Build record
Amúyẹ
builtAn agent procurement system that commissions specialist work for protocol assessments, learns from execution, and applies that experience to later jobs.
- Classification
- Software / Agent system / Hackathon project
- Last updated
- Source
- Open repository
- Live
- Open site
What
Amúyẹ accepts a protocol-assessment objective, budget, deadline, priority and hard constraints, then purchases useful specialist evidence progressively and can stop before unnecessary deeper work.
System facts
- Protocol assessments are decomposed into specialist capabilities.
- The execution controller enforces dependencies, gates, budget and early stopping.
- Sibyl stores execution history and operational lessons across sessions.
- In a controlled repeat run, recalled experience changed the purchase from three specialists costing 95 to two costing 35.
- Recalled experience can change the plan, but it cannot override the job's hard constraints.
- Risk synthesis can use a real Virtuals ACP provider purchase, with ACP spend counted against the client budget.
- The browser console supports proof modes and new assessments, while the programmatic API exposes the same constrained assessment path.
Boundary
- Amúyẹ is limited to evidence-only, risk and security protocol assessments; it is not a general-purpose agent.
- Live ACP spending requires explicit confirmation, and not every specialist is purchased through ACP.
Why
Protocol assessments often need several kinds of evidence, but not every job needs every specialist. Amúyẹ uses execution history to adjust later procurement while keeping the current job's constraints authoritative.
Evidence
- feat: prove Sibyl-backed planning adaptationEstablished the first proof that persisted Sibyl-backed experience could alter later specialist procurement.
- Implement Amúyẹ checkpoints 2-4Implemented the execution controller, specialist stages and initial Virtuals ACP purchase path.
- Complete Amúyẹ learning proofs and judge consoleRecorded the controlled Memory OFF and ON comparison, mandatory-security adaptation and Base settlement proof.
- Connect execution console to live Amúyẹ runtimeConnected the browser execution console to the application runtime.
- Fail live ACP purchases safely without automatic repurchaseStopped failed live ACP purchases from silently triggering another paid attempt.
- Persist assessment history across restartsPersisted assessment jobs so prior runs remain available after a process restart.
- Secure public ACP execution and sync partner proofKept paid ACP execution gated while allowing the public path to publish verified partner proof.
- Configure Vercel as static frontend buildConfigured the browser console for the verified Vercel deployment.
- Amúyẹ live browser consoleVerified public deployment of the Amúyẹ Memory ON interface.
- Virtuals ACP job 75660 fundingBase mainnet transaction placing 0.1 USDC into ACP escrow for job 75660.
- Virtuals ACP job 75660 completion and releaseBase mainnet completion released 0.09 USDC to the risk provider, 0.005 USDC to the evaluator and 0.005 USDC to the platform treasury.
- Virtuals ACP contractVirtuals ACP contract used for the verified Base mainnet settlement.
Log
Published the Amúyẹ browser console.
Configured the static frontend for the verified public deployment without widening its live-purchase authority.
Separated public proof from paid ACP authority.
The public assessment path can sync partner proof while live ACP spending remains behind the controlled execution boundary.
Made assessment history survive restarts.
Assessment jobs now persist across process restarts, keeping prior runs available to the browser console instead of losing them with runtime memory.
Made failed live purchases stop safely.
A failed live ACP purchase no longer triggers an automatic paid replacement attempt.
Connected planning to specialist execution.
Built the controller, specialist stages and ACP path, then connected the execution console to the real application runtime.
Proved memory changed the purchase.
Under the same controlled task conditions, the cold run purchased viability, risk and security for 95. The memory-backed run recalled prior execution experience, stopped after risk and spent 35.
Settled a real specialist purchase on Base.
Virtuals ACP job 75660 moved 0.1 USDC into escrow and completed settlement across the provider, evaluator and platform treasury.
Made memory yield to a hard constraint.
A recalled lesson normally allowed security to be skipped. When security became mandatory, the controller kept the useful ordering but overrode the conflicting memory rule for that job.
Made past execution change a future plan.
Built the first Sibyl-backed planning proof, where operational experience persisted across sessions and could alter later specialist procurement.
Stack
- Python
- TypeScript
- Sibyl
- Virtuals ACP
- SQLite
- Base
