with a person co-approving large transactions, across EVM, Solana, Bitcoin, Tron and other chains.

Ahead on

  • Agent ergonomics, 77 against 65
  • Security & auth, 85 against 65

Also in its favour

  • No incidents deducted, where Openfort loses 5 points for them

Watch for

Policy conditions cap value per transaction. No daily, rolling or cumulative spending limit was found in the policy language

Score by category

CategoryWeight this runOpenfortTurnkey Agentic WalletsEdge
Reliability16%208875Openfort +13
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28979Openfort +10
Agent ergonomics13%16.26577Turnkey Agentic Wallets +12
Security & auth14%17.56585Turnkey Agentic Wallets +20
Payments & pricing10%12.56058Openfort +2
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88783Openfort +4
Transparency & trust7%8.86972Turnkey Agentic Wallets +3
Negative events≤15-50
Total70.1 · BB76 · BB

Facts side by side

FactOpenfortTurnkey Agentic Wallets
KindHTTP APIHTTP API
VendorOpenfort (Alamas Labs Inc.)Turnkey Global, Inc.
Hosted endpointhttps://api.openfort.iohttps://api.turnkey.com
TransportsHTTP, stdioHTTP
AuthAPI keyAPI key
PricingFreemiumFreemium
x402payer tooling onlypayer tooling only
LicenceProprietary service under the Openfort Developer Terms of Service. The Node SDK and OpenSigner are MIT. The CLI repository and package state no licenceProprietary service under Turnkey's terms of service. The SDKs, the CLI and the agent skills on GitHub are Apache-2.0
Read-only variant documentednono
llms.txtyesyes
Last release2026-09-282026-10-08
Terms last updated2026-01-162026-08-06
Privacy policy last updated2026-09-042026-06-29
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waiveryesyes
Popularity10 stars, 7.6k npm/wk304k npm/wk, 12k PyPI/wk

Verdicts

Openfort

Backend wallets sign inside a GCP Confidential Space enclave, secret keys carry 26 scopes, and rate limits, errors and prices are published. On EVM, a backend send reaches the policy engine only as a hash, so address and value rules bind only when the caller runs the pre-flight check first.

Turnkey Agentic Wallets

An agent gets a non-root user that can sign nothing until a policy allows it, with DENY rules taking precedence and human co-approval available. Policies cap value per transaction only, with no daily or rolling limit found, and each organisation gets five policies below Enterprise. Signing endpoints returned elevated errors for five hours on 27 August 2026.

Before you call either

Openfort

  1. Call policies.evaluate with operation signEvmTransaction before every EVM backend send. The send itself is checked only as signEvmHash
  2. Keep the signing policy and the gas sponsorship policy separate. Linking a signing policy to a fee sponsorship stops it working as a guardrail
  3. Pass a fee sponsorship on EVM sends. Without one the transaction stays pending with no error
  4. Give an agent a secret key without accounts:export, and limit the CLI MCP server to the tools it needs
  5. On a 5xx after a write, read the resource before retrying. On a 429, wait the full Retry-After

Turnkey Agentic Wallets

  1. Use a non-root user's key. Refuse root credentials for unattended work, because root bypasses every policy
  2. Scope every signing ALLOW policy by wallet.id or wallet_account.address, or it covers every key the user can reach
  3. Check the activity status on each response. ACTIVITY_STATUS_CONSENSUS_NEEDED means a person must approve within 24 hours
  4. Retry with the identical body to stay idempotent. Changing timestampMs creates a new activity
  5. Back off with jitter on 429 and poll get_activity sparingly, since polling counts against the same 1 to 3 requests a second

Questions

Which is better for AI agents, Openfort or Turnkey Agentic Wallets?

Turnkey Agentic Wallets scores 76 (BB) on agent readiness against Openfort's 70.1 (BB), and leads in 3 of 7 scored categories. Openfort leads on reliability and schema & documentation.

Do Openfort and Turnkey Agentic Wallets need an API key?

Both need an API key.

Can an agent call Openfort and Turnkey Agentic Wallets without installing anything?

Yes. Openfort has a hosted endpoint at https://api.openfort.io and Turnkey Agentic Wallets at https://api.turnkey.com.

Other comparisons with Openfort or Turnkey Agentic Wallets

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report