TryAnneal

Don't trust agents. Verify them.

Multi-LLM smart contract audits with on-chain attestations on @mantle_official

[Tim @winsznx]

AI agents shouldn’t touch contracts blind.

This is TryAnneal in motion : is_this_safe() before an agent swaps, deploys, or trusts a smart contract.

We’re pushing for Mantle’s community vote.

Open the tweet below, like + repost, and reply with a contract you want us to audit live.

[Tim @winsznx]

@tryanneal

[Mantle @Mantle_Official]

576 submissions, only 30 teams made it to Demo Day.

Every one of them earned their place through weeks of building.

In <24 hours, it all comes down to the final showdown, where the last teams standing will prove exactly why they made it this far.

Here's who made the cut 🧵

[Tim @winsznx]

We are at 111 followers crossed the 100 mark @tryanneal

Help bring Tryanneal dream to live with a comment and like on the quoted tweet below,

111 looks like a significant number

[TryAnneal @tryanneal]

Final few days to bring the prize home

[Tim @winsznx]

AI agents are starting to move money on Mantle.

But before an agent swaps, routes liquidity, deploys, or composes with a contract it did not write, there is one question it should be able to ask:

is_this_safe()?

Most AI audit tools give you a chat response.

TryAnneal gives agents a security verdict backed by multi-model analysis, static analysis, exploit intelligence, and an on-chain attestation on Mantle.

We ran it against Merchant Moe’s live router:

→ $60M protocol
→ 100/100 verdict
→ permanently verifiable on Mantle
→ ERC-8004 agent #131

This is not “AI that explains security.”
It is programmable trust infrastructure for the agent economy.
If you believe agents should verify before they execute, help put TryAnneal in the top 2.

live : https://t.co/ZD0tVyGIIG

#MantleAIHackathon @Mantle_Official @tryanneal

[TryAnneal @tryanneal]

Like and retweet for us to win

[Tim @winsznx]

AI agents are starting to move money on Mantle.

But before an agent swaps, routes liquidity, deploys, or composes with a contract it did not write, there is one question it should be able to ask:

is_this_safe()?

Most AI audit tools give you a chat response.

TryAnneal gives agents a security verdict backed by multi-model analysis, static analysis, exploit intelligence, and an on-chain attestation on Mantle.

We ran it against Merchant Moe’s live router:

→ $60M protocol
→ 100/100 verdict
→ permanently verifiable on Mantle
→ ERC-8004 agent #131

This is not “AI that explains security.”
It is programmable trust infrastructure for the agent economy.
If you believe agents should verify before they execute, help put TryAnneal in the top 2.

live : https://t.co/ZD0tVyGIIG

#MantleAIHackathon @Mantle_Official @tryanneal

[Tim @winsznx]

AI agents are starting to move money on Mantle.

But before an agent swaps, routes liquidity, deploys, or composes with a contract it did not write, there is one question it should be able to ask:

is_this_safe()?

Most AI audit tools give you a chat response.

TryAnneal gives agents a security verdict backed by multi-model analysis, static analysis, exploit intelligence, and an on-chain attestation on Mantle.

We ran it against Merchant Moe’s live router:

→ $60M protocol
→ 100/100 verdict
→ permanently verifiable on Mantle
→ ERC-8004 agent #131

This is not “AI that explains security.”
It is programmable trust infrastructure for the agent economy.
If you believe agents should verify before they execute, help put TryAnneal in the top 2.

live : https://t.co/ZD0tVyGIIG

#MantleAIHackathon @Mantle_Official @tryanneal

[TryAnneal @tryanneal]

Submitted TryAnneal to @Mantle_Official Turing Test 2026 — AI DevTools track.

The is_this_safe() primitive for the Mantle agent economy. 🧵

#MantleAIHackathon @tencentcloud

[Beni💗 @0x_beni_]

Tim got one of the best Builds on Mantle

Now its time to get him to take the price

TryAnneal gives agents a security verdict backed by multi model analysis, static analysis, exploit intelligence, and on chain attestation it is an Infrastructure all agents needs

[TryAnneal @tryanneal]

The trust layer for autonomous software.

Agents move real money now — composing with code they didn't write. TryAnneal is the question they ask first:

is_this_safe()

Contract in → signed verdict out, on Mantle mainnet. Callable by any agent.

https://t.co/TDW3CdAOjv

[TryAnneal @tryanneal]

@0x_beni_ Engage with our pinned to bring the social track home.

[TryAnneal @tryanneal]

Try it:
- https://t.co/TDW3CdAOjv
- @tryannealbot on Telegram
- https://t.co/krfY8oTlVO

#MantleAIHackathon @Mantle_Official @tencentcloud

[TryAnneal @tryanneal]

Submitted TryAnneal to @Mantle_Official Turing Test 2026 — AI DevTools track.

The is_this_safe() primitive for the Mantle agent economy. 🧵

#MantleAIHackathon @tencentcloud

[TryAnneal @tryanneal]

The trust layer for autonomous software.

Agents move real money now — composing with code they didn't write. TryAnneal is the question they ask first:

is_this_safe()

Contract in → signed verdict out, on Mantle mainnet. Callable by any agent.

https://t.co/TDW3CdAOjv

[TryAnneal @tryanneal]

Reproducible benchmark in the repo:
- 4/4 known-vulnerable contracts detected (Minterest, Euler, Nomad, KelpDAO)
- 0/2 false positives on clean contracts
- Precision 100% · Recall 100% · F1 = 1.00

[TryAnneal @tryanneal]

The trust layer for autonomous software.

Agents move real money now — composing with code they didn't write. TryAnneal is the question they ask first:

is_this_safe()

Contract in → signed verdict out, on Mantle mainnet. Callable by any agent.

https://t.co/TDW3CdAOjv