Franklin
An autonomous AI agent with its own wallet that spends USDC to get real work done.
- Sato Score78
- ChainsBase, Solana
Franklin is an open-source onchain agent by BlockRun on Base and Solana, with last code activity on 2026-10-27 (Active). Latest release on 2026-10-27. Sato Score 78/100 (how open, active and verifiable it is, not a safety grade), as of 2026-10-30. How the score works →
See the evidence behind Franklin →Last commit Oct 26, 2026 · Last release Oct 27, 2026 (desktop-v0.2.0-beta.6) · ★ 563
Listed from franklin.run on 2026-06-16. Install: reproduced by Sato Hub on 2026-10-15. Evidence →
Next step
Watch Franklin
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/mcpRun Sato Hub Preflight on blockrunai/franklin before I use it.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
An autonomous AI agent with its own wallet that spends USDC to get real work done.
Sato Score
78/100· HighHow open, active & verifiable — not a safety or returns grade.
- Maintenance & liveness
- 35/35
- Code transparency
- 19/20
- Interface verifiability
- 8/10
- Docs & demo
- 0/10
- Listing transparency & provenance
- 13/15
- Independent verification
- 3/10
Deploy path reproduced — install verified in an isolated container (proves installability, not runtime safety).
Sato Check
v3.49.16 · as of 2026-10-27- Does it take your key?
- Reads a key
- Does your key leave?
- Not yet run · earlier run 2026-10-26: not observed
- Can it move funds on its own?
- Unknown
A profile describes what we read and ran, with dates. It is not a safety rating, an audit or an endorsement, and "not found" is not "not there".
Evidence — listed vs checked · what the words mean
Listed from franklin.run on 2026-06-16. Install: reproduced by Sato Hub on 2026-10-15.
| Claim | Value | Evidence | Source | Checked |
|---|---|---|---|---|
| Chains supported | Base, Solana | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-25 |
| Verification status | Unverified — not independently reviewed | self-reported | franklin.run | as of 2026-10-30 |
| Recent activity | last release 2026-10-27 · last commit 2026-10-26 | observed | github.com/BlockRunAI/Franklin | 2026-10-30 |
| Install works | reproduced — install and entry both completedshows the install path works as written; not a statement about runtime behaviour | ✓ reproduced | github.com/BlockRunAI/Franklin | 2026-10-15 |
| Website answers | answered (HTTP 200) | observed | franklin.run | 2026-10-30 |
| Daily check record | 90 of 90 daily checks since 2026-08-01 succeededa success rate of our checks, not uptime; the source is this listing's own history | observed | — | 2026-10-29 |
| Takes your key | reads private-key material | traced | satohub.ai | 2026-10-27 |
| Key leaves the machine | not yet run with planted test keysthe sandbox lane has not run on this version | observed | satohub.ai | not dated |
| Moves funds on its own | unknown — could not read what it exposes | traced | satohub.ai | 2026-10-27 |
| Built by | BlockRunconfidence 0.85 | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-25 |
| Creator profile | https://github.com/BlockRunAIconfidence 0.85 | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-25 |
| Deploys as | npm, VS Code extensionconfidence 0.90 | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-25 |
| Works with | x402, USDC, VS Code, BlockRun gatewayconfidence 0.80 | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-25 |
| Agent types | DeFi/Yieldconfidence 0.80 | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-25 |
| Tags | x402, usdc, micropayments, autonomous-agent, walletconfidence 0.85 | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-25 |
| Website | https://franklin.runconfidence 0.90 | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-25 |
| Repository | https://github.com/BlockRunAI/Franklinconfidence 0.90 | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-16 |
| Category | Onchain Agentconfidence 0.90 | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-16 |
| Short description | text setconfidence 0.90 | self-reported | github.com/BlockRunAI/Franklin | as of 2026-06-16 |
| Sato Score | 78/100 (High)how open, active and verifiable — not a safety or quality grade | computed | satohub.ai | 2026-10-30 |
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.
Install — reproduced in a container Oct 15, 2026
Runtime: node
npm install -g @blockrun/franklin franklin
Read from the project’s own docs as of 2026-10-15. What a deploy spec is →
Observed record — 91 daily checks since 2026-08-01
- Succeeded
- 91
- 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. 31 of these checks predate 2026-09-01, when the probe counted a bot-block (HTTP 403) as a failure and recorded no reason for any failure. Every one of them passed, so the rate covers them too.
Last 30 days — to 2026-10-30, one point per UTC day
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
- DeFi/Yield
- Open source
- Yes
- Pricing
- Pay-per-action (YOPO): provider cost + 5%, settled in USDC per action; no subscription.
- Deploys as
- npm, VS Code extension
- Works with
- x402, USDC, VS Code, BlockRun gateway
- Last checked
- 2026-10-30
Marketplace Signals
- ▸ Functional agent
Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.
Where Franklin fits
Related concepts: How Agents Interact With Smart Contracts, How Agents Use Wallets, What Are Onchain Agents?
Recent Activity
All news →Releases and posts from Franklin, pulled from its GitHub and X.
Franklin Desktop 0.2.0-beta.6
Franklin Desktop beta for macOS Apple Silicon and Windows x64. Packaging validation The embedded runtime now declares its production dependencies directly. Both platforms verify the packaged runtime from a temporary directory outside the checkout, preventing host node_modules from hiding missing package dependencies. The beta.5 candidate was withdrawn after this check exposed a missing model-catal
Franklin desktop-v0.2.0-beta.5
Franklin Desktop 0.2.0-beta.5: verified Skills import and Trading Mode
Franklin Agent 3.49.16
Bump @blockrun/router-core to fd6d03d: adds the shared parseModelCatalog / toRoutingCatalog catalog API. No routing behavior change.
Franklin v3.49.15 — Mistral Large 4 at its list price; two more verified tool fallbacks
Mistral's launch promotion ended and blockrun moved mistral/mistral-large-4 from $0.68/$2.09 to $1.36/$4.18. The offline price table follows, so session cost estimates match what the gateway bills. @blockrun/router-core moves to 8773a99. A live probe confirmed well-formed tool calls from deepseek/deepseek-v4.1-flash and openai/gpt-6.1-sol , so auto routing can fall back to them on tool turns, behi
Franklin v3.49.14
What's Changed Gemini 4 Argon: priced, vision-tagged, pinnable (3.49.14) by @VickyXAI in #220 chore: bump model-catalog to b95efe2 (Gemini 4 Argon) by @VickyXAI in #221 Full Changelog : v3.49.13...v3.49.14
Franklin v3.49.12 — a refuted-then-verified goal now teaches the next one
A /goal that the verifier panel refuted and then verified on a later round is a behavioral contrast between two attempts at the same objective: same model, same tools, one gap closed. Those verdicts were written under ~/.blockrun/goals/ /verdicts/ and never read. Now a reflector on the free extraction models turns the contrast into at most one lesson per goal: the shape of situation it applies to,
Listing History
Recorded changes to Franklin's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.
- Oct 27, 2026New release published
- Oct 26, 2026New release published
- Oct 15, 2026Verified: deploy spec
- Sep 1, 2026Sato Score tier: Medium → HighScore 67 → 70.
- Aug 13, 202618 releases trackedShowing the 2 most recent. Full release history is retained in the listing record.
- Aug 2, 2026Sato Hub began tracking this listing
- Jun 25, 2026Enriched: pricing
- Jun 25, 2026Auto-enriched: creator name, creator profile url, website url, chains supported +5 more
- Jun 16, 2026Edited: category, github url, description short
Compared with
Appears in
- Onchain trading tools on Base, scored →
- x402 payment tools on Base, scored →
- x402-ready tools, scored →
- Onchain trading tools on Solana, scored →
- Npm-installable crypto agent tools, scored →
- x402 payment tools on Solana, scored →
- Payment tools for agents, scored →
- x402 endpoints checked for a payment-required answer →
- x402 facilitators on Base →
- x402: agent payments over HTTP →
- Onchain agents on Base →
- Onchain agents on Solana →
Related Resources
Agent Payments Protocol (AP2)
ActiveOpen protocol from Google for secure agent-led payments across traditional and crypto rails, with a crypto-native x402 extension built with Coinbase, Ethereum Foundation, and MetaMask.
Zerion
ActiveWallet and DeFi data provider offering portfolio, positions, transactions, PnL, and prices across many chains, with an agent-accessible API.
Bankr
ActiveCrypto execution layer and cross-chain wallet that lets agents and users trade, bridge, and manage assets via natural language, plus a skills marketplace and an x402 cloud for spinning up pay-per-call agent endpoints.
Reference
QuestionsWhat people ask about this pageShowHide
Questions people ask about Franklin
- Is Franklin open source?
- Yes. Franklin is open source under the Apache-2.0 license; the repository is https://github.com/BlockRunAI/Franklin. Checked as of 2026-10-30.
- Which chains does Franklin support?
- Franklin lists support for Base, Solana as of 2026-10-30.
- Is Franklin still maintained?
- The most recent code activity Sato Hub observed was on 2026-10-27 (last commit 2026-10-26, last release 2026-10-27), 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 Franklin?
- node. Install: npm install -g @blockrun/franklin. Entry: franklin. Sato Hub reproduced this install in a container on 2026-10-15.
- Is Franklin verified on Sato Hub?
- Sato Hub holds one earned check for Franklin: Deploy path reproduced — install verified in an isolated container (proves installability, not runtime safety). Its Sato Score is 78 of 100, a measure of how open, active and verifiable the project is, not a safety, quality or returns grade.
Cite this pagePlain text, APA or BibTeXShowHide
Cite this page
Sato Hub. "Franklin — Sato Hub." Sato Hub, updated 2026-10-30, accessed 2026-10-30. https://satohub.ai/resources/franklin-blockrunData last refreshed 2026-10-30; 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.