Skip to content

Cerebral Valley · Anthropic · 2026-04-21 to 2026-04-27

Built with Opus 4.7: a Claude Code hackathon

Public gallery: every submissionEvent page ↗

Projects
288
Winners
9
With repo
99%

Winners

All other submissions

279Search and filter all 279

Ujian SD

Ujian SD turns a single sentence — "Pendidikan Pancasila, kelas 5, sumatif tengah semester, tema sila ke-3" — into a print-ready exam sheet: 20 questions, mixed types (multiple choice, complex MCQ, true/false, short answ

education

Tortilya

In five days, one researcher and Claude Opus 4.7 broke the most capable LLMs on the planet — twenty-four different ways — then turned every failure into a lesson, a defense, and a public certification course.

securityeducation

APPRA

APPRA — A Curriculum Assistant for Spanish Vocational Training APPRA helps the three audiences who actually need Spain's Vocational Training (FP) curriculum — teachers, students, and families — work with it.

education

StinKit

StinKit is an open-source code intelligence platform that indexes your codebase into a structural dependency graph and lets you query it nine different ways — through a CLI, a web dashboard, or an AI agent via MCP.

dev toolsvision

Two+Aliens

God Bless The United States Of Aliens is a non-looping, eighteen-minute AI-voiced ceremony for the 61st International Art Exhibition — La Biennale di Venezia 2026, where it appears as a guest work in Domus Diasporica (Pa

creative/musicvoice

RoadWatch

RoadWatch is an autonomous multi-agent pavement surveyor that grades road condition at scale using Mapillary street-level imagery — no custom CV model, no windshield survey crew, no $250k engineering contract.

visionrepair/trades

Poligent

Poligent, a policy simulation platform, is a multi-agent system that takes a government policy document and streams parallel reasoning from four demographically-grounded UK population archetypes using Claude Opus 4.7 wit

financeagents

Vivax

Clinical research leads spend weeks manually identifying care gaps and overprescription patterns in their patient population — querying EHRs, cross-referencing guidelines, validating statistically, packaging intervention

healthscienceagents

Jesus Rodriguez

AI to Widget is an open-source toolkit designed to turn any existing web application into one with its own conversational agent — grounded in the app's real data, able to take real actions on behalf of the user with thei

dev toolsagents

Jesus Lanzarote Rodriguez Quinones Galindo

JournalShift

JournalShift is a tool-augmented agentic app: two Opus 4.7 agents running on Anthropic's Managed Agents platform, a Smart Journal Finder that queries OpenAlex, Crossref, and SCImago to rank candidate journals, and a Temp

productivitydev tools

Lemonode

You describe what you want covered in one sentence: "Chicago weekends with the kids, every Friday at 7am" or "Iran–Israel daily briefing, primary sources, deep" or "Musicals & Live concerts near Paris, every week".

agentsproductivity

Axiom

Axiom — autonomous software-engineering swarm that builds its own skills Axiom is a swarm of nine specialised AI roles that solves Terminal-Bench 2.0 tasks by synthesising its own skill library through a learning-and-ite

agentsdev tools

SAFER

SAFER is an open-source agent control plane that turns any AI agent running on LangChain, Google ADK, AWS Strands, raw Anthropic, raw OpenAI, OpenAI Agents SDK, AWS Bedrock, or CrewAI into one observable, governable, aud

agentssecurity

Nagi

Nagi is an AI elder-care product where the AI's job is to route routine requests and to step aside the moment a human family member should take over — and where that family member can self-host the entire stack on a $5 s

healthvoice

NISP

NISP is a 5-layer neuro-symbolic pipeline that reads a foundation model's predicted brain response to autonomous systems videos and produces a formally certified anomaly verdict: slow enough for a Lean 4 proof, fast enou

sciencevision

Inferred from GitHub

24

Repos whose README mentions this hackathon. These are not confirmed submissions. Open one to see the matching line.

inferred

liminal agents

Three bounded agents (Analyst, SDR, Auditor) that do agency-priced B2B work locally. Each refuses out of lane and names the right agent. SQLCipher-encrypted vault keeps the record. Built for the AI Agent Economy Hackathon (AgentHansa, Apr 25, 2026).

agentssecurity