Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
Sort by:
Freelancers sign bad contracts because they forget. This agent remembers your rules and past risks permanently in CockroachDB to draft safe counter-offers.
Kill the agent. Not its memory. AFTERLIFE lets ephemeral AI agents survive runtime failure by restoring identity, task state, commitments, and semantic memory from CockroachDB.
A real-time truth layer that stops AI agents from acting on stale, superseded, or revoked memories by revalidating critical memory at commit time.
RelayIQ never lets a ticket start from zero - it briefs your team by day and solves it by night.
I’m building an agentic CRM platform for The Fortified Enterprise Fleet, powered by Google Gemini Enterprise and ADK, to automate customer qualification, outreach, risk analysis, and decision-making.
OrbitOne is an autonomous AI agent that turns a single natural-language request into a coordinated event plan; checking rooms, budgets, and tasks, then asking for approval when it matters
From information overload to intelligent action.
When one agent's commit invalidates another's plan, INTERLOCK finds which steps actually died and redoes only those. Semantic concurrency control for parallel agents, built on CockroachDB.
CaseMind: an AML investigation copilot with real memory - CockroachDB vector search + MCP retrieval fed by AWS Bedrock, so every decision cites its evidence instead of just asserting it.
Normal agents remember conversations. Sentinel remembers consequences — an incident-response command center whose memory is CockroachDB, not a context window.
Judge the decision, not the hindsight. HindSight reconstructs what an AI agent could know at decision time, so a wrong outcome stops automatically meaning a faulty agent.
Retractable agent memory. When a lot is recalled, Rescind pulls back every conclusion the agent built on it - in one transaction, with proof of what the agent knew before and after.
CourtSignal AI uses AI to analyze performance, exposure, and growth, helping recruiters discover overlooked athletes before traditional scouting systems do.
Upload once, extract once, remember forever, forget honestly. A decaying agentic memory layer on CockroachDB with vector + graph retrieval, powered by Amazon Bedrock.
Community groups lose track of who asked for help. Backstop gives them a memory: every request, what happened to it, and the ones nobody answered.
Selfie to Glow-Up: AI skin analysis, personalized style, and smart local beauty shopping in one app.
AIGo keeps software projects moving. Gemini suggests the next safe step, scoped coding agents do approved work, local validation checks the result, and a human decides when it is done.
AI agents lie when their memory is poisoned. PQBS is the immune system - 8 signals check whether every fact deserves to be believed. Built on CockroachDB + AWS Bedrock.
An AI-powered cybersecurity tool that analyzes network vulnerabilities, identifies security risks, and provides actionable recommendations to strengthen network protection.
prescription ai solution
Most records disappear because nobody writes the few hundred people who'd play them. Spindle does it every night
21 Gemini agents swarm Plenva, analyzing SMEs via 33 KPIs + viability scoring in minutes. Proof Gemini scales beyond chat to real enterprise decisions and capital calls.
On-call triage that remembers. A new incident recalls the fix that worked 9 days ago at 97% similarity in 2.5ms — CockroachDB is the agent's memory and its execution state.
Community Hero AI turns local civic complaints into verified, prioritized, and accountable action using AI, community validation, and human oversight.
