How it works Agents Capabilities Main site Follow on X ↗
Labs / Research

Autonomous AI agents
for Fogo blockchain.

Multi-agent systems that research, deploy, and operate DeFi tools on Fogo. Self-healing, memory-driven, no human in the loop. Real on-chain execution.

smartcoded-labs / fogo-agent.js
1 // Fogo agent: self-healing oracle + staking
2 const agent = await spawnAgent({
3   name: 'fogofi-oracle',
4   chain: 'fogo',
5   memory: 'main.sqlite',
6   skills: [
7     'pyth-sse', 'pool-prices',
8     'self-restart', 'tg-alert',
9   ],
10   cron: '*/5 * * * *',
11 });
12 await agent.deploy();
13 // running 24/7 on Fogo mainnet
000
Followers
@smartcoded on X
7+
Live agents
running 24/7
5+
Live products
on Fogo
99.9%
Uptime
self-healed
How it works

Build it once. Let it run for years.

Every agent has memory, skills, and a watchdog. They wake up on schedule, pick up where they left off, and only ask for help when stuck.

STEP 01

Spawn an agent with skills

Each agent gets a name, a chain, persistent memory, and a list of skills. Skills are reusable building blocks: pyth-sse, swap, send, alert, deploy.

STEP 02

Schedule + watchdog

Cron runs the agent on its cadence. A separate watchdog checks that the process is alive every 2 min. Crash? Auto-restart. Token expired? Auto-refresh.

STEP 03

Memory + reconciler

Persistent SQLite memory survives restarts. A reconciler runs every 15 min to fill any gaps the agent missed: failed orders, stuck states, low balances. Alerts to TG.

Live agents

Operating right now

Active in production on Fogo mainnet. Each is a single PM2 process with its own memory, skills, and crash recovery.

📡
fogofi-oracle
online
Pulls FOGO + ecosystem prices from Pyth SSE, CoinGecko, DefiLlama, and on-chain pools. Updates every 5 min.
pyth-ssecmcdefillamaon-chain
🔍
fogofi-indexer
online
Crawls Fogo for token holders, transfers, NFT activity. Powers the FogoFi explorer with 153K+ wallets indexed.
batch-rpcbackfillcrawler
🤖
fogofi-bot
online
Telegram bot for portfolio tracking, IgnitionFi liquid staking, price alerts, whale tracking. 16 commands.
telegramspl-stake-poolwhale-watch
🔌
rpc-proxy
online
Boolean-stripping RPC proxy for Fogo mainnet. Fixes a Solana RPC quirk where some bot SDKs send unsupported boolean params.
fogo-rpcmiddlewarelow-mem
🍃
fogofi-monitor
online
Price monitor + alert pipeline. Pushes FOGO movement notifications to subscribers. 5-min cadence.
price-polltg-push
grants-discovery
online
Scans Karma + ecosystem feeds for new Fogo / Solana grants. Auto-updates the public discovery feed.
karma-apiauto-update
Capabilities

What every agent gets out of the box

Battle-tested primitives. Every new agent inherits these by default.

💾

Persistent memory

SQLite-backed memory survives restarts. Reload state where you left off.

🔁

Self-healing watchdogs

Cron-based watchdog every 2 min. Dead process? Auto-restart with token refresh.

🔐

Multi-LLM

Groq for speed, Anthropic for reasoning, MiniMax fallback. Auto-select per task.

On-chain native

Direct Solana / Fogo / EVM execution. No middleware. spl-stake-pool, vortex, raw RPC.

🔊

Multi-channel alerts

Telegram, browser push, in-app notifications, SSE broadcast. Pick what fits.

📊

Public observability

Read-only API for safe metrics. CORS-open. Embed live data anywhere.

Want to deploy a custom agent?

Need an autonomous bot for your project on Fogo or another SVM chain? Custom agents, integrations, and tooling. DM open.