Nusa
Nusa: an AI agent that rewrites AMD's CPU inference kernels to make models run faster.
View project
Verdict
Verdict is an autonomous AI agent that scouts any hackathon's submitted projects and ranks them against your own judging rubric — turning every hackathon into a courtroom.
ProofRun
ProofRun helps developers answer a critical question before shipping: will this update break behavior users rely on? An AI agent inspects two Git revisions, designs targeted experiments, and proposes repairs. An independent Docker-based verifier runs those experiments against both versions, preserves the original tests, and checks whether the repair actually works. Developers receive an update, skip, or postpone recommendation with recorded evidence and a reviewable patch. In a live synthetic…
Join Vultr Community
Points, levels & badges
Enter challenges & submit builds
Register to events & meetups
Get your work featured
Older than a Month
ProofRun helps developers answer a critical question before shipping: will this update break behavior users rely on? An AI agent inspects two Git revisions, designs targeted experiments, and proposes repairs. An independent Docker-based verifier runs those experiments against both versions, preserves the original tests, and checks whether the repair actually works. Developers receive an update, skip, or postpone recommendation with recorded evidence and a reviewable patch. In a live synthetic…
Full-Stack Self-Healing DevOps & Security Copilot The Concept: An AI operations engineer that doesn't just suggest code fixes—it monitors cloud infra, detects uptime/security drops, automatically provisions fixes, and generates audit reports for enterprise compliance.
AI agent to reduce cloud costs
Give the agent a stranger's bug report. Get back a patch you can try, with checks the agent could not fake, while every line of untrusted code runs in a disposable sandbox.
Sandbox inside of a sandbox. Agent codebase remediation.
Featured
Featured
Nusa: an AI agent that rewrites AMD's CPU inference kernels to make models run faster.
A PR check for ML training code that executes the math instead of reading the diff, in gVisor sandboxes on Vultr, behind NetBird with zero open ports.
MiniAVO runs an evolutionary loop over GPU kernels (matmul_v2, vectorsum_v2, cholesky, trimul_alphafold3) on target GPUs from A100, H100, B200, GB10, etc.
Upgrade chamber is automated dependency upgrade testing and repair service.
NebulaCode is a web-based autonomous coding agent for enterprise software delivery. It moves beyond a copilot by planning work, routing between specialist agents, executing Codespace, validating results, reviewing code, and persisting project memory.
5 specialist LLMs investigate your production incident. One generates hypotheses. One tests evidence. One synthesizes root cause. One red-teams the conclusion. One writes the report. Wrong answers get rejected with proof. Alert to post-mortem: 93 seconds.
Autonomous incident response: Pageless spawns an agent tree on each alert, runs real kubectl/Prometheus commands, and shows the operator the literal proposed fix, the classifier rule, and rejected alternatives before they approve.