Open Console →
● On-chain · chain 1370

The contracts — and what each one does

Ramestta Agent OS isn't one big program. It's nine small contracts, each with a single job. Together they let an agent boot, obey your rules, pay its own gas, and run on schedule — with no hidden server. Every address here is a verifiable, upgradeable proxy on RamaScan.

How the pieces fit

One agent, nine cooperating contracts

🚀 BootHelpercreates the agent 👛 Agent Walletholds funds · runs actions 🛡️ Permissionsrules checked first ⛽ Treasurysponsors the gas ⏰ Schedulerruns tasks on time ⚙️ Keepersexecute 🏷️ RNSgives a .rama name 🧠 Memoryshared team state every action → rules → gas → done

The agent wallet is the centre; every value-moving action passes the Permissions rulebook before it happens.

Each contract, in plain words

🚀
AgentBootHelper
The front door. One call creates a whole agent — name, wallet, gas account and rulebook — in a single transaction, so nothing is left half-set-up.
Deploys the wallet, opens the Treasury account, registers identity & permissions atomically.
0x0781EAc0486cB177864586e4DfC2077E8B88bBEa
👛
AgentWallet (beacon)
Each agent's own smart-contract wallet. Holds its funds and executes its actions — but only inside your limits.
Two paths: sovereign execute() by the owner, and executeMeta() — signed by a scoped session key, permission-checked every time.
0x54ac9E097D709482101326AaFB59E990096ebcc3
🛡️
AgentPermissions
The rulebook. Spend caps, allow-lists, human approvals and session-key powers — every value-moving action is checked here first.
Per-token limits, per-(target,selector) capability lists, an approval inbox, and instant pause / revoke.
0xA1C395a5AeF2b584982A1cEC27F10f33D29e25a0
⛽
AgentTreasury
The gas tank. Sponsors agents' transaction fees so they "just work", with a per-agent monthly quota.
Atomic sponsored execution — quota + refund only settle if the agent's action succeeds.
0x2a5EBF934D72d3b4b65F6d4A85dCB8639C8cfD8d
⏰
Scheduler
The heartbeat. Stores "run this at this time" tasks on-chain so an open keeper market executes them — no server needed.
Time / block / condition triggers, prepaid keeper fees, catch-up protection and failure auto-pause.
0xb01dcA10Dff6242c46d69CBB9EfcC514a9995F23
🏷️
RAMANameService (RNS)
The identity layer. Turns a long address into a readable name like mybot.rama.
Search, register, resolve, renew and manage names; the readable identity every agent boots with.
0xde4ACb2fB2b69c96c2312887c2656Ee5Ff6290EB
🏅
AgentReputation
The track record. Turns good on-chain behaviour into a score that can raise an agent's sponsored-gas tier.
Increase-only, allow-listed reporters, per-window caps — reputation can promote a tier but never demote or drain.
0x774a0da308cD92a09BCF08ff896733fdBDC7786a
🧠
AgentMemory
A shared notebook. Lets a team of agents read and write a common, permissioned state to coordinate a job.
Membership-gated "spaces", versioned keys and optimistic writes; values are meant to be client-side encrypted.
0x571e0C76594348038ed4B9361211Ea2A50bd24ac
🛟
SLAInsurancePool
The safety net. Pays capped compensation if a scheduled task provably misses its window — bounded, opt-in cover.
Non-refundable premium, claim bounded to a multiple of premium, per-creator + global epoch budgets.
0x24fb0B59356799bc985AC6B0476Da9e9180de3bf
🏛️

Who controls it: every contract is an upgradeable proxy governed by an on-chain 24-hour timelock, which is driven by a 2-of-3 operations multisig. The logic can improve without ever changing these addresses — and no upgrade can happen instantly or in secret; there's always a public 24-hour window first. See the full safety model →

Want to build on these?

Developer docs →See how it works