Category
Which agent frameworks exist for onchain agents?
Sato Hub lists 30 agent frameworks: 20 open source, 13 with public activity in the last 30 days, 27 with a documented install, across 19 chains · as of 2026-09-26.
Ordered by Sato Score, a 0–100 measure of how open, active and verifiable each project is, computed from public evidence. It is not a safety rating, an audit, or a quality ranking, and this page declares no winner.
Agent Framework listings
30OpenClaw
ActiveOpen-source self-hosted personal AI agent framework with a public skill registry (ClawHub) that runs across multiple messaging channels.
Hermes Agent
ActiveOpen-source self-improving AI agent from Nous Research with a built-in learning loop and one-step migration from OpenClaw.
OpenAI Codex
ActiveOpenAI's agentic coding tool (CLI, IDE, and cloud) that runs agents and connects to MCP servers and skills.
TradingAgents
ActiveAn open-source multi-agent LLM framework that simulates a trading firm with analyst, trader, and risk-management agents for research purposes.
ElizaOS
ActiveOpen-source TypeScript framework for building crypto-native multi-agent systems.
Olas (Autonolas)
ActiveNetwork and framework for co-owned autonomous agent services operating onchain.
Fetch.ai uAgents
ActivePython framework for lightweight autonomous agents with built-in crypto-economic features.
IntentKit
EarlyOpen-source, self-hosted framework for running collaborative clusters of onchain AI agents.
Claude Code
ActiveAnthropic's agentic command-line coding tool that runs agents and loads Agent Skills, including onchain skills.
Almanak
ActiveAn AI-agent framework and non-custodial vault protocol for designing, backtesting, and deploying automated DeFi yield and trading strategies.
NEAR Shade Agent Framework
BetaFramework for TEE-hosted agents that hold assets and sign on many chains via NEAR chain signatures, with guardrails in an agent contract.
OpenServ
ActiveTypeScript SDK and platform for building, orchestrating, and monetizing collaborative AI agents.
Arbitrum Vibekit
ActiveArbitrum-native, MCP-first agent framework with A2A and x402 support, backed by an Arbitrum Foundation grant program.
Lucid Agents
EarlyCommerce SDK for bootstrapping AI agents that can pay, sell, and transact onchain.
IronClaw
ActiveNEAR AI's open-source secure agent runtime that runs agent workloads inside hardware TEEs on NEAR AI Cloud.
Daydreams
EarlyFramework and tooling for building AI agents for onchain commerce.
GAME SDK (Virtuals Protocol)
ActiveVirtuals Protocol's official Python SDK for building autonomous agents with planning, worker, and function layers.
Grok CLI
ActiveOpen-source terminal coding agent for the xAI Grok API — community-built, not affiliated with xAI.
LumoKit
EarlyLightweight AI toolkit framework offering on-chain actions and research abilities for Solana.
Starknet Agentic
ActiveOfficial Starknet-ecosystem infra for self-custodial agents: Cairo contracts, MCP/A2A runtimes, and installable skills.
Snak (Starknet Agent Kit)
UnknownNestJS-based toolkit for building AI agents that interact with Starknet, supporting multiple LLM providers.
Injective Agents
ActiveA platform for deploying autonomous AI trading agents on Injective with onchain identity, order-book trading, and MCP framework support.
Warden Protocol
ActiveA Cosmos SDK Layer 1 with EVM compatibility positioned as a settlement and distribution layer for AI agents.
Ping Agent Kit
EarlyOpen-source Solana agent-integration kit with a plugin architecture spanning tokens, NFTs, DeFi, and Blinks.
Wayfinder
BetaOmnichain protocol that lets AI agents navigate blockchains and execute transactions via natural-language 'Paths'.
Cambrian Agent Kit
EarlyTypeScript SDK giving AI agents direct access to Sei DeFi protocols: swaps, lending, staking, and perps.
listen (DeFAI toolkit)
EarlyRust toolkit pairing the rig LLM framework with Solana trading primitives, including Jito bundle submission.
Spectral Syntax
ActiveA no-code platform from Spectral Labs that turns natural-language prompts into autonomous onchain agents with wallets and trading capabilities.
Manus
ActiveGeneral-purpose autonomous AI agent that executes multi-step tasks and can run onchain agent skills.
Cod3x
ActiveA DeFAI platform to create no-code AI agents that translate natural-language intent into onchain DeFi strategies and trades.
By chain
Chains these listings declare support for, most represented first. A listing that supports several chains counts once on each.
- Base8 listingsTrading on Base (6)Wallets on Base (5)Payments on Base (2)filter →
- Ethereum8 listingsTrading on Ethereum (5)Wallets on Ethereum (5)Payments on Ethereum (2)Data on Ethereum (1)filter →
- Solana8 listingsTrading on Solana (4)Wallets on Solana (4)Payments on Solana (1)filter →
- Multichain7 listingsfilter →
- Arbitrum4 listingsTrading on Arbitrum (3)filter →
- Cosmos3 listingsfilter →
- BNB Chain2 listingsTrading on BNB Chain (2)filter →
- Hyperliquid2 listingsfilter →
- Near2 listingsfilter →
- Starknet2 listingsfilter →
- Avalanche1 listingsfilter →
- Berachain1 listingsfilter →
Other categories
Questions people ask about agent frameworks
- Which of these are open source?
- 20 of 30: OpenClaw, Hermes Agent, TradingAgents, ElizaOS, Olas (Autonolas), Fetch.ai uAgents, IntentKit, NEAR Shade Agent Framework, Arbitrum Vibekit, Lucid Agents, IronClaw, Daydreams and others.
- Which are actively maintained?
- 13 showed public activity in the last 30 days: OpenClaw, Hermes Agent, OpenAI Codex, TradingAgents, ElizaOS, Olas (Autonolas), Fetch.ai uAgents, IntentKit, Claude Code, Almanak, NEAR Shade Agent Framework, IronClaw and others. Activity is a recency signal, not a quality judgment.
- Which have an earned verification on Sato Hub?
- 15: OpenClaw, Hermes Agent, OpenAI Codex, TradingAgents, ElizaOS, Olas (Autonolas), Fetch.ai uAgents, IntentKit, Claude Code, Almanak, OpenServ, Lucid Agents. An earned check is named as what was checked (install reproduced, endpoint probed, on-chain identity read, reviewed against evidence); none is a safety claim.
- Which run as MCP servers?
- 6: Hermes Agent, OpenAI Codex, Claude Code, Lucid Agents, Daydreams, Injective Agents.
- How is this list ranked?
- Which agent frameworks exist for onchain agents? is derived from Sato Hub's live records by a stated rule and ordered by Sato Score, a 0–100 measure of how open, active and verifiable each project is. It is not a quality ranking and declares no winner.
Sources — the listings' own repositories and docs
Cite this page
Sato Hub. "Which agent frameworks exist for onchain agents?." Sato Hub, updated 2026-09-26, accessed 2026-09-27. https://satohub.ai/categories/agent-frameworkData last refreshed 2026-09-26; 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.