Sato Hub
Developer Tool

ClawRouter (BlockRun)

Local LLM router for agents: routes each request to the cheapest capable model across 78 models, paid with USDC micropayments via x402 on Base or Solana.

  • Sato Score84
  • ChainsBase, Solana
ActiveSelf-ReportedActive · 1d ago

ClawRouter (BlockRun) is an open-source developer tool on Base and Solana, with last code activity on 2026-11-06 (Active). Latest release on 2026-11-06. Sato Score 84/100 (how open, active and verifiable it is, not a safety grade), as of 2026-11-07. How the score works →

Check what an install would ask of your keys, before you run it →

Last commit Nov 6, 2026 · Last release Nov 6, 2026 (v0.12.309) · ★ 6,652

Listed from blockrun.ai on 2026-09-23. Install: not attempted — no install path on record. Evidence →

Next step

Watch ClawRouter (BlockRun)

One email if what we observe changes — its repo goes quiet or disappears, or the listing is retired. Nothing else.

Check it from your agent

Add Sato Hub’s MCP server (no key), then ask:

https://satohub.ai/api/mcp
Run Sato Hub Preflight on blockrunai/clawrouter before I use it.
Full setup: Claude Code, Cursor, others →

Your project?

Prove you control the domain and correct this page — description, links, tags, chains. A claim proves control, not verification: it never changes the Sato Score.

Claim this listing →

Overview

Per its README, ClawRouter is an MIT-licensed router that "analyzes each request across 15 dimensions and routes to the cheapest capable model in under 1ms, entirely locally". Paid models are settled by x402 USDC micropayments on Base or Solana, or by card-funded API keys. It installs as an OpenClaw plugin or standalone via npx @blockrun/clawrouter for any OpenAI-compatible client, and covers 78 chat models, 6 of them free.

Sato Score

84/100· High

How open, active & verifiable — not a safety or returns grade.

Maintenance & liveness
35/35
Code transparency
20/20
Interface verifiability
8/10
Docs & demo
6/10
Listing transparency & provenance
6/15
Independent verification
9/10

Evidence — listed vs checked · what the words mean

Listed from blockrun.ai on 2026-09-23. Install: not attempted — no install path on record.

ClaimValueEvidenceSourceChecked
Chains supportedBase, Solanaself-reportedblockrun.aias of 2026-11-07
Verification statusSelf-Reported — not independently reviewedself-reportedblockrun.aias of 2026-11-07
Recent activitylast release 2026-11-06 · last commit 2026-11-06observedgithub.com/BlockRunAI/ClawRouter2026-11-07
Website answersanswered (HTTP 200)observedblockrun.ai2026-11-07
Daily check record45 of 45 daily checks since 2026-09-23 succeededa success rate of our checks, not uptime; the source is this listing's own historyobserved—2026-11-06
ERC-8004 registrationdeclared address not found in the registryobserved—2026-11-07
Sato Score84/100 (High)how open, active and verifiable — not a safety or quality gradecomputedsatohub.ai2026-11-07

Self-reported rows are the project’s own words, dated when we recorded them — not a check. Only reproduced and reviewed rows carry a mark. None of these rows is a safety or quality rating.

Observed record — 46 daily checks since 2026-09-23

100%of 46 checks since 2026-09-23 succeeded
Currently responding for 46 days
Succeeded
46
Failed
0
Their error
0
Unattributed
0

This is the share of our daily checks that succeeded — not an availability guarantee. A check can fail because the host was down, because our runner timed out, or because the network in between dropped it, and only the first of those is a fact about this project. Failures are split by what we can attribute; anything we cannot attribute is counted, not hidden.

Last 30 days — to 2026-11-07, one point per UTC day

Share of OUR checks that succeeded
100%
7-day rolling; unattributable days are gaps · 30/30 days
Tools listed
fewer than 2 points—
from the server's own tools/list · 0/30 days
Sato Score
84
as snapshotted that day · 29/30 days

A gap is a day we have no attributable observation — never a zero. Thirty points is the whole shape the free layer carries; the daily rows behind it stay in the snapshot series.

Details

Chains
Base, Solana
Agent types
LLM Gateway
Open source
Yes
Last checked
2026-11-07

Marketplace Signals

No marketplace signals recorded for this resource yet.

Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.

#x402#llm-router#usdc#openclaw#micropayments

Where ClawRouter (BlockRun) fits

Related concepts: How Agents Use Wallets, What Are Onchain Agents?

See something inaccurate or outdated?Submit a correction →

Recent Activity

All news →

Releases and posts from ClawRouter (BlockRun), pulled from its GitHub and X.

ReleaseBlockRunAI/ClawRouter1d ago

ClawRouter v0.12.309

A positive maxCostPerRun now covers /v1/messages Behaviour change: a positive cap only covered /v1/chat/completions , so a client on /v1/messages , such as Claude Code, could spend past it without limit. If you set a cap and call that route, you now get a 429 once the budget can't cover the next paid call. Shared budget: the route draws on the same session budget as chat, on the wallet and API-key

BaseSolana
GitHub ↗
ReleaseBlockRunAI/ClawRouter2d ago

ClawRouter v0.12.308

maxCostPerRun: 0 now means nothing gets paid for Behaviour change: a cap of 0 used to switch the cap off, while startup logged Cost cap: $0.00 per session . It now refuses every paid call. If you set 0 to mean "no limit", remove the key. The refusal covers every route on both rails: chat, /v1/messages , image, video, music and speech generation, the partner and data APIs, and the /imagegen and /im

BaseSolana
GitHub ↗
ReleaseBlockRunAI/ClawRouter3d ago

ClawRouter v0.12.307

The SSRF guard reads every IPv6 form that embeds an IPv4 address Three more ways of writing an IPv4 address inside an IPv6 literal now resolve to the embedded address and are judged by the IPv4 rules: IPv4-translated ( ::ffff:0:127.0.0.1 , ::ffff:0:7f00:1 ), IPv4-compatible ( ::127.0.0.1 , ::7f00:1 ) and the hex spelling of each. Loopback, private, link-local and cloud-metadata targets written tha

BaseSolana
GitHub ↗
ReleaseBlockRunAI/ClawRouter4d ago

ClawRouter v0.12.306 — Dependency security sweep: 91 Dependabot alerts → 0

Dependency security sweep: 91 open Dependabot alerts → 0 In the npm package: follow-redirects 1.16.0 → 1.16.2, bundled into dist/ through axios on the Polymarket path. Older versions could carry credential headers across a cross-origin redirect (four high advisories). In ClawRouter Desktop: DeepSeek Harness 0.1.1-rc.2 → 0.1.2-rc.1. The old version trusted the client's Host header on its local cont

BaseSolana
GitHub ↗
ReleaseBlockRunAI/ClawRouter4d ago

ClawRouter v0.12.305 — Solana batch payments: four fixes from @blockrun/llm 3.25.0

Solana batch payments: four fixes from @blockrun/llm 3.25.0 ClawRouter pays Solana batch-settlement through @blockrun/llm's SolanaBatchPayer , bundled into this package. 3.24.4 → 3.25.0 brings: A channel the facilitator reclaimed is reopened, instead of topped up. A paid call the gateway did not settle is booked at $0, not its quoted price. A deposit is signed with a finalized blockhash when the 4

BaseSolana
GitHub ↗
ReleaseBlockRunAI/ClawRouter12d ago

v0.12.301 — Failed requests show up in `clawrouter logs` and `doctor` again

Failed requests show up in clawrouter logs and doctor again The proxy logs every failed request with status: "error" , but the stats reader rebuilt each log entry without that field. So clawrouter logs marked every request OK, and clawrouter doctor always reported 0 errors (it was hardcoded). The reader now keeps status , getStats() returns an errorCount , and doctor reports it. Thanks @Tyagiquama

BaseSolana
GitHub ↗

Listing History

Recorded changes to ClawRouter (BlockRun)'s listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.

  1. Nov 6, 2026
    New release published
  2. Nov 4, 2026
    New release published
  3. Sep 29, 2026
    12 releases tracked
    Showing the 2 most recent. Full release history is retained in the listing record.
  4. Sep 23, 2026
    Listed on Sato Hub
  5. Sep 23, 2026
    Sato Hub began tracking this listing

Compared with

Appears in

Related Resources

Reference

QuestionsShowHide

Questions people ask about ClawRouter (BlockRun)

Is ClawRouter (BlockRun) open source?
Yes. ClawRouter (BlockRun) is open source; the repository is https://github.com/BlockRunAI/ClawRouter. Checked as of 2026-11-07.
Which chains does ClawRouter (BlockRun) support?
ClawRouter (BlockRun) lists support for Base, Solana as of 2026-11-07.
Is ClawRouter (BlockRun) still maintained?
The most recent code activity Sato Hub observed was on 2026-11-06 (last commit 2026-11-06, last release 2026-11-06), which Sato Hub labels "Active". Posts on X are not counted as maintenance. Activity is a recency signal, not a quality judgment.
How do I install or run ClawRouter (BlockRun)?
Sato Hub has no deploy spec for ClawRouter (BlockRun); follow the project's own documentation at https://blockrun.ai/docs.
Is ClawRouter (BlockRun) verified on Sato Hub?
No independent verification is on record for ClawRouter (BlockRun); its verification status is "Self-Reported" and its Sato Score is 84 of 100. Self-reported is not verified, and the score is not a safety, quality or returns grade.
Cite this pageShowHide

Cite this page

Sato Hub. "ClawRouter (BlockRun) — Sato Hub." Sato Hub, updated 2026-11-07, accessed 2026-11-07. https://satohub.ai/resources/clawrouter

Data last refreshed 2026-11-07; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.

Join the Sato Hub Briefing

Sign up for the Briefing: the agents, tools, and infrastructure that actually shipped, and why they matter.